[Improvement] Make embedchain home dir configurable (#1341)

.github/workflows/ci.yml

@@ -39,7 +39,7 @@ jobs:
           path: .venv
           key: venv-${{ runner.os }}-${{ hashFiles('**/poetry.lock') }}
       - name: Install dependencies
-        run: poetry install --all-extras
+        run: make install_all
         if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
       - name: Lint with ruff
         run: make lint

.gitignore

@@ -165,6 +165,7 @@ cython_debug/
 # Database
 db
 test-db
+!embedchain/core/db/
 
 .vscode
 .idea/

Makefile

@@ -11,6 +11,7 @@ install:
 
 install_all:
 	poetry install --all-extras
+	poetry run pip install pinecone-text pinecone-client langchain-anthropic
 
 install_es:
 	poetry install --extras elasticsearch
@@ -37,6 +38,12 @@ clean:
 lint:
 	poetry run ruff .
 
+build:
+	poetry build
+
+publish:
+	poetry publish
+
 # for example: make test file=tests/test_factory.py
 test:
 	poetry run pytest $(file)

README.md

@@ -2,10 +2,6 @@
   <img src="docs/logo/dark.svg" width="400px" alt="Embedchain Logo">
 </p>
 
-<p align="center">
-  <a href="https://runacap.com/ross-index/q3-2023/" target="_blank" rel="noopener"><img style="width: 260px; height: 56px" src="https://runacap.com/wp-content/uploads/2023/10/ROSS_badge_black_Q3_2023.svg" alt="ROSS Index - Fastest Growing Open-Source Startups in Q3 2023 | Runa Capital" width="260" height="56"/></a>
-</p>
-
 <p align="center">
   <a href="https://pypi.org/project/embedchain/">
     <img src="https://img.shields.io/pypi/v/embedchain" alt="PyPI">
@@ -34,9 +30,9 @@
 
 ## What is Embedchain?
 
-Embedchain is an Open Source RAG Framework that makes it easy to create and deploy AI apps. At its core, Embedchain follows the design principle of being *"Conventional but Configurable"* to serve both software engineers and machine learning engineers.
+Embedchain is an Open Source Framework for personalizing LLM responses. It makes it easy to create and deploy personalized AI apps. At its core, Embedchain follows the design principle of being *"Conventional but Configurable"* to serve both software engineers and machine learning engineers.
 
-Embedchain streamlines the creation of Retrieval-Augmented Generation (RAG) applications, offering a seamless process for managing various types of unstructured data. It efficiently segments data into manageable chunks, generates relevant embeddings, and stores them in a vector database for optimized retrieval. With a suite of diverse APIs, it enables users to extract contextual information, find precise answers, or engage in interactive chat conversations, all tailored to their own data.
+Embedchain streamlines the creation of personalized LLM applications, offering a seamless process for managing various types of unstructured data. It efficiently segments data into manageable chunks, generates relevant embeddings, and stores them in a vector database for optimized retrieval. With a suite of diverse APIs, it enables users to extract contextual information, find precise answers, or engage in interactive chat conversations, all tailored to their own data.
 
 ## 🔧 Quick install
 
@@ -64,15 +60,15 @@ import os
 from embedchain import App
 
 # Create a bot instance
-os.environ["OPENAI_API_KEY"] = "YOUR API KEY"
-elon_bot = App()
+os.environ["OPENAI_API_KEY"] = "<YOUR_API_KEY>"
+app = App()
 
 # Embed online resources
-elon_bot.add("https://en.wikipedia.org/wiki/Elon_Musk")
-elon_bot.add("https://www.forbes.com/profile/elon-musk")
+app.add("https://en.wikipedia.org/wiki/Elon_Musk")
+app.add("https://www.forbes.com/profile/elon-musk")
 
-# Query the bot
-elon_bot.query("How many companies does Elon Musk run and name those?")
+# Query the app
+app.query("How many companies does Elon Musk run and name those?")
 # Answer: Elon Musk currently runs several companies. As of my knowledge, he is the CEO and lead designer of SpaceX, the CEO and product architect of Tesla, Inc., the CEO and founder of Neuralink, and the CEO and founder of The Boring Company. However, please note that this information may change over time, so it's always good to verify the latest updates.
 ```
 

configs/ollama.yaml

@@ -5,6 +5,7 @@ llm:
     temperature: 0.5
     top_p: 1
     stream: true
+    base_url: http://localhost:11434
 
 embedder:
   provider: huggingface

docs/components/data-sources/data-type-handling.mdx

@@ -37,7 +37,14 @@ Create a local index:
 ```python
 from embedchain import App
 
-naval_chat_bot = App()
+config = {
+    "app": {
+        "config": {
+            "id": "app-1"
+        }
+    }
+}
+naval_chat_bot = App.from_config(config=config)
 naval_chat_bot.add("https://www.youtube.com/watch?v=3qHkcs3kG44")
 naval_chat_bot.add("https://navalmanack.s3.amazonaws.com/Eric-Jorgenson_The-Almanack-of-Naval-Ravikant_Final.pdf")
 ```
@@ -47,7 +54,14 @@ You can reuse the local index with the same code, but without adding new documen
 ```python
 from embedchain import App
 
-naval_chat_bot = App()
+config = {
+    "app": {
+        "config": {
+            "id": "app-1"
+        }
+    }
+}
+naval_chat_bot = App.from_config(config=config)
 print(naval_chat_bot.query("What unique capacity does Naval argue humans possess when it comes to understanding explanations or concepts?"))
 ```
 
@@ -58,7 +72,14 @@ You can reset the app by simply calling the `reset` method. This will delete the
 ```python
 from embedchain import App
 
-app = App()
+app = App()config = {
+    "app": {
+        "config": {
+            "id": "app-1"
+        }
+    }
+}
+naval_chat_bot = App.from_config(config=config)
 app.add("https://www.youtube.com/watch?v=3qHkcs3kG44")
 app.reset()
 ```

docs/components/data-sources/excel-file.mdx

@@ -0,0 +1,18 @@
+---
+title: '📄 Excel file'
+---
+
+### Excel file
+
+To add any xlsx/xls file, use the data_type as `excel_file`. `excel_file` allows remote urls and conventional file paths. Eg:
+
+```python
+from embedchain import App
+
+app = App()
+app.add('https://example.com/content/intro.xlsx', data_type="excel_file")
+# Or add file using the local file path on your system
+# app.add('content/intro.xls', data_type="excel_file")
+
+app.query("Give brief information about data.")
+```

docs/components/data-sources/github.mdx

@@ -29,11 +29,13 @@ response = app.query("What is Embedchain?")
 ```
 The `add` function of the app will accept any valid github query with qualifiers. It only supports loading github code, repository, issues and pull-requests.
 <Note>
-You must provide qualifiers `type:` and `repo:` in the query. The `type:` qualifier can be a combination of `code`, `repo`, `pr`, `issue`. The `repo:` qualifier must be a valid github repository name.
+You must provide qualifiers `type:` and `repo:` in the query. The `type:` qualifier can be a combination of `code`, `repo`, `pr`, `issue`, `branch`, `file`. The `repo:` qualifier must be a valid github repository name.
 </Note>
 
 <Card title="Valid queries" icon="lightbulb" iconType="duotone" color="#ca8b04">
     - `repo:embedchain/embedchain type:repo` - to load the repository
+    - `repo:embedchain/embedchain type:branch name:feature_test` - to load the branch of the repository
+    - `repo:embedchain/embedchain type:file path:README.md` - to load the specific file of the repository
     - `repo:embedchain/embedchain type:issue,pr` - to load the issues and pull-requests of the repository
     - `repo:embedchain/embedchain type:issue state:closed` - to load the closed issues of the repository
 </Card>

docs/components/embedding-models.mdx

@@ -13,6 +13,8 @@ Embedchain supports several embedding models from the following providers:
   <Card title="GPT4All" href="#gpt4all"></Card>
   <Card title="Hugging Face" href="#hugging-face"></Card>
   <Card title="Vertex AI" href="#vertex-ai"></Card>
+  <Card title="NVIDIA AI" href="#nvidia-ai"></Card>
+  <Card title="Cohere" href="#cohere"></Card>
 </CardGroup>
 
 ## OpenAI
@@ -220,3 +222,139 @@ embedder:
 ```
 
 </CodeGroup>
+
+## NVIDIA AI
+
+[NVIDIA AI Foundation Endpoints](https://www.nvidia.com/en-us/ai-data-science/foundation-models/) let you quickly use NVIDIA's AI models, such as Mixtral 8x7B, Llama 2 etc, through our API. These models are available in the [NVIDIA NGC catalog](https://catalog.ngc.nvidia.com/ai-foundation-models), fully optimized and ready to use on NVIDIA's AI platform. They are designed for high speed and easy customization, ensuring smooth performance on any accelerated setup.
+
+
+### Usage
+
+In order to use embedding models and LLMs from NVIDIA AI, create an account on [NVIDIA NGC Service](https://catalog.ngc.nvidia.com/).
+
+Generate an API key from their dashboard. Set the API key as `NVIDIA_API_KEY` environment variable. Note that the `NVIDIA_API_KEY` will start with `nvapi-`.
+
+Below is an example of how to use LLM model and embedding model from NVIDIA AI:
+
+<CodeGroup>
+
+```python main.py
+import os
+from embedchain import App
+
+os.environ['NVIDIA_API_KEY'] = 'nvapi-xxxx'
+
+config = {
+    "app": {
+        "config": {
+            "id": "my-app",
+        },
+    },
+    "llm": {
+        "provider": "nvidia",
+        "config": {
+            "model": "nemotron_steerlm_8b",
+        },
+    },
+    "embedder": {
+        "provider": "nvidia",
+        "config": {
+            "model": "nvolveqa_40k",
+            "vector_dimension": 1024,
+        },
+    },
+}
+
+app = App.from_config(config=config)
+
+app.add("https://www.forbes.com/profile/elon-musk")
+answer = app.query("What is the net worth of Elon Musk today?")
+# Answer: The net worth of Elon Musk is subject to fluctuations based on the market value of his holdings in various companies.
+# As of March 1, 2024, his net worth is estimated to be approximately $210 billion. However, this figure can change rapidly due to stock market fluctuations and other factors.
+# Additionally, his net worth may include other assets such as real estate and art, which are not reflected in his stock portfolio.
+```
+</CodeGroup>
+
+
+## Cohere
+
+To use embedding models and LLMs from COHERE, create an account on [COHERE](https://dashboard.cohere.com/welcome/login?redirect_uri=%2Fapi-keys).
+
+Generate an API key from their dashboard. Set the API key as `COHERE_API_KEY` environment variable.
+
+Once you have obtained the key, you can use it like this:
+
+<CodeGroup>
+
+```python main.py
+import os
+from embedchain import App
+
+os.environ['COHERE_API_KEY'] = 'xxx'
+
+# load embedding model configuration from config.yaml file
+app = App.from_config(config_path="config.yaml")
+```
+
+```yaml config.yaml
+embedder:
+  provider: cohere
+  config:
+    model: 'embed-english-light-v3.0'
+```
+
+</CodeGroup>
+
+* Cohere has few embedding models: `embed-english-v3.0`, `embed-multilingual-v3.0`, `embed-multilingual-light-v3.0`, `embed-english-v2.0`, `embed-english-light-v2.0` and `embed-multilingual-v2.0`. Embedchain supports all these models. Below you can find YAML config for all:
+
+<CodeGroup>
+
+```yaml embed-english-v3.0.yaml
+embedder:
+  provider: cohere
+  config:
+    model: 'embed-english-v3.0'
+    vector_dimension: 1024
+```
+
+```yaml embed-multilingual-v3.0.yaml
+embedder:
+  provider: cohere
+  config:
+    model: 'embed-multilingual-v3.0'
+    vector_dimension: 1024
+```
+
+```yaml embed-multilingual-light-v3.0.yaml
+embedder:
+  provider: cohere
+  config:
+    model: 'embed-multilingual-light-v3.0'
+    vector_dimension: 384
+```
+
+```yaml embed-english-v2.0.yaml
+embedder:
+  provider: cohere
+  config:
+    model: 'embed-english-v2.0'
+    vector_dimension: 4096
+```
+
+```yaml embed-english-light-v2.0.yaml
+embedder:
+  provider: cohere
+  config:
+    model: 'embed-english-light-v2.0'
+    vector_dimension: 1024
+```
+
+```yaml embed-multilingual-v2.0.yaml
+embedder:
+  provider: cohere
+  config:
+    model: 'embed-multilingual-v2.0'
+    vector_dimension: 768
+```
+
+</CodeGroup>

docs/components/introduction.mdx

@@ -9,4 +9,5 @@ You can configure following components
 * [Data Source](/components/data-sources/overview)
 * [LLM](/components/llms)
 * [Embedding Model](/components/embedding-models)
-* [Vector Database](/components/vector-databases)
+* [Vector Database](/components/vector-databases)
+* [Evaluation](/components/evaluation)

docs/components/llms.mdx

@@ -22,6 +22,8 @@ Embedchain comes with built-in support for various popular large language models
   <Card title="Vertex AI" href="#vertex-ai"></Card>
   <Card title="Mistral AI" href="#mistral-ai"></Card>
   <Card title="AWS Bedrock" href="#aws-bedrock"></Card>
+  <Card title="Groq" href="#groq"></Card>
+  <Card title="NVIDIA AI" href="#nvidia-ai"></Card>
 </CardGroup>
 
 ## OpenAI
@@ -81,7 +83,7 @@ Embedchain supports OpenAI [Function calling](https://platform.openai.com/docs/g
       b: int = Field(..., description="Second integer")
   ```
 </Accordion>
-  
+
 <Accordion title="Python function">
   ```python
   def multiply(a: int, b: int) -> int:
@@ -342,6 +344,7 @@ llm:
     temperature: 0.5
     top_p: 1
     stream: true
+    base_url: 'http://localhost:11434'
 ```
 
 </CodeGroup>
@@ -450,7 +453,15 @@ pip install --upgrade 'embedchain[huggingface-hub]'
 
 First, set `HUGGINGFACE_ACCESS_TOKEN` in environment variable which you can obtain from [their platform](https://huggingface.co/settings/tokens).
 
-Once you have the token, load the app using the config yaml file:
+You can load the LLMs from Hugging Face using three ways:
+
+- [Hugging Face Hub](#hugging-face-hub)
+- [Hugging Face Local Pipelines](#hugging-face-local-pipelines)
+- [Hugging Face Inference Endpoint](#hugging-face-inference-endpoint)
+
+### Hugging Face Hub
+
+To load the model from Hugging Face Hub, use the following code:
 
 <CodeGroup>
 
@@ -460,24 +471,49 @@ from embedchain import App
 
 os.environ["HUGGINGFACE_ACCESS_TOKEN"] = "xxx"
 
-# load llm configuration from config.yaml file
-app = App.from_config(config_path="config.yaml")
-```
+config = {
+  "app": {"config": {"id": "my-app"}},
+  "llm": {
+      "provider": "huggingface",
+      "config": {
+          "model": "bigscience/bloom-1b7",
+          "top_p": 0.5,
+          "max_length": 200,
+          "temperature": 0.1,
+      },
+  },
+}
 
-```yaml config.yaml
-llm:
-  provider: huggingface
-  config:
-    model: 'google/flan-t5-xxl'
-    temperature: 0.5
-    max_tokens: 1000
-    top_p: 0.5
-    stream: false
+app = App.from_config(config=config)
 ```
 </CodeGroup>
 
-### Custom Endpoints
+### Hugging Face Local Pipelines
 
+If you want to load the locally downloaded model from Hugging Face, you can do so by following the code provided below:
+
+<CodeGroup>
+```python main.py
+from embedchain import App
+
+config = {
+  "app": {"config": {"id": "my-app"}},
+  "llm": {
+      "provider": "huggingface",
+      "config": {
+          "model": "Trendyol/Trendyol-LLM-7b-chat-v0.1",
+          "local": True,  # Necessary if you want to run model locally
+          "top_p": 0.5,
+          "max_tokens": 1000,
+          "temperature": 0.1,
+      },
+  }
+}
+app = App.from_config(config=config)
+```
+</CodeGroup>
+
+### Hugging Face Inference Endpoint
 
 You can also use [Hugging Face Inference Endpoints](https://huggingface.co/docs/inference-endpoints/index#-inference-endpoints) to access custom endpoints. First, set the `HUGGINGFACE_ACCESS_TOKEN` as above.
 
@@ -486,35 +522,23 @@ Then, load the app using the config yaml file:
 <CodeGroup>
 
 ```python main.py
-import os
 from embedchain import App
 
-os.environ["HUGGINGFACE_ACCESS_TOKEN"] = "xxx"
+config = {
+  "app": {"config": {"id": "my-app"}},
+  "llm": {
+      "provider": "huggingface",
+      "config": {
+        "endpoint": "https://api-inference.huggingface.co/models/gpt2",
+        "model_params": {"temprature": 0.1, "max_new_tokens": 100}
+      },
+  },
+}
+app = App.from_config(config=config)
 
-# load llm configuration from config.yaml file
-app = App.from_config(config_path="config.yaml")
-```
-
-```yaml config.yaml
-llm:
-  provider: huggingface
-  config:
-    endpoint: https://api-inference.huggingface.co/models/gpt2 # replace with your personal endpoint
 ```
 </CodeGroup>
 
-If your endpoint requires additional parameters, you can pass them in the `model_kwargs` field:
-
-```
-llm:
-  provider: huggingface
-  config:
-    endpoint: <YOUR_ENDPOINT_URL_HERE>
-    model_kwargs:
-      max_new_tokens: 100
-      temperature: 0.5
-```
-
 Currently only supports `text-generation` and `text2text-generation` for now [[ref](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html?highlight=huggingfaceendpoint#)].
 
 See langchain's [hugging face endpoint](https://python.langchain.com/docs/integrations/chat/huggingface#huggingfaceendpoint) for more information. 
@@ -654,4 +678,112 @@ llm:
 </Note>
 
 <br/ >
+
+## Groq
+
+[Groq](https://groq.com/) is the creator of the world's first Language Processing Unit (LPU), providing exceptional speed performance for AI workloads running on their LPU Inference Engine.
+
+
+### Usage
+
+In order to use LLMs from Groq, go to their [platform](https://console.groq.com/keys) and get the API key.
+
+Set the API key as `GROQ_API_KEY` environment variable or pass in your app configuration to use the model as given below in the example.
+
+<CodeGroup>
+
+```python main.py
+import os
+from embedchain import App
+
+# Set your API key here or pass as the environment variable
+groq_api_key = "gsk_xxxx"
+
+config = {
+    "llm": {
+        "provider": "groq",
+        "config": {
+            "model": "mixtral-8x7b-32768",
+            "api_key": groq_api_key,
+            "stream": True
+        }
+    }
+}
+
+app = App.from_config(config=config)
+# Add your data source here
+app.add("https://docs.embedchain.ai/sitemap.xml", data_type="sitemap")
+app.query("Write a poem about Embedchain")
+
+# In the realm of data, vast and wide,
+# Embedchain stands with knowledge as its guide.
+# A platform open, for all to try,
+# Building bots that can truly fly.
+
+# With REST API, data in reach,
+# Deployment a breeze, as easy as a speech.
+# Updating data sources, anytime, anyday,
+# Embedchain's power, never sway.
+
+# A knowledge base, an assistant so grand,
+# Connecting to platforms, near and far.
+# Discord, WhatsApp, Slack, and more,
+# Embedchain's potential, never a bore.
+```
+</CodeGroup>
+
+## NVIDIA AI
+
+[NVIDIA AI Foundation Endpoints](https://www.nvidia.com/en-us/ai-data-science/foundation-models/) let you quickly use NVIDIA's AI models, such as Mixtral 8x7B, Llama 2 etc, through our API. These models are available in the [NVIDIA NGC catalog](https://catalog.ngc.nvidia.com/ai-foundation-models), fully optimized and ready to use on NVIDIA's AI platform. They are designed for high speed and easy customization, ensuring smooth performance on any accelerated setup.
+
+
+### Usage
+
+In order to use LLMs from NVIDIA AI, create an account on [NVIDIA NGC Service](https://catalog.ngc.nvidia.com/).
+
+Generate an API key from their dashboard. Set the API key as `NVIDIA_API_KEY` environment variable. Note that the `NVIDIA_API_KEY` will start with `nvapi-`.
+
+Below is an example of how to use LLM model and embedding model from NVIDIA AI:
+
+<CodeGroup>
+
+```python main.py
+import os
+from embedchain import App
+
+os.environ['NVIDIA_API_KEY'] = 'nvapi-xxxx'
+
+config = {
+    "app": {
+        "config": {
+            "id": "my-app",
+        },
+    },
+    "llm": {
+        "provider": "nvidia",
+        "config": {
+            "model": "nemotron_steerlm_8b",
+        },
+    },
+    "embedder": {
+        "provider": "nvidia",
+        "config": {
+            "model": "nvolveqa_40k",
+            "vector_dimension": 1024,
+        },
+    },
+}
+
+app = App.from_config(config=config)
+
+app.add("https://www.forbes.com/profile/elon-musk")
+answer = app.query("What is the net worth of Elon Musk today?")
+# Answer: The net worth of Elon Musk is subject to fluctuations based on the market value of his holdings in various companies.
+# As of March 1, 2024, his net worth is estimated to be approximately $210 billion. However, this figure can change rapidly due to stock market fluctuations and other factors.
+# Additionally, his net worth may include other assets such as real estate and art, which are not reflected in his stock portfolio.
+```
+</CodeGroup>
+
+<br/ >
+
 <Snippet file="missing-llm-tip.mdx" />

docs/components/vector-databases/pinecone.mdx

@@ -7,7 +7,7 @@ title: Pinecone
 Install pinecone related dependencies using the following command:
 
 ```bash
-pip install --upgrade 'embedchain[pinecone]'
+pip install --upgrade 'pinecone-client pinecone-text'
 ```
 
 In order to use Pinecone as vector database, set the environment variable `PINECONE_API_KEY` which you can find on [Pinecone dashboard](https://app.pinecone.io/).
@@ -98,6 +98,9 @@ app.add("/path/to/file.pdf", data_type="pdf_file", namespace="my-namespace")
 
 # Query
 app.query("<YOUR QUESTION HERE>", namespace="my-namespace")
+
+# Chat
+app.chat("<YOUR QUESTION HERE>", namespace="my-namespace")
 ```
 
 Under the hood, Embedchain fetches the relevant chunks from the documents you added by doing hybrid search on the pinecone index.

docs/get-started/introduction.mdx

@@ -4,21 +4,21 @@ title: 📚 Introduction
 
 ## What is Embedchain?
 
-Embedchain is an Open Source RAG Framework that makes it easy to create and deploy AI apps. At its core, Embedchain follows the design principle of being *"Conventional but Configurable"* to serve both software engineers and machine learning engineers.
+Embedchain is an Open Source Framework that makes it easy to create and deploy personalized AI apps. At its core, Embedchain follows the design principle of being *"Conventional but Configurable"* to serve both software engineers and machine learning engineers.
 
-Embedchain streamlines the creation of RAG applications, offering a seamless process for managing various types of unstructured data. It efficiently segments data into manageable chunks, generates relevant embeddings, and stores them in a vector database for optimized retrieval. With a suite of diverse APIs, it enables users to extract contextual information, find precise answers, or engage in interactive chat conversations, all tailored to their own data.
+Embedchain streamlines the creation of personalized LLM applications, offering a seamless process for managing various types of unstructured data. It efficiently segments data into manageable chunks, generates relevant embeddings, and stores them in a vector database for optimized retrieval. With a suite of diverse APIs, it enables users to extract contextual information, find precise answers, or engage in interactive chat conversations, all tailored to their own data.
 
 ## Who is Embedchain for?
 
 Embedchain is designed for a diverse range of users, from AI professionals like Data Scientists and Machine Learning Engineers to those just starting their AI journey, including college students, independent developers, and hobbyists. Essentially, it's for anyone with an interest in AI, regardless of their expertise level.
 
-Our APIs are user-friendly yet adaptable, enabling beginners to effortlessly create LLM-powered applications with as few as 4 lines of code. At the same time, we offer extensive customization options for every aspect of the RAG pipeline. This includes the choice of LLMs, vector databases, loaders and chunkers, retrieval strategies, re-ranking, and more.
+Our APIs are user-friendly yet adaptable, enabling beginners to effortlessly create LLM-powered applications with as few as 4 lines of code. At the same time, we offer extensive customization options for every aspect of building a personalized AI application. This includes the choice of LLMs, vector databases, loaders and chunkers, retrieval strategies, re-ranking, and more.
 
 Our platform's clear and well-structured abstraction layers ensure that users can tailor the system to meet their specific needs, whether they're crafting a simple project or a complex, nuanced AI application.
 
 ## Why Use Embedchain?
 
-Developing a robust and efficient RAG (Retrieval-Augmented Generation) pipeline for production use presents numerous complexities, such as:
+Developing a personalized AI application for production use presents numerous complexities, such as:
 
 - Integrating and indexing data from diverse sources.
 - Determining optimal data chunking methods for each source.
@@ -48,11 +48,11 @@ When a user asks a question, whether for chatting, searching, or querying, Embed
 2. **Document Retrieval**: These embeddings are then used to find related documents in the database.
 3. **Answer Generation**: The related documents are used by the LLM to craft a precise answer.
 
-With Embedchain, you don’t have to worry about the complexities of building a RAG pipeline. It offers an easy-to-use interface for developing applications with any kind of data.
+With Embedchain, you don’t have to worry about the complexities of building a personalized AI application. It offers an easy-to-use interface for developing applications with any kind of data.
 
 ## Getting started
 
-Checkout our [quickstart guide](/get-started/quickstart) to start your first RAG application.
+Checkout our [quickstart guide](/get-started/quickstart) to start your first AI application.
 
 ## Support
 

docs/get-started/quickstart.mdx

@@ -1,6 +1,6 @@
 ---
 title: '⚡ Quickstart'
-description: '💡 Create a RAG app on your own data in a minute'
+description: '💡 Create an AI app on your own data in a minute'
 ---
 
 ## Installation
@@ -31,41 +31,47 @@ This section gives a quickstart example of using Mistral as the Open source LLM
 We are using Mistral hosted at Hugging Face, so will you need a Hugging Face token to run this example. Its *free* and you can create one [here](https://huggingface.co/docs/hub/security-tokens).
 
 <CodeGroup>
-```python quickstart.py
+```python huggingface_demo.py
 import os
-# replace this with your HF key
+# Replace this with your HF token
 os.environ["HUGGINGFACE_ACCESS_TOKEN"] = "hf_xxxx"
 
 from embedchain import App
-app = App.from_config("mistral.yaml")
+
+config = {
+  'llm': {
+    'provider': 'huggingface',
+    'config': {
+      'model': 'mistralai/Mistral-7B-Instruct-v0.2',
+      'top_p': 0.5
+    }
+  },
+  'embedder': {
+    'provider': 'huggingface',
+    'config': {
+      'model': 'sentence-transformers/all-mpnet-base-v2'
+    }
+  }
+}
+app = App.from_config(config=config)
 app.add("https://www.forbes.com/profile/elon-musk")
 app.add("https://en.wikipedia.org/wiki/Elon_Musk")
 app.query("What is the net worth of Elon Musk today?")
 # Answer: The net worth of Elon Musk today is $258.7 billion.
 ```
-```yaml mistral.yaml
-llm:
-  provider: huggingface
-  config:
-    model: 'mistralai/Mistral-7B-Instruct-v0.2'
-    top_p: 0.5
-embedder:
-  provider: huggingface
-  config:
-    model: 'sentence-transformers/all-mpnet-base-v2'
-```
 </CodeGroup>
 
 ## Paid Models
 
 In this section, we will use both LLM and embedding model from OpenAI.
 
-```python quickstart.py
+```python openai_demo.py
 import os
-# replace this with your OpenAI key
+from embedchain import App
+
+# Replace this with your OpenAI key
 os.environ["OPENAI_API_KEY"] = "sk-xxxx"
 
-from embedchain import App
 app = App()
 app.add("https://www.forbes.com/profile/elon-musk")
 app.add("https://en.wikipedia.org/wiki/Elon_Musk")

docs/integration/langsmith.mdx

@@ -5,22 +5,30 @@ description: 'Integrate with Langsmith to debug and monitor your LLM app'
 
 Embedchain now supports integration with [LangSmith](https://www.langchain.com/langsmith).
 
-To use langsmith, you need to do the following steps
+To use LangSmith, you need to do the following steps.
 
-1. Have an account on langsmith and keep the environment variables in handy
-2. Set the environments variables in your app so that embedchain has context about it.
+1. Have an account on LangSmith and keep the environment variables in handy
+2. Set the environment variables in your app so that embedchain has context about it.
 3. Just use embedchain and everything will be logged to LangSmith, so that you can better test and monitor your application.
 
-Lets cover each step in detail.
+Let's cover each step in detail.
 
-* First make sure that you a LangSmith account created and have all the necessary variables handy. LangSmith has a [good documentation](https://docs.smith.langchain.com/) on how to get started with their service.
 
-* Once you have the account setup, we will need the following environment variables
+* First make sure that you have created a LangSmith account and have all the necessary variables handy. LangSmith has a [good documentation](https://docs.smith.langchain.com/) on how to get started with their service.
+
+* Once you have setup the account, we will need the following environment variables
 
 ```bash
+# Setting environment variable for LangChain Tracing V2 integration.
 export LANGCHAIN_TRACING_V2=true
+
+# Setting the API endpoint for LangChain.
 export LANGCHAIN_ENDPOINT=https://api.smith.langchain.com
+
+# Replace '<your-api-key>' with your LangChain API key.
 export LANGCHAIN_API_KEY=<your-api-key>
+
+# Replace '<your-project>' with your LangChain project name, or it defaults to "default".
 export LANGCHAIN_PROJECT=<your-project>  # if not specified, defaults to "default"
 ```
 
@@ -29,20 +37,32 @@ If you are using Python, you can use the following code to set environment varia
 ```python
 import os
 
+# Setting environment variable for LangChain Tracing V2 integration.
 os.environ['LANGCHAIN_TRACING_V2'] = 'true'
+
+# Setting the API endpoint for LangChain.
 os.environ['LANGCHAIN_ENDPOINT'] = 'https://api.smith.langchain.com'
-os.environ['LANGCHAIN_API_KEY'] = <your-api-key>
-os.environ['LANGCHAIN_PROJECT] = <your-project>
+
+# Replace '<your-api-key>' with your LangChain API key.
+os.environ['LANGCHAIN_API_KEY'] = '<your-api-key>'
+
+# Replace '<your-project>' with your LangChain project name.
+os.environ['LANGCHAIN_PROJECT'] = '<your-project>'
 ```
 
-* Now create an app using embedchain and everything will be automatically visible in the LangSmith
+* Now create an app using Embedchain and everything will be automatically visible in the LangSmith
 
 
 ```python
 from embedchain import App
 
+# Initialize EmbedChain application.
 app = App()
+
+# Add data to your app
 app.add("https://en.wikipedia.org/wiki/Elon_Musk")
+
+# Query your app
 app.query("How many companies did Elon found?")
 ```
 

embedchain/__init__.py

@@ -7,4 +7,4 @@ from embedchain.client import Client  # noqa: F401
 from embedchain.pipeline import Pipeline  # noqa: F401
 
 # Setup the user directory if doesn't exist already
-Client.setup_dir()
+Client.setup()

embedchain/alembic.ini

@@ -0,0 +1,116 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = embedchain:migrations
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.
+prepend_sys_path = .
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the python>=3.9 or backports.zoneinfo library.
+# Any required deps can installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to ZoneInfo()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the
+# "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to alembic/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "version_path_separator" below.
+# version_locations = %(here)s/bar:%(here)s/bat:alembic/versions
+
+# version path separator; As mentioned above, this is the character used to split
+# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
+# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or commas.
+# Valid values for version_path_separator are:
+#
+# version_path_separator = :
+# version_path_separator = ;
+# version_path_separator = space
+version_path_separator = os  # Use os.pathsep. Default configuration used for new projects.
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+sqlalchemy.url = driver://user:pass@localhost/dbname
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# lint with attempts to fix using "ruff" - use the exec runner, execute a binary
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = %(here)s/.venv/bin/ruff
+# ruff.options = --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARN
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARN
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = WARN
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

embedchain/app.py

@@ -3,8 +3,6 @@ import concurrent.futures
 import json
 import logging
 import os
-import sqlite3
-import uuid
 from typing import Any, Optional, Union
 
 import requests
@@ -16,7 +14,8 @@ from embedchain.cache import (Config, ExactMatchEvaluation,
                               gptcache_data_manager, gptcache_pre_function)
 from embedchain.client import Client
 from embedchain.config import AppConfig, CacheConfig, ChunkerConfig
-from embedchain.constants import SQLITE_PATH
+from embedchain.core.db.database import get_session, init_db, setup_engine
+from embedchain.core.db.models import DataSource
 from embedchain.embedchain import EmbedChain
 from embedchain.embedder.base import BaseEmbedder
 from embedchain.embedder.openai import OpenAIEmbedder
@@ -33,8 +32,7 @@ from embedchain.utils.misc import validate_config
 from embedchain.vectordb.base import BaseVectorDB
 from embedchain.vectordb.chroma import ChromaDB
 
-# Set up the user directory if it doesn't exist already
-Client.setup_dir()
+logger = logging.getLogger(__name__)
 
 
 @register_deserializable
@@ -54,10 +52,10 @@ class App(EmbedChain):
         embedding_model: BaseEmbedder = None,
         llm: BaseLlm = None,
         config_data: dict = None,
-        log_level=logging.WARN,
         auto_deploy: bool = False,
         chunker: ChunkerConfig = None,
         cache_config: CacheConfig = None,
+        log_level: int = logging.WARN,
     ):
         """
         Initialize a new `App` instance.
@@ -72,8 +70,6 @@ class App(EmbedChain):
         :type llm: BaseLlm, optional
         :param config_data: Config dictionary, defaults to None
         :type config_data: dict, optional
-        :param log_level: Log level to use, defaults to logging.WARN
-        :type log_level: int, optional
         :param auto_deploy: Whether to deploy the pipeline automatically, defaults to False
         :type auto_deploy: bool, optional
         :raises Exception: If an error occurs while creating the pipeline
@@ -87,22 +83,22 @@ class App(EmbedChain):
         if name and config:
             raise Exception("Cannot provide both name and config. Please provide only one of them.")
 
-        logging.basicConfig(level=log_level, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s")
-        self.logger = logging.getLogger(__name__)
+        # Initialize the metadata db for the app
+        setup_engine(database_uri=os.environ.get("EMBEDCHAIN_DB_URI"))
+        init_db()
+
         self.auto_deploy = auto_deploy
         # Store the dict config as an attribute to be able to send it
         self.config_data = config_data if (config_data and validate_config(config_data)) else None
         self.client = None
         # pipeline_id from the backend
         self.id = None
-        self.chunker = None
-        if chunker:
-            self.chunker = ChunkerConfig(**chunker)
+        self.chunker = ChunkerConfig(**chunker) if chunker else None
         self.cache_config = cache_config
 
         self.config = config or AppConfig()
         self.name = self.config.name
-        self.config.id = self.local_id = str(uuid.uuid4()) if self.config.id is None else self.config.id
+        self.config.id = self.local_id = "default-app-id" if self.config.id is None else self.config.id
 
         if id is not None:
             # Init client first since user is trying to fetch the pipeline
@@ -120,6 +116,9 @@ class App(EmbedChain):
         self.llm = llm or OpenAILlm()
         self._init_db()
 
+        # Session for the metadata db
+        self.db_session = get_session()
+
         # If cache_config is provided, initializing the cache ...
         if self.cache_config is not None:
             self._init_cache()
@@ -127,27 +126,6 @@ class App(EmbedChain):
         # Send anonymous telemetry
         self._telemetry_props = {"class": self.__class__.__name__}
         self.telemetry = AnonymousTelemetry(enabled=self.config.collect_metrics)
-
-        # Establish a connection to the SQLite database
-        self.connection = sqlite3.connect(SQLITE_PATH, check_same_thread=False)
-        self.cursor = self.connection.cursor()
-
-        # Create the 'data_sources' table if it doesn't exist
-        self.cursor.execute(
-            """
-            CREATE TABLE IF NOT EXISTS data_sources (
-                pipeline_id TEXT,
-                hash TEXT,
-                type TEXT,
-                value TEXT,
-                metadata TEXT,
-                is_uploaded INTEGER DEFAULT 0,
-                PRIMARY KEY (pipeline_id, hash)
-            )
-        """
-        )
-        self.connection.commit()
-        # Send anonymous telemetry
         self.telemetry.capture(event_name="init", properties=self._telemetry_props)
 
         self.user_asks = []
@@ -257,7 +235,7 @@ class App(EmbedChain):
                 response.raise_for_status()
                 return response.status_code == 200
         except Exception as e:
-            self.logger.exception(f"Error occurred during file upload: {str(e)}")
+            logger.exception(f"Error occurred during file upload: {str(e)}")
             print("❌ Error occurred during file upload!")
             return False
 
@@ -291,7 +269,7 @@ class App(EmbedChain):
                 metadata = {"file_path": data_value, "s3_key": s3_key}
                 data_value = presigned_url
             else:
-                self.logger.error(f"File upload failed for hash: {data_hash}")
+                logger.error(f"File upload failed for hash: {data_hash}")
                 return False
         else:
             if data_type == "qna_pair":
@@ -307,20 +285,14 @@ class App(EmbedChain):
             return False
 
     def _mark_data_as_uploaded(self, data_hash):
-        self.cursor.execute(
-            "UPDATE data_sources SET is_uploaded = 1 WHERE hash = ? AND pipeline_id = ?",
-            (data_hash, self.local_id),
-        )
-        self.connection.commit()
+        self.db_session.query(DataSource).filter_by(hash=data_hash, app_id=self.local_id).update({"is_uploaded": 1})
 
     def get_data_sources(self):
-        db_data = self.cursor.execute("SELECT * FROM data_sources WHERE pipeline_id = ?", (self.local_id,)).fetchall()
-
-        data_sources = []
-        for data in db_data:
-            data_sources.append({"data_type": data[2], "data_value": data[3], "metadata": data[4]})
-
-        return data_sources
+        data_sources = self.db_session.query(DataSource).filter_by(app_id=self.local_id).all()
+        results = []
+        for row in data_sources:
+            results.append({"data_type": row.type, "data_value": row.value, "metadata": row.meta_data})
+        return results
 
     def deploy(self):
         if self.client is None:
@@ -329,14 +301,11 @@ class App(EmbedChain):
         pipeline_data = self._create_pipeline()
         self.id = pipeline_data["id"]
 
-        results = self.cursor.execute(
-            "SELECT * FROM data_sources WHERE pipeline_id = ? AND is_uploaded = 0", (self.local_id,)  # noqa:E501
-        ).fetchall()
-
+        results = self.db_session.query(DataSource).filter_by(app_id=self.local_id, is_uploaded=0).all()
         if len(results) > 0:
             print("🛠️ Adding data to your pipeline...")
         for result in results:
-            data_hash, data_type, data_value = result[1], result[2], result[3]
+            data_hash, data_type, data_value = result.hash, result.data_type, result.data_value
             self._process_and_upload_data(data_hash, data_type, data_value)
 
         # Send anonymous telemetry
@@ -351,18 +320,18 @@ class App(EmbedChain):
         yaml_path: Optional[str] = None,
     ):
         """
-        Instantiate a Pipeline object from a configuration.
+        Instantiate a App object from a configuration.
 
         :param config_path: Path to the YAML or JSON configuration file.
         :type config_path: Optional[str]
         :param config: A dictionary containing the configuration.
         :type config: Optional[dict[str, Any]]
-        :param auto_deploy: Whether to deploy the pipeline automatically, defaults to False
+        :param auto_deploy: Whether to deploy the app automatically, defaults to False
         :type auto_deploy: bool, optional
         :param yaml_path: (Deprecated) Path to the YAML configuration file. Use config_path instead.
         :type yaml_path: Optional[str]
-        :return: An instance of the Pipeline class.
-        :rtype: Pipeline
+        :return: An instance of the App class.
+        :rtype: App
         """
         # Backward compatibility for yaml_path
         if yaml_path and not config_path:
@@ -385,18 +354,16 @@ class App(EmbedChain):
         elif config and isinstance(config, dict):
             config_data = config
         else:
-            logging.error(
+            logger.error(
                 "Please provide either a config file path (YAML or JSON) or a config dictionary. Falling back to defaults because no config is provided.",  # noqa: E501
             )
             config_data = {}
 
-        try:
-            validate_config(config_data)
-        except Exception as e:
-            raise Exception(f"Error occurred while validating the config. Error: {str(e)}")
+        # Validate the config
+        validate_config(config_data)
 
         app_config_data = config_data.get("app", {}).get("config", {})
-        db_config_data = config_data.get("vectordb", {})
+        vector_db_config_data = config_data.get("vectordb", {})
         embedding_model_config_data = config_data.get("embedding_model", config_data.get("embedder", {}))
         llm_config_data = config_data.get("llm", {})
         chunker_config_data = config_data.get("chunker", {})
@@ -404,10 +371,14 @@ class App(EmbedChain):
 
         app_config = AppConfig(**app_config_data)
 
-        db_provider = db_config_data.get("provider", "chroma")
-        db = VectorDBFactory.create(db_provider, db_config_data.get("config", {}))
+        vector_db_provider = vector_db_config_data.get("provider", "chroma")
+        vector_db = VectorDBFactory.create(vector_db_provider, vector_db_config_data.get("config", {}))
 
         if llm_config_data:
+            # Initialize the metadata db for the app here since llmfactory needs it for initialization of
+            # the llm memory
+            setup_engine(database_uri=os.environ.get("EMBEDCHAIN_DB_URI"))
+            init_db()
             llm_provider = llm_config_data.get("provider", "openai")
             llm = LlmFactory.create(llm_provider, llm_config_data.get("config", {}))
         else:
@@ -423,14 +394,10 @@ class App(EmbedChain):
         else:
             cache_config = None
 
-        # Send anonymous telemetry
-        event_properties = {"init_type": "config_data"}
-        AnonymousTelemetry().capture(event_name="init", properties=event_properties)
-
         return cls(
             config=app_config,
             llm=llm,
-            db=db,
+            db=vector_db,
             embedding_model=embedding_model,
             config_data=config_data,
             auto_deploy=auto_deploy,
@@ -505,12 +472,12 @@ class App(EmbedChain):
             EvalMetric.GROUNDEDNESS.value,
         ]
 
-        logging.info(f"Collecting data from {len(queries)} questions for evaluation...")
+        logger.info(f"Collecting data from {len(queries)} questions for evaluation...")
         dataset = []
         for q, a, c in zip(queries, answers, contexts):
             dataset.append(EvalData(question=q, answer=a, contexts=c))
 
-        logging.info(f"Evaluating {len(dataset)} data points...")
+        logger.info(f"Evaluating {len(dataset)} data points...")
         result = {}
         with concurrent.futures.ThreadPoolExecutor(max_workers=num_workers) as executor:
             future_to_metric = {executor.submit(self._eval, dataset, metric): metric for metric in metrics}

embedchain/bots/discord.py

@@ -17,6 +17,8 @@ except ModuleNotFoundError:
     ) from None
 
 
+logger = logging.getLogger(__name__)
+
 intents = discord.Intents.default()
 intents.message_content = True
 client = discord.Client(intents=intents)
@@ -37,7 +39,7 @@ class DiscordBot(BaseBot):
             self.add(data)
             response = f"Added data from: {data}"
         except Exception:
-            logging.exception(f"Failed to add data {data}.")
+            logger.exception(f"Failed to add data {data}.")
             response = "Some error occurred while adding data."
         return response
 
@@ -45,7 +47,7 @@ class DiscordBot(BaseBot):
         try:
             response = self.query(message)
         except Exception:
-            logging.exception(f"Failed to query {message}.")
+            logger.exception(f"Failed to query {message}.")
             response = "An error occurred. Please try again!"
         return response
 
@@ -60,7 +62,7 @@ class DiscordBot(BaseBot):
 async def query_command(interaction: discord.Interaction, question: str):
     await interaction.response.defer()
     member = client.guilds[0].get_member(client.user.id)
-    logging.info(f"User: {member}, Query: {question}")
+    logger.info(f"User: {member}, Query: {question}")
     try:
         answer = discord_bot.ask_bot(question)
         if args.include_question:
@@ -70,20 +72,20 @@ async def query_command(interaction: discord.Interaction, question: str):
         await interaction.followup.send(response)
     except Exception as e:
         await interaction.followup.send("An error occurred. Please try again!")
-        logging.error("Error occurred during 'query' command:", e)
+        logger.error("Error occurred during 'query' command:", e)
 
 
 @tree.command(name="add", description="add new content to the embedchain database")
 async def add_command(interaction: discord.Interaction, url_or_text: str):
     await interaction.response.defer()
     member = client.guilds[0].get_member(client.user.id)
-    logging.info(f"User: {member}, Add: {url_or_text}")
+    logger.info(f"User: {member}, Add: {url_or_text}")
     try:
         response = discord_bot.add_data(url_or_text)
         await interaction.followup.send(response)
     except Exception as e:
         await interaction.followup.send("An error occurred. Please try again!")
-        logging.error("Error occurred during 'add' command:", e)
+        logger.error("Error occurred during 'add' command:", e)
 
 
 @tree.command(name="ping", description="Simple ping pong command")
@@ -96,7 +98,7 @@ async def on_app_command_error(interaction: discord.Interaction, error: discord.
     if isinstance(error, commands.CommandNotFound):
         await interaction.followup.send("Invalid command. Please refer to the documentation for correct syntax.")
     else:
-        logging.error("Error occurred during command execution:", error)
+        logger.error("Error occurred during command execution:", error)
 
 
 @client.event
@@ -104,8 +106,8 @@ async def on_ready():
     # TODO: Sync in admin command, to not hit rate limits.
     # This might be overkill for most users, and it would require to set a guild or user id, where sync is allowed.
     await tree.sync()
-    logging.debug("Command tree synced")
-    logging.info(f"Logged in as {client.user.name}")
+    logger.debug("Command tree synced")
+    logger.info(f"Logged in as {client.user.name}")
 
 
 def start_command():

embedchain/bots/slack.py

@@ -19,6 +19,8 @@ except ModuleNotFoundError:
     ) from None
 
 
+logger = logging.getLogger(__name__)
+
 SLACK_BOT_TOKEN = os.environ.get("SLACK_BOT_TOKEN")
 
 
@@ -42,10 +44,10 @@ class SlackBot(BaseBot):
                     try:
                         response = self.chat_bot.chat(question)
                         self.send_slack_message(message["channel"], response)
-                        logging.info("Query answered successfully!")
+                        logger.info("Query answered successfully!")
                     except Exception as e:
                         self.send_slack_message(message["channel"], "An error occurred. Please try again!")
-                        logging.error("Error occurred during 'query' command:", e)
+                        logger.error("Error occurred during 'query' command:", e)
                 elif text.startswith("add"):
                     _, data_type, url_or_text = text.split(" ", 2)
                     if url_or_text.startswith("<") and url_or_text.endswith(">"):
@@ -55,10 +57,10 @@ class SlackBot(BaseBot):
                         self.send_slack_message(message["channel"], f"Added {data_type} : {url_or_text}")
                     except ValueError as e:
                         self.send_slack_message(message["channel"], f"Error: {str(e)}")
-                        logging.error("Error occurred during 'add' command:", e)
+                        logger.error("Error occurred during 'add' command:", e)
                     except Exception as e:
                         self.send_slack_message(message["channel"], f"Failed to add {data_type} : {url_or_text}")
-                        logging.error("Error occurred during 'add' command:", e)
+                        logger.error("Error occurred during 'add' command:", e)
 
     def send_slack_message(self, channel, message):
         response = self.client.chat_postMessage(channel=channel, text=message)
@@ -68,7 +70,7 @@ class SlackBot(BaseBot):
         app = Flask(__name__)
 
         def signal_handler(sig, frame):
-            logging.info("\nGracefully shutting down the SlackBot...")
+            logger.info("\nGracefully shutting down the SlackBot...")
             sys.exit(0)
 
         signal.signal(signal.SIGINT, signal_handler)

embedchain/bots/whatsapp.py

@@ -8,6 +8,8 @@ from embedchain.helpers.json_serializable import register_deserializable
 
 from .base import BaseBot
 
+logger = logging.getLogger(__name__)
+
 
 @register_deserializable
 class WhatsAppBot(BaseBot):
@@ -35,7 +37,7 @@ class WhatsAppBot(BaseBot):
             self.add(data)
             response = f"Added data from: {data}"
         except Exception:
-            logging.exception(f"Failed to add data {data}.")
+            logger.exception(f"Failed to add data {data}.")
             response = "Some error occurred while adding data."
         return response
 
@@ -43,7 +45,7 @@ class WhatsAppBot(BaseBot):
         try:
             response = self.query(message)
         except Exception:
-            logging.exception(f"Failed to query {message}.")
+            logger.exception(f"Failed to query {message}.")
             response = "An error occurred. Please try again!"
         return response
 
@@ -51,7 +53,7 @@ class WhatsAppBot(BaseBot):
         app = self.flask.Flask(__name__)
 
         def signal_handler(sig, frame):
-            logging.info("\nGracefully shutting down the WhatsAppBot...")
+            logger.info("\nGracefully shutting down the WhatsAppBot...")
             sys.exit(0)
 
         signal.signal(signal.SIGINT, signal_handler)

embedchain/cache.py

@@ -14,6 +14,8 @@ from gptcache.similarity_evaluation.distance import \
 from gptcache.similarity_evaluation.exact_match import \
     ExactMatchEvaluation  # noqa: F401
 
+logger = logging.getLogger(__name__)
+
 
 def gptcache_pre_function(data: dict[str, Any], **params: dict[str, Any]):
     return data["input_query"]
@@ -24,12 +26,12 @@ def gptcache_data_manager(vector_dimension):
 
 
 def gptcache_data_convert(cache_data):
-    logging.info("[Cache] Cache hit, returning cache data...")
+    logger.info("[Cache] Cache hit, returning cache data...")
     return cache_data
 
 
 def gptcache_update_cache_callback(llm_data, update_cache_func, *args, **kwargs):
-    logging.info("[Cache] Cache missed, updating cache...")
+    logger.info("[Cache] Cache missed, updating cache...")
     update_cache_func(Answer(llm_data, CacheDataType.STR))
     return llm_data
 

embedchain/chunkers/base_chunker.py

@@ -6,6 +6,8 @@ from embedchain.config.add_config import ChunkerConfig
 from embedchain.helpers.json_serializable import JSONSerializable
 from embedchain.models.data_type import DataType
 
+logger = logging.getLogger(__name__)
+
 
 class BaseChunker(JSONSerializable):
     def __init__(self, text_splitter):
@@ -27,7 +29,7 @@ class BaseChunker(JSONSerializable):
         chunk_ids = []
         id_map = {}
         min_chunk_size = config.min_chunk_size if config is not None else 1
-        logging.info(f"Skipping chunks smaller than {min_chunk_size} characters")
+        logger.info(f"Skipping chunks smaller than {min_chunk_size} characters")
         data_result = loader.load_data(src)
         data_records = data_result["data"]
         doc_id = data_result["doc_id"]

embedchain/chunkers/excel_file.py

@@ -0,0 +1,22 @@
+from typing import Optional
+
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+from embedchain.chunkers.base_chunker import BaseChunker
+from embedchain.config.add_config import ChunkerConfig
+from embedchain.helpers.json_serializable import register_deserializable
+
+
+@register_deserializable
+class ExcelFileChunker(BaseChunker):
+    """Chunker for Excel file."""
+
+    def __init__(self, config: Optional[ChunkerConfig] = None):
+        if config is None:
+            config = ChunkerConfig(chunk_size=1000, chunk_overlap=0, length_function=len)
+        text_splitter = RecursiveCharacterTextSplitter(
+            chunk_size=config.chunk_size,
+            chunk_overlap=config.chunk_overlap,
+            length_function=config.length_function,
+        )
+        super().__init__(text_splitter)

embedchain/client.py

@@ -7,6 +7,8 @@ import requests
 
 from embedchain.constants import CONFIG_DIR, CONFIG_FILE
 
+logger = logging.getLogger(__name__)
+
 
 class Client:
     def __init__(self, api_key=None, host="https://apiv2.embedchain.ai"):
@@ -24,14 +26,14 @@ class Client:
         else:
             if "api_key" in self.config_data:
                 self.api_key = self.config_data["api_key"]
-                logging.info("API key loaded successfully!")
+                logger.info("API key loaded successfully!")
             else:
                 raise ValueError(
                     "You are not logged in. Please obtain an API key from https://app.embedchain.ai/settings/keys/"
                 )
 
     @classmethod
-    def setup_dir(cls):
+    def setup(cls):
         """
         Loads the user id from the config file if it exists, otherwise generates a new
         one and saves it to the config file.
@@ -40,6 +42,7 @@ class Client:
         :rtype: str
         """
         os.makedirs(CONFIG_DIR, exist_ok=True)
+
         if os.path.exists(CONFIG_FILE):
             with open(CONFIG_FILE, "r") as f:
                 data = json.load(f)
@@ -53,7 +56,7 @@ class Client:
     @classmethod
     def load_config(cls):
         if not os.path.exists(CONFIG_FILE):
-            cls.setup_dir()
+            cls.setup()
 
         with open(CONFIG_FILE, "r") as config_file:
             return json.load(config_file)
@@ -63,7 +66,7 @@ class Client:
         with open(CONFIG_FILE, "w") as config_file:
             json.dump(self.config_data, config_file, indent=4)
 
-        logging.info("API key saved successfully!")
+        logger.info("API key saved successfully!")
 
     def clear(self):
         if "api_key" in self.config_data:
@@ -71,17 +74,17 @@ class Client:
             with open(CONFIG_FILE, "w") as config_file:
                 json.dump(self.config_data, config_file, indent=4)
             self.api_key = None
-            logging.info("API key deleted successfully!")
+            logger.info("API key deleted successfully!")
         else:
-            logging.warning("API key not found in the configuration file.")
+            logger.warning("API key not found in the configuration file.")
 
     def update(self, api_key):
         if self.check(api_key):
             self.api_key = api_key
             self.save()
-            logging.info("API key updated successfully!")
+            logger.info("API key updated successfully!")
         else:
-            logging.warning("Invalid API key provided. API key not updated.")
+            logger.warning("Invalid API key provided. API key not updated.")
 
     def check(self, api_key):
         validation_url = f"{self.host}/api/v1/accounts/api_keys/validate/"
@@ -89,8 +92,8 @@ class Client:
         if response.status_code == 200:
             return True
         else:
-            logging.warning(f"Response from API: {response.text}")
-            logging.warning("Invalid API key. Unable to validate.")
+            logger.warning(f"Response from API: {response.text}")
+            logger.warning("Invalid API key. Unable to validate.")
             return False
 
     def get(self):

embedchain/config/base_app_config.py

@@ -5,6 +5,8 @@ from embedchain.config.base_config import BaseConfig
 from embedchain.helpers.json_serializable import JSONSerializable
 from embedchain.vectordb.base import BaseVectorDB
 
+logger = logging.getLogger(__name__)
+
 
 class BaseAppConfig(BaseConfig, JSONSerializable):
     """
@@ -36,29 +38,21 @@ class BaseAppConfig(BaseConfig, JSONSerializable):
         defaults to None
         :type collection_name: Optional[str], optional
         """
-        self._setup_logging(log_level)
         self.id = id
         self.collect_metrics = True if (collect_metrics is True or collect_metrics is None) else False
         self.collection_name = collection_name
 
         if db:
             self._db = db
-            logging.warning(
+            logger.warning(
                 "DEPRECATION WARNING: Please supply the database as the second parameter during app init. "
                 "Such as `app(config=config, db=db)`."
             )
 
         if collection_name:
-            logging.warning("DEPRECATION WARNING: Please supply the collection name to the database config.")
+            logger.warning("DEPRECATION WARNING: Please supply the collection name to the database config.")
         return
 
-    def _setup_logging(self, debug_level):
-        level = logging.WARNING  # Default level
-        if debug_level is not None:
-            level = getattr(logging, debug_level.upper(), None)
-            if not isinstance(level, int):
-                raise ValueError(f"Invalid log level: {debug_level}")
-
-        logging.basicConfig(format="%(asctime)s [%(name)s] [%(levelname)s] %(message)s", level=level)
-        self.logger = logging.getLogger(__name__)
-        return
+    def _setup_logging(self, log_level):
+        logger.basicConfig(format="%(asctime)s [%(name)s] [%(levelname)s] %(message)s", level=log_level)
+        self.logger = logger.getLogger(__name__)

embedchain/config/embedder/base.py

@@ -11,6 +11,7 @@ class BaseEmbedderConfig:
         deployment_name: Optional[str] = None,
         vector_dimension: Optional[int] = None,
         api_key: Optional[str] = None,
+        api_base: Optional[str] = None,
     ):
         """
         Initialize a new instance of an embedder config class.
@@ -24,3 +25,4 @@ class BaseEmbedderConfig:
         self.deployment_name = deployment_name
         self.vector_dimension = vector_dimension
         self.api_key = api_key
+        self.api_base = api_base

embedchain/config/llm/base.py

@@ -6,6 +6,8 @@ from typing import Any, Optional
 from embedchain.config.base_config import BaseConfig
 from embedchain.helpers.json_serializable import register_deserializable
 
+logger = logging.getLogger(__name__)
+
 DEFAULT_PROMPT = """
 You are a Q&A expert system. Your responses must always be rooted in the context provided for each query. Here are some guidelines to follow:
 
@@ -93,8 +95,10 @@ class BaseLlmConfig(BaseConfig):
         query_type: Optional[str] = None,
         callbacks: Optional[list] = None,
         api_key: Optional[str] = None,
+        base_url: Optional[str] = None,
         endpoint: Optional[str] = None,
         model_kwargs: Optional[dict[str, Any]] = None,
+        local: Optional[bool] = False,
     ):
         """
         Initializes a configuration class instance for the LLM.
@@ -138,12 +142,14 @@ class BaseLlmConfig(BaseConfig):
         :type callbacks: Optional[list], optional
         :param query_type: The type of query to use, defaults to None
         :type query_type: Optional[str], optional
+        :param local: If True, the model will be run locally, defaults to False (for huggingface provider)
+        :type local: Optional[bool], optional
         :raises ValueError: If the template is not valid as template should
         contain $context and $query (and optionally $history)
         :raises ValueError: Stream is not boolean
         """
         if template is not None:
-            logging.warning(
+            logger.warning(
                 "The `template` argument is deprecated and will be removed in a future version. "
                 + "Please use `prompt` instead."
             )
@@ -163,8 +169,10 @@ class BaseLlmConfig(BaseConfig):
         self.query_type = query_type
         self.callbacks = callbacks
         self.api_key = api_key
+        self.base_url = base_url
         self.endpoint = endpoint
         self.model_kwargs = model_kwargs
+        self.local = local
 
         if isinstance(prompt, str):
             prompt = Template(prompt)

embedchain/config/vectordb/pinecone.py

@@ -16,6 +16,7 @@ class PineconeDBConfig(BaseVectorDbConfig):
         pod_config: Optional[dict[str, any]] = None,
         serverless_config: Optional[dict[str, any]] = None,
         hybrid_search: bool = False,
+        bm25_encoder: any = None,
         **extra_params: dict[str, any],
     ):
         self.metric = metric
@@ -24,6 +25,7 @@ class PineconeDBConfig(BaseVectorDbConfig):
         self.vector_dimension = vector_dimension
         self.extra_params = extra_params
         self.hybrid_search = hybrid_search
+        self.bm25_encoder = bm25_encoder
         if pod_config is None and serverless_config is None:
             # If no config is provided, use the default pod spec config
             pod_environment = os.environ.get("PINECONE_ENV", "gcp-starter")

embedchain/constants.py

@@ -2,7 +2,10 @@ import os
 from pathlib import Path
 
 ABS_PATH = os.getcwd()
-HOME_DIR = str(Path.home())
+HOME_DIR = os.environ.get("EMBEDCHAIN_CONFIG_DIR", str(Path.home()))
 CONFIG_DIR = os.path.join(HOME_DIR, ".embedchain")
 CONFIG_FILE = os.path.join(CONFIG_DIR, "config.json")
 SQLITE_PATH = os.path.join(CONFIG_DIR, "embedchain.db")
+
+# Set the environment variable for the database URI
+os.environ.setdefault("EMBEDCHAIN_DB_URI", f"sqlite:///{SQLITE_PATH}")

embedchain/core/db/database.py

@@ -0,0 +1,88 @@
+import os
+
+from alembic import command
+from alembic.config import Config
+from sqlalchemy import create_engine
+from sqlalchemy.engine.base import Engine
+from sqlalchemy.orm import Session as SQLAlchemySession
+from sqlalchemy.orm import scoped_session, sessionmaker
+
+from .models import Base
+
+
+class DatabaseManager:
+    def __init__(self, echo: bool = False):
+        self.database_uri = os.environ.get("EMBEDCHAIN_DB_URI")
+        self.echo = echo
+        self.engine: Engine = None
+        self._session_factory = None
+
+    def setup_engine(self) -> None:
+        """Initializes the database engine and session factory."""
+        if not self.database_uri:
+            raise RuntimeError("Database URI is not set. Set the EMBEDCHAIN_DB_URI environment variable.")
+        connect_args = {}
+        if self.database_uri.startswith("sqlite"):
+            connect_args["check_same_thread"] = False
+        self.engine = create_engine(self.database_uri, echo=self.echo, connect_args=connect_args)
+        self._session_factory = scoped_session(sessionmaker(bind=self.engine))
+        Base.metadata.bind = self.engine
+
+    def init_db(self) -> None:
+        """Creates all tables defined in the Base metadata."""
+        if not self.engine:
+            raise RuntimeError("Database engine is not initialized. Call setup_engine() first.")
+        Base.metadata.create_all(self.engine)
+
+    def get_session(self) -> SQLAlchemySession:
+        """Provides a session for database operations."""
+        if not self._session_factory:
+            raise RuntimeError("Session factory is not initialized. Call setup_engine() first.")
+        return self._session_factory()
+
+    def close_session(self) -> None:
+        """Closes the current session."""
+        if self._session_factory:
+            self._session_factory.remove()
+
+    def execute_transaction(self, transaction_block):
+        """Executes a block of code within a database transaction."""
+        session = self.get_session()
+        try:
+            transaction_block(session)
+            session.commit()
+        except Exception as e:
+            session.rollback()
+            raise e
+        finally:
+            self.close_session()
+
+
+# Singleton pattern to use throughout the application
+database_manager = DatabaseManager()
+
+
+# Convenience functions for backward compatibility and ease of use
+def setup_engine(database_uri: str, echo: bool = False) -> None:
+    database_manager.database_uri = database_uri
+    database_manager.echo = echo
+    database_manager.setup_engine()
+
+
+def alembic_upgrade() -> None:
+    """Upgrades the database to the latest version."""
+    alembic_config_path = os.path.join(os.path.dirname(__file__), "..", "..", "alembic.ini")
+    alembic_cfg = Config(alembic_config_path)
+    command.upgrade(alembic_cfg, "head")
+
+
+def init_db() -> None:
+    alembic_upgrade()
+
+
+def get_session() -> SQLAlchemySession:
+    return database_manager.get_session()
+
+
+def execute_transaction(transaction_block):
+    database_manager.execute_transaction(transaction_block)

embedchain/core/db/models.py

@@ -0,0 +1,31 @@
+import uuid
+
+from sqlalchemy import TIMESTAMP, Column, Integer, String, Text, func
+from sqlalchemy.orm import declarative_base
+
+Base = declarative_base()
+metadata = Base.metadata
+
+
+class DataSource(Base):
+    __tablename__ = "ec_data_sources"
+
+    id = Column(String, primary_key=True, default=lambda: str(uuid.uuid4()))
+    app_id = Column(Text, index=True)
+    hash = Column(Text, index=True)
+    type = Column(Text, index=True)
+    value = Column(Text)
+    meta_data = Column(Text, name="metadata")
+    is_uploaded = Column(Integer, default=0)
+
+
+class ChatHistory(Base):
+    __tablename__ = "ec_chat_history"
+
+    app_id = Column(String, primary_key=True)
+    id = Column(String, primary_key=True)
+    session_id = Column(String, primary_key=True, index=True)
+    question = Column(Text)
+    answer = Column(Text)
+    meta_data = Column(Text, name="metadata")
+    created_at = Column(TIMESTAMP, default=func.current_timestamp(), index=True)

embedchain/data_formatter/data_formatter.py

@@ -80,6 +80,7 @@ class DataFormatter(JSONSerializable):
             DataType.SLACK: "embedchain.loaders.slack.SlackLoader",
             DataType.DROPBOX: "embedchain.loaders.dropbox.DropboxLoader",
             DataType.TEXT_FILE: "embedchain.loaders.text_file.TextFileLoader",
+            DataType.EXCEL_FILE: "embedchain.loaders.excel_file.ExcelFileLoader",
         }
 
         if data_type == DataType.CUSTOM or loader is not None:
@@ -127,6 +128,7 @@ class DataFormatter(JSONSerializable):
             DataType.SLACK: "embedchain.chunkers.common_chunker.CommonChunker",
             DataType.DROPBOX: "embedchain.chunkers.common_chunker.CommonChunker",
             DataType.TEXT_FILE: "embedchain.chunkers.common_chunker.CommonChunker",
+            DataType.EXCEL_FILE: "embedchain.chunkers.excel_file.ExcelFileChunker",
         }
 
         if chunker is not None:

embedchain/embedchain.py

@@ -1,7 +1,6 @@
 import hashlib
 import json
 import logging
-import sqlite3
 from typing import Any, Optional, Union
 
 from dotenv import load_dotenv
@@ -13,7 +12,7 @@ from embedchain.cache import (adapt, get_gptcache_session,
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config import AddConfig, BaseLlmConfig, ChunkerConfig
 from embedchain.config.base_app_config import BaseAppConfig
-from embedchain.constants import SQLITE_PATH
+from embedchain.core.db.models import ChatHistory, DataSource
 from embedchain.data_formatter import DataFormatter
 from embedchain.embedder.base import BaseEmbedder
 from embedchain.helpers.json_serializable import JSONSerializable
@@ -21,12 +20,13 @@ from embedchain.llm.base import BaseLlm
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.models.data_type import (DataType, DirectDataType,
                                          IndirectDataType, SpecialDataType)
-from embedchain.telemetry.posthog import AnonymousTelemetry
 from embedchain.utils.misc import detect_datatype, is_valid_json_string
 from embedchain.vectordb.base import BaseVectorDB
 
 load_dotenv()
 
+logger = logging.getLogger(__name__)
+
 
 class EmbedChain(JSONSerializable):
     def __init__(
@@ -53,7 +53,6 @@ class EmbedChain(JSONSerializable):
         :type system_prompt: Optional[str], optional
         :raises ValueError: No database or embedder provided.
         """
-
         self.config = config
         self.cache_config = None
         # Llm
@@ -85,30 +84,6 @@ class EmbedChain(JSONSerializable):
         self.user_asks = []
 
         self.chunker: Optional[ChunkerConfig] = None
-        # Send anonymous telemetry
-        self._telemetry_props = {"class": self.__class__.__name__}
-        self.telemetry = AnonymousTelemetry(enabled=self.config.collect_metrics)
-        # Establish a connection to the SQLite database
-        self.connection = sqlite3.connect(SQLITE_PATH, check_same_thread=False)
-        self.cursor = self.connection.cursor()
-
-        # Create the 'data_sources' table if it doesn't exist
-        self.cursor.execute(
-            """
-            CREATE TABLE IF NOT EXISTS data_sources (
-                pipeline_id TEXT,
-                hash TEXT,
-                type TEXT,
-                value TEXT,
-                metadata TEXT,
-                is_uploaded INTEGER DEFAULT 0,
-                PRIMARY KEY (pipeline_id, hash)
-            )
-        """
-        )
-        self.connection.commit()
-        # Send anonymous telemetry
-        self.telemetry.capture(event_name="init", properties=self._telemetry_props)
 
     @property
     def collect_metrics(self):
@@ -170,10 +145,10 @@ class EmbedChain(JSONSerializable):
 
         try:
             DataType(source)
-            logging.warning(
+            logger.warning(
                 f"""Starting from version v0.0.40, Embedchain can automatically detect the data type. So, in the `add` method, the argument order has changed. You no longer need to specify '{source}' for the `source` argument. So the code snippet will be `.add("{data_type}", "{source}")`"""  # noqa #E501
             )
-            logging.warning(
+            logger.warning(
                 "Embedchain is swapping the arguments for you. This functionality might be deprecated in the future, so please adjust your code."  # noqa #E501
             )
             source, data_type = data_type, source
@@ -184,7 +159,7 @@ class EmbedChain(JSONSerializable):
             try:
                 data_type = DataType(data_type)
             except ValueError:
-                logging.info(
+                logger.info(
                     f"Invalid data_type: '{data_type}', using `custom` instead.\n Check docs to pass the valid data type: `https://docs.embedchain.ai/data-sources/overview`"  # noqa: E501
                 )
                 data_type = DataType.CUSTOM
@@ -204,21 +179,29 @@ class EmbedChain(JSONSerializable):
         if data_type in {DataType.DOCS_SITE}:
             self.is_docs_site_instance = True
 
-        # Insert the data into the 'data' table
-        self.cursor.execute(
-            """
-            INSERT OR REPLACE INTO data_sources (hash, pipeline_id, type, value, metadata)
-            VALUES (?, ?, ?, ?, ?)
-        """,
-            (source_hash, self.config.id, data_type.value, str(source), json.dumps(metadata)),
-        )
+        # Convert the source to a string if it is not already
+        if not isinstance(source, str):
+            source = str(source)
 
-        # Commit the transaction
-        self.connection.commit()
+        # Insert the data into the 'ec_data_sources' table
+        self.db_session.add(
+            DataSource(
+                hash=source_hash,
+                app_id=self.config.id,
+                type=data_type.value,
+                value=source,
+                metadata=json.dumps(metadata),
+            )
+        )
+        try:
+            self.db_session.commit()
+        except Exception as e:
+            logger.error(f"Error adding data source: {e}")
+            self.db_session.rollback()
 
         if dry_run:
             data_chunks_info = {"chunks": documents, "metadata": metadatas, "count": len(documents), "type": data_type}
-            logging.debug(f"Dry run info : {data_chunks_info}")
+            logger.debug(f"Dry run info : {data_chunks_info}")
             return data_chunks_info
 
         # Send anonymous telemetry
@@ -331,12 +314,12 @@ class EmbedChain(JSONSerializable):
         new_doc_id = embeddings_data["doc_id"]
 
         if existing_doc_id and existing_doc_id == new_doc_id:
-            print("Doc content has not changed. Skipping creating chunks and embeddings")
+            logger.info("Doc content has not changed. Skipping creating chunks and embeddings")
             return [], [], [], 0
 
         # this means that doc content has changed.
         if existing_doc_id and existing_doc_id != new_doc_id:
-            print("Doc content has changed. Recomputing chunks and embeddings intelligently.")
+            logger.info("Doc content has changed. Recomputing chunks and embeddings intelligently.")
             self.db.delete({"doc_id": existing_doc_id})
 
         # get existing ids, and discard doc if any common id exist.
@@ -362,7 +345,7 @@ class EmbedChain(JSONSerializable):
                 src_copy = src
                 if len(src_copy) > 50:
                     src_copy = src[:50] + "..."
-                print(f"All data from {src_copy} already exists in the database.")
+                logger.info(f"All data from {src_copy} already exists in the database.")
                 # Make sure to return a matching return type
                 return [], [], [], 0
 
@@ -401,18 +384,20 @@ class EmbedChain(JSONSerializable):
         # Chunk documents into batches of 2048 and handle each batch
         # helps wigth large loads of embeddings  that hit OpenAI limits
         document_batches = [documents[i : i + 2048] for i in range(0, len(documents), 2048)]
-        for batch in document_batches:
+        metadata_batches = [metadatas[i : i + 2048] for i in range(0, len(metadatas), 2048)]
+        id_batches = [ids[i : i + 2048] for i in range(0, len(ids), 2048)]
+        for batch_docs, batch_meta, batch_ids in zip(document_batches, metadata_batches, id_batches):
             try:
                 # Add only valid batches
-                if batch:
-                    self.db.add(documents=batch, metadatas=metadatas, ids=ids, **kwargs)
+                if batch_docs:
+                    self.db.add(documents=batch_docs, metadatas=batch_meta, ids=batch_ids, **kwargs)
             except Exception as e:
-                print(f"Failed to add batch due to a bad request: {e}")
+                logger.info(f"Failed to add batch due to a bad request: {e}")
                 # Handle the error, e.g., by logging, retrying, or skipping
                 pass
 
         count_new_chunks = self.db.count() - chunks_before_addition
-        print(f"Successfully saved {src} ({chunker.data_type}). New chunks count: {count_new_chunks}")
+        logger.info(f"Successfully saved {str(src)[:100]} ({chunker.data_type}). New chunks count: {count_new_chunks}")
 
         return list(documents), metadatas, ids, count_new_chunks
 
@@ -511,7 +496,7 @@ class EmbedChain(JSONSerializable):
             contexts_data_for_llm_query = contexts
 
         if self.cache_config is not None:
-            logging.info("Cache enabled. Checking cache...")
+            logger.info("Cache enabled. Checking cache...")
             answer = adapt(
                 llm_handler=self.llm.query,
                 cache_data_convert=gptcache_data_convert,
@@ -583,7 +568,7 @@ class EmbedChain(JSONSerializable):
         self.llm.update_history(app_id=self.config.id, session_id=session_id)
 
         if self.cache_config is not None:
-            logging.info("Cache enabled. Checking cache...")
+            logger.debug("Cache enabled. Checking cache...")
             cache_id = f"{session_id}--{self.config.id}"
             answer = adapt(
                 llm_handler=self.llm.chat,
@@ -596,6 +581,7 @@ class EmbedChain(JSONSerializable):
                 dry_run=dry_run,
             )
         else:
+            logger.debug("Cache disabled. Running chat without cache.")
             answer = self.llm.chat(
                 input_query=input_query, contexts=contexts_data_for_llm_query, config=config, dry_run=dry_run
             )
@@ -611,7 +597,7 @@ class EmbedChain(JSONSerializable):
         else:
             return answer
 
-    def search(self, query, num_documents=3, where=None, raw_filter=None):
+    def search(self, query, num_documents=3, where=None, raw_filter=None, namespace=None):
         """
         Search for similar documents related to the query in the vector database.
 
@@ -620,6 +606,7 @@ class EmbedChain(JSONSerializable):
             num_documents (int, optional): Number of similar documents to fetch. Defaults to 3.
             where (dict[str, any], optional): Filter criteria for the search.
             raw_filter (dict[str, any], optional): Advanced raw filter criteria for the search.
+            namespace (str, optional): The namespace to search in. Defaults to None.
 
         Raises:
             ValueError: If both `raw_filter` and `where` are used simultaneously.
@@ -641,6 +628,7 @@ class EmbedChain(JSONSerializable):
             "n_results": num_documents,
             "citations": True,
             "app_id": self.config.id,
+            "namespace": namespace,
             filter_type: filter_criteria,
         }
 
@@ -666,9 +654,15 @@ class EmbedChain(JSONSerializable):
         Resets the database. Deletes all embeddings irreversibly.
         `App` does not have to be reinitialized after using this method.
         """
+        try:
+            self.db_session.query(DataSource).filter_by(app_id=self.config.id).delete()
+            self.db_session.query(ChatHistory).filter_by(app_id=self.config.id).delete()
+            self.db_session.commit()
+        except Exception as e:
+            logger.error(f"Error deleting data sources: {e}")
+            self.db_session.rollback()
+            return None
         self.db.reset()
-        self.cursor.execute("DELETE FROM data_sources WHERE pipeline_id = ?", (self.config.id,))
-        self.connection.commit()
         self.delete_all_chat_history(app_id=self.config.id)
         # Send anonymous telemetry
         self.telemetry.capture(event_name="reset", properties=self._telemetry_props)
@@ -703,8 +697,15 @@ class EmbedChain(JSONSerializable):
         :param source_hash: The hash of the source.
         :type source_hash: str
         """
+        try:
+            self.db_session.query(DataSource).filter_by(hash=source_id, app_id=self.config.id).delete()
+            self.db_session.commit()
+        except Exception as e:
+            logger.error(f"Error deleting data sources: {e}")
+            self.db_session.rollback()
+            return None
         self.db.delete(where={"hash": source_id})
-        logging.info(f"Successfully deleted {source_id}")
+        logger.info(f"Successfully deleted {source_id}")
         # Send anonymous telemetry
         if self.config.collect_metrics:
             self.telemetry.capture(event_name="delete", properties=self._telemetry_props)

embedchain/embedder/cohere.py

@@ -0,0 +1,19 @@
+from typing import Optional
+
+from langchain_community.embeddings import CohereEmbeddings
+
+from embedchain.config import BaseEmbedderConfig
+from embedchain.embedder.base import BaseEmbedder
+from embedchain.models import VectorDimensions
+
+
+class CohereEmbedder(BaseEmbedder):
+    def __init__(self, config: Optional[BaseEmbedderConfig] = None):
+        super().__init__(config=config)
+
+        embeddings = CohereEmbeddings(model=self.config.model)
+        embedding_fn = BaseEmbedder._langchain_default_concept(embeddings)
+        self.set_embedding_fn(embedding_fn=embedding_fn)
+
+        vector_dimension = self.config.vector_dimension or VectorDimensions.COHERE.value
+        self.set_vector_dimension(vector_dimension=vector_dimension)

embedchain/embedder/nvidia.py

@@ -0,0 +1,28 @@
+import logging
+import os
+from typing import Optional
+
+from langchain_nvidia_ai_endpoints import NVIDIAEmbeddings
+
+from embedchain.config import BaseEmbedderConfig
+from embedchain.embedder.base import BaseEmbedder
+from embedchain.models import VectorDimensions
+
+logger = logging.getLogger(__name__)
+
+
+class NvidiaEmbedder(BaseEmbedder):
+    def __init__(self, config: Optional[BaseEmbedderConfig] = None):
+        if "NVIDIA_API_KEY" not in os.environ:
+            raise ValueError("NVIDIA_API_KEY environment variable must be set")
+
+        super().__init__(config=config)
+
+        model = self.config.model or "nvolveqa_40k"
+        logger.info(f"Using NVIDIA embedding model: {model}")
+        embedder = NVIDIAEmbeddings(model=model)
+        embedding_fn = BaseEmbedder._langchain_default_concept(embedder)
+        self.set_embedding_fn(embedding_fn=embedding_fn)
+
+        vector_dimension = self.config.vector_dimension or VectorDimensions.NVIDIA_AI.value
+        self.set_vector_dimension(vector_dimension=vector_dimension)

embedchain/embedder/openai.py

@@ -17,6 +17,7 @@ class OpenAIEmbedder(BaseEmbedder):
             self.config.model = "text-embedding-ada-002"
 
         api_key = self.config.api_key or os.environ["OPENAI_API_KEY"]
+        api_base = self.config.api_base or os.environ.get("OPENAI_API_BASE")
 
         if self.config.deployment_name:
             embeddings = AzureOpenAIEmbeddings(deployment=self.config.deployment_name)
@@ -28,6 +29,7 @@ class OpenAIEmbedder(BaseEmbedder):
                 )  # noqa:E501
             embedding_fn = OpenAIEmbeddingFunction(
                 api_key=api_key,
+                api_base=api_base,
                 organization_id=os.getenv("OPENAI_ORGANIZATION"),
                 model_name=self.config.model,
             )

embedchain/evaluation/metrics/answer_relevancy.py

@@ -12,6 +12,8 @@ from embedchain.config.evaluation.base import AnswerRelevanceConfig
 from embedchain.evaluation.base import BaseMetric
 from embedchain.utils.evaluation import EvalData, EvalMetric
 
+logger = logging.getLogger(__name__)
+
 
 class AnswerRelevance(BaseMetric):
     """
@@ -88,6 +90,6 @@ class AnswerRelevance(BaseMetric):
                 try:
                     results.append(future.result())
                 except Exception as e:
-                    logging.error(f"Error evaluating answer relevancy for {data}: {e}")
+                    logger.error(f"Error evaluating answer relevancy for {data}: {e}")
 
         return np.mean(results) if results else 0.0

embedchain/evaluation/metrics/groundedness.py

@@ -12,6 +12,8 @@ from embedchain.config.evaluation.base import GroundednessConfig
 from embedchain.evaluation.base import BaseMetric
 from embedchain.utils.evaluation import EvalData, EvalMetric
 
+logger = logging.getLogger(__name__)
+
 
 class Groundedness(BaseMetric):
     """
@@ -97,6 +99,6 @@ class Groundedness(BaseMetric):
                     score = future.result()
                     results.append(score)
                 except Exception as e:
-                    logging.error(f"Error while evaluating groundedness for data point {data}: {e}")
+                    logger.error(f"Error while evaluating groundedness for data point {data}: {e}")
 
         return np.mean(results) if results else 0.0

embedchain/factory.py

@@ -23,6 +23,9 @@ class LlmFactory:
         "google": "embedchain.llm.google.GoogleLlm",
         "aws_bedrock": "embedchain.llm.aws_bedrock.AWSBedrockLlm",
         "mistralai": "embedchain.llm.mistralai.MistralAILlm",
+        "groq": "embedchain.llm.groq.GroqLlm",
+        "nvidia": "embedchain.llm.nvidia.NvidiaLlm",
+        "vllm": "embedchain.llm.vllm.VLLM",
     }
     provider_to_config_class = {
         "embedchain": "embedchain.config.llm.base.BaseLlmConfig",
@@ -53,13 +56,15 @@ class EmbedderFactory:
         "vertexai": "embedchain.embedder.vertexai.VertexAIEmbedder",
         "google": "embedchain.embedder.google.GoogleAIEmbedder",
         "mistralai": "embedchain.embedder.mistralai.MistralAIEmbedder",
+        "nvidia": "embedchain.embedder.nvidia.NvidiaEmbedder",
+        "cohere": "embedchain.embedder.cohere.CohereEmbedder",
     }
     provider_to_config_class = {
         "azure_openai": "embedchain.config.embedder.base.BaseEmbedderConfig",
-        "openai": "embedchain.config.embedder.base.BaseEmbedderConfig",
-        "gpt4all": "embedchain.config.embedder.base.BaseEmbedderConfig",
         "google": "embedchain.config.embedder.google.GoogleAIEmbedderConfig",
+        "gpt4all": "embedchain.config.embedder.base.BaseEmbedderConfig",
         "huggingface": "embedchain.config.embedder.base.BaseEmbedderConfig",
+        "openai": "embedchain.config.embedder.base.BaseEmbedderConfig",
     }
 
     @classmethod

embedchain/helpers/callbacks.py

@@ -56,7 +56,7 @@ def generate(rq: queue.Queue):
     ```
     def askQuestion(callback_fn: StreamingStdOutCallbackHandlerYield):
         llm = OpenAI(streaming=True, callbacks=[callback_fn])
-        return llm(prompt="Write a poem about a tree.")
+        return llm.invoke(prompt="Write a poem about a tree.")
 
     @app.route("/", methods=["GET"])
     def generate_output():

embedchain/helpers/json_serializable.py

@@ -8,6 +8,8 @@ T = TypeVar("T", bound="JSONSerializable")
 # NOTE: Through inheritance, all of our classes should be children of JSONSerializable. (highest level)
 # NOTE: The @register_deserializable decorator should be added to all user facing child classes. (lowest level)
 
+logger = logging.getLogger(__name__)
+
 
 def register_deserializable(cls: Type[T]) -> Type[T]:
     """
@@ -57,7 +59,7 @@ class JSONSerializable:
         try:
             return json.dumps(self, default=self._auto_encoder, ensure_ascii=False)
         except Exception as e:
-            logging.error(f"Serialization error: {e}")
+            logger.error(f"Serialization error: {e}")
             return "{}"
 
     @classmethod
@@ -79,7 +81,7 @@ class JSONSerializable:
         try:
             return json.loads(json_str, object_hook=cls._auto_decoder)
         except Exception as e:
-            logging.error(f"Deserialization error: {e}")
+            logger.error(f"Deserialization error: {e}")
             # Return a default instance in case of failure
             return cls()
 

embedchain/llm/anthropic.py

@@ -2,10 +2,17 @@ import logging
 import os
 from typing import Optional
 
+try:
+    from langchain_anthropic import ChatAnthropic
+except ImportError:
+    raise ImportError("Please install the langchain-anthropic package by running `pip install langchain-anthropic`.")
+
 from embedchain.config import BaseLlmConfig
 from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
+logger = logging.getLogger(__name__)
+
 
 @register_deserializable
 class AnthropicLlm(BaseLlm):
@@ -19,14 +26,12 @@ class AnthropicLlm(BaseLlm):
 
     @staticmethod
     def _get_answer(prompt: str, config: BaseLlmConfig) -> str:
-        from langchain_community.chat_models import ChatAnthropic
-
         chat = ChatAnthropic(
-            anthropic_api_key=os.environ["ANTHROPIC_API_KEY"], temperature=config.temperature, model=config.model
+            anthropic_api_key=os.environ["ANTHROPIC_API_KEY"], temperature=config.temperature, model_name=config.model
         )
 
         if config.max_tokens and config.max_tokens != 1000:
-            logging.warning("Config option `max_tokens` is not supported by this model.")
+            logger.warning("Config option `max_tokens` is not supported by this model.")
 
         messages = BaseLlm._get_messages(prompt, system_prompt=config.system_prompt)
 

embedchain/llm/aws_bedrock.py

@@ -46,4 +46,4 @@ class AWSBedrockLlm(BaseLlm):
         else:
             llm = Bedrock(**kwargs)
 
-        return llm(prompt)
+        return llm.invoke(prompt)

embedchain/llm/azure_openai.py

@@ -5,6 +5,8 @@ from embedchain.config import BaseLlmConfig
 from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
+logger = logging.getLogger(__name__)
+
 
 @register_deserializable
 class AzureOpenAILlm(BaseLlm):
@@ -31,7 +33,7 @@ class AzureOpenAILlm(BaseLlm):
         )
 
         if config.top_p and config.top_p != 1:
-            logging.warning("Config option `top_p` is not supported by this model.")
+            logger.warning("Config option `top_p` is not supported by this model.")
 
         messages = BaseLlm._get_messages(prompt, system_prompt=config.system_prompt)
 

embedchain/llm/base.py

@@ -12,6 +12,8 @@ from embedchain.helpers.json_serializable import JSONSerializable
 from embedchain.memory.base import ChatHistory
 from embedchain.memory.message import ChatMessage
 
+logger = logging.getLogger(__name__)
+
 
 class BaseLlm(JSONSerializable):
     def __init__(self, config: Optional[BaseLlmConfig] = None):
@@ -108,7 +110,7 @@ class BaseLlm(JSONSerializable):
                 )
             else:
                 # If we can't swap in the default, we still proceed but tell users that the history is ignored.
-                logging.warning(
+                logger.warning(
                     "Your bot contains a history, but prompt does not include `$history` key. History is ignored."
                 )
                 prompt = self.config.prompt.substitute(context=context_string, query=input_query)
@@ -159,7 +161,7 @@ class BaseLlm(JSONSerializable):
                 'Searching requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
             ) from None
         search = DuckDuckGoSearchRun()
-        logging.info(f"Access search to get answers for {input_query}")
+        logger.info(f"Access search to get answers for {input_query}")
         return search.run(input_query)
 
     @staticmethod
@@ -175,7 +177,7 @@ class BaseLlm(JSONSerializable):
         for chunk in answer:
             streamed_answer = streamed_answer + chunk
             yield chunk
-        logging.info(f"Answer: {streamed_answer}")
+        logger.info(f"Answer: {streamed_answer}")
 
     def query(self, input_query: str, contexts: list[str], config: BaseLlmConfig = None, dry_run=False):
         """
@@ -214,13 +216,13 @@ class BaseLlm(JSONSerializable):
             if self.online:
                 k["web_search_result"] = self.access_search_and_get_results(input_query)
             prompt = self.generate_prompt(input_query, contexts, **k)
-            logging.info(f"Prompt: {prompt}")
+            logger.info(f"Prompt: {prompt}")
             if dry_run:
                 return prompt
 
             answer = self.get_answer_from_llm(prompt)
             if isinstance(answer, str):
-                logging.info(f"Answer: {answer}")
+                logger.info(f"Answer: {answer}")
                 return answer
             else:
                 return self._stream_response(answer)
@@ -270,14 +272,14 @@ class BaseLlm(JSONSerializable):
                 k["web_search_result"] = self.access_search_and_get_results(input_query)
 
             prompt = self.generate_prompt(input_query, contexts, **k)
-            logging.info(f"Prompt: {prompt}")
+            logger.info(f"Prompt: {prompt}")
 
             if dry_run:
                 return prompt
 
             answer = self.get_answer_from_llm(prompt)
             if isinstance(answer, str):
-                logging.info(f"Answer: {answer}")
+                logger.info(f"Answer: {answer}")
                 return answer
             else:
                 # this is a streamed response and needs to be handled differently.

embedchain/llm/cohere.py

@@ -40,4 +40,4 @@ class CohereLlm(BaseLlm):
             p=config.top_p,
         )
 
-        return llm(prompt)
+        return llm.invoke(prompt)

embedchain/llm/google.py

@@ -10,6 +10,8 @@ from embedchain.config import BaseLlmConfig
 from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
+logger = logging.getLogger(__name__)
+
 
 @register_deserializable
 class GoogleLlm(BaseLlm):
@@ -36,7 +38,7 @@ class GoogleLlm(BaseLlm):
 
     def _get_answer(self, prompt: str) -> Union[str, Generator[Any, Any, None]]:
         model_name = self.config.model or "gemini-pro"
-        logging.info(f"Using Google LLM model: {model_name}")
+        logger.info(f"Using Google LLM model: {model_name}")
         model = genai.GenerativeModel(model_name=model_name)
 
         generation_config_params = {

embedchain/llm/groq.py

@@ -0,0 +1,43 @@
+import os
+from typing import Optional
+
+from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+from langchain.schema import HumanMessage, SystemMessage
+
+try:
+    from langchain_groq import ChatGroq
+except ImportError:
+    raise ImportError("Groq requires extra dependencies. Install with `pip install langchain-groq`") from None
+
+
+from embedchain.config import BaseLlmConfig
+from embedchain.helpers.json_serializable import register_deserializable
+from embedchain.llm.base import BaseLlm
+
+
+@register_deserializable
+class GroqLlm(BaseLlm):
+    def __init__(self, config: Optional[BaseLlmConfig] = None):
+        super().__init__(config=config)
+
+    def get_llm_model_answer(self, prompt) -> str:
+        response = self._get_answer(prompt, self.config)
+        return response
+
+    def _get_answer(self, prompt: str, config: BaseLlmConfig) -> str:
+        messages = []
+        if config.system_prompt:
+            messages.append(SystemMessage(content=config.system_prompt))
+        messages.append(HumanMessage(content=prompt))
+        api_key = config.api_key or os.environ["GROQ_API_KEY"]
+        kwargs = {
+            "model_name": config.model or "mixtral-8x7b-32768",
+            "temperature": config.temperature,
+            "groq_api_key": api_key,
+        }
+        if config.stream:
+            callbacks = config.callbacks if config.callbacks else [StreamingStdOutCallbackHandler()]
+            chat = ChatGroq(**kwargs, streaming=config.stream, callbacks=callbacks, api_key=api_key)
+        else:
+            chat = ChatGroq(**kwargs)
+        return chat.invoke(messages).content

embedchain/llm/huggingface.py

@@ -5,11 +5,14 @@ from typing import Optional
 
 from langchain_community.llms.huggingface_endpoint import HuggingFaceEndpoint
 from langchain_community.llms.huggingface_hub import HuggingFaceHub
+from langchain_community.llms.huggingface_pipeline import HuggingFacePipeline
 
 from embedchain.config import BaseLlmConfig
 from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
+logger = logging.getLogger(__name__)
+
 
 @register_deserializable
 class HuggingFaceLlm(BaseLlm):
@@ -34,12 +37,15 @@ class HuggingFaceLlm(BaseLlm):
 
     @staticmethod
     def _get_answer(prompt: str, config: BaseLlmConfig) -> str:
-        if config.model:
+        # If the user wants to run the model locally, they can do so by setting the `local` flag to True
+        if config.model and config.local:
+            return HuggingFaceLlm._from_pipeline(prompt=prompt, config=config)
+        elif config.model:
             return HuggingFaceLlm._from_model(prompt=prompt, config=config)
         elif config.endpoint:
             return HuggingFaceLlm._from_endpoint(prompt=prompt, config=config)
         else:
-            raise ValueError("Either `model` or `endpoint` must be set")
+            raise ValueError("Either `model` or `endpoint` must be set in config")
 
     @staticmethod
     def _from_model(prompt: str, config: BaseLlmConfig) -> str:
@@ -53,15 +59,14 @@ class HuggingFaceLlm(BaseLlm):
         else:
             raise ValueError("`top_p` must be > 0.0 and < 1.0")
 
-        model = config.model or "google/flan-t5-xxl"
-        logging.info(f"Using HuggingFaceHub with model {model}")
+        model = config.model
+        logger.info(f"Using HuggingFaceHub with model {model}")
         llm = HuggingFaceHub(
             huggingfacehub_api_token=os.environ["HUGGINGFACE_ACCESS_TOKEN"],
             repo_id=model,
             model_kwargs=model_kwargs,
         )
-
-        return llm(prompt)
+        return llm.invoke(prompt)
 
     @staticmethod
     def _from_endpoint(prompt: str, config: BaseLlmConfig) -> str:
@@ -71,4 +76,23 @@ class HuggingFaceLlm(BaseLlm):
             task="text-generation",
             model_kwargs=config.model_kwargs,
         )
-        return llm(prompt)
+        return llm.invoke(prompt)
+
+    @staticmethod
+    def _from_pipeline(prompt: str, config: BaseLlmConfig) -> str:
+        model_kwargs = {
+            "temperature": config.temperature or 0.1,
+            "max_new_tokens": config.max_tokens,
+        }
+
+        if 0.0 < config.top_p < 1.0:
+            model_kwargs["top_p"] = config.top_p
+        else:
+            raise ValueError("`top_p` must be > 0.0 and < 1.0")
+
+        llm = HuggingFacePipeline.from_model_id(
+            model_id=config.model,
+            task="text-generation",
+            pipeline_kwargs=model_kwargs,
+        )
+        return llm.invoke(prompt)

embedchain/llm/llama2.py

@@ -48,4 +48,4 @@ class Llama2Llm(BaseLlm):
                 "top_p": self.config.top_p,
             },
         )
-        return llm(prompt)
+        return llm.invoke(prompt)

embedchain/llm/nvidia.py

@@ -0,0 +1,47 @@
+import os
+from collections.abc import Iterable
+from typing import Optional, Union
+
+from langchain.callbacks.manager import CallbackManager
+from langchain.callbacks.stdout import StdOutCallbackHandler
+from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+
+try:
+    from langchain_nvidia_ai_endpoints import ChatNVIDIA
+except ImportError:
+    raise ImportError(
+        "NVIDIA AI endpoints requires extra dependencies. Install with `pip install langchain-nvidia-ai-endpoints`"
+    ) from None
+
+from embedchain.config import BaseLlmConfig
+from embedchain.helpers.json_serializable import register_deserializable
+from embedchain.llm.base import BaseLlm
+
+
+@register_deserializable
+class NvidiaLlm(BaseLlm):
+    def __init__(self, config: Optional[BaseLlmConfig] = None):
+        if "NVIDIA_API_KEY" not in os.environ:
+            raise ValueError("NVIDIA_API_KEY environment variable must be set")
+
+        super().__init__(config=config)
+
+    def get_llm_model_answer(self, prompt):
+        return self._get_answer(prompt=prompt, config=self.config)
+
+    @staticmethod
+    def _get_answer(prompt: str, config: BaseLlmConfig) -> Union[str, Iterable]:
+        callback_manager = [StreamingStdOutCallbackHandler()] if config.stream else [StdOutCallbackHandler()]
+        model_kwargs = config.model_kwargs or {}
+        labels = model_kwargs.get("labels", None)
+        params = {"model": config.model}
+        if config.system_prompt:
+            params["system_prompt"] = config.system_prompt
+        if config.temperature:
+            params["temperature"] = config.temperature
+        if config.top_p:
+            params["top_p"] = config.top_p
+        if labels:
+            params["labels"] = labels
+        llm = ChatNVIDIA(**params, callback_manager=CallbackManager(callback_manager))
+        return llm.invoke(prompt).content if labels is None else llm.invoke(prompt, labels=labels).content

embedchain/llm/ollama.py

@@ -31,6 +31,7 @@ class OllamaLlm(BaseLlm):
             temperature=config.temperature,
             top_p=config.top_p,
             callback_manager=CallbackManager(callback_manager),
+            base_url=config.base_url,
         )
 
-        return llm(prompt)
+        return llm.invoke(prompt)

embedchain/llm/openai.py

@@ -39,13 +39,20 @@ class OpenAILlm(BaseLlm):
             "model_kwargs": {},
         }
         api_key = config.api_key or os.environ["OPENAI_API_KEY"]
+        base_url = config.base_url or os.environ.get("OPENAI_API_BASE", None)
         if config.top_p:
             kwargs["model_kwargs"]["top_p"] = config.top_p
         if config.stream:
             callbacks = config.callbacks if config.callbacks else [StreamingStdOutCallbackHandler()]
-            chat = ChatOpenAI(**kwargs, streaming=config.stream, callbacks=callbacks, api_key=api_key)
+            chat = ChatOpenAI(
+                **kwargs,
+                streaming=config.stream,
+                callbacks=callbacks,
+                api_key=api_key,
+                base_url=base_url,
+            )
         else:
-            chat = ChatOpenAI(**kwargs, api_key=api_key)
+            chat = ChatOpenAI(**kwargs, api_key=api_key, base_url=base_url)
         if self.tools:
             return self._query_function_call(chat, self.tools, messages)
 

embedchain/llm/together.py

@@ -40,4 +40,4 @@ class TogetherLlm(BaseLlm):
             top_p=config.top_p,
         )
 
-        return llm(prompt)
+        return llm.invoke(prompt)

embedchain/llm/vertex_ai.py

@@ -9,6 +9,8 @@ from embedchain.config import BaseLlmConfig
 from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
+logger = logging.getLogger(__name__)
+
 
 @register_deserializable
 class VertexAILlm(BaseLlm):
@@ -28,7 +30,7 @@ class VertexAILlm(BaseLlm):
     @staticmethod
     def _get_answer(prompt: str, config: BaseLlmConfig) -> str:
         if config.top_p and config.top_p != 1:
-            logging.warning("Config option `top_p` is not supported by this model.")
+            logger.warning("Config option `top_p` is not supported by this model.")
 
         messages = BaseLlm._get_messages(prompt, system_prompt=config.system_prompt)
 

embedchain/llm/vllm.py

@@ -37,4 +37,4 @@ class VLLM(BaseLlm):
             llm_args.update(config.model_kwargs)
 
         llm = BaseVLLM(**llm_args)
-        return llm(prompt)
+        return llm.invoke(prompt)

embedchain/loaders/beehiiv.py

@@ -9,6 +9,8 @@ from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils.misc import is_readable
 
+logger = logging.getLogger(__name__)
+
 
 @register_deserializable
 class BeehiivLoader(BaseLoader):
@@ -90,9 +92,9 @@ class BeehiivLoader(BaseLoader):
                 if is_readable(data):
                     return data
                 else:
-                    logging.warning(f"Page is not readable (too many invalid characters): {link}")
+                    logger.warning(f"Page is not readable (too many invalid characters): {link}")
             except ParserRejectedMarkup as e:
-                logging.error(f"Failed to parse {link}: {e}")
+                logger.error(f"Failed to parse {link}: {e}")
             return None
 
         for link in links:

embedchain/loaders/directory_loader.py

@@ -10,6 +10,8 @@ from embedchain.loaders.base_loader import BaseLoader
 from embedchain.loaders.text_file import TextFileLoader
 from embedchain.utils.misc import detect_datatype
 
+logger = logging.getLogger(__name__)
+
 
 @register_deserializable
 class DirectoryLoader(BaseLoader):
@@ -27,12 +29,12 @@ class DirectoryLoader(BaseLoader):
         if not directory_path.is_dir():
             raise ValueError(f"Invalid path: {path}")
 
-        logging.info(f"Loading data from directory: {path}")
+        logger.info(f"Loading data from directory: {path}")
         data_list = self._process_directory(directory_path)
         doc_id = hashlib.sha256((str(data_list) + str(directory_path)).encode()).hexdigest()
 
         for error in self.errors:
-            logging.warning(error)
+            logger.warning(error)
 
         return {"doc_id": doc_id, "data": data_list}
 
@@ -46,7 +48,7 @@ class DirectoryLoader(BaseLoader):
                 loader = self._predict_loader(file_path)
                 data_list.extend(loader.load_data(str(file_path))["data"])
             elif file_path.is_dir():
-                logging.info(f"Loading data from directory: {file_path}")
+                logger.info(f"Loading data from directory: {file_path}")
         return data_list
 
     def _predict_loader(self, file_path: Path) -> BaseLoader:

embedchain/loaders/discord.py

@@ -5,6 +5,8 @@ import os
 from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 
+logger = logging.getLogger(__name__)
+
 
 @register_deserializable
 class DiscordLoader(BaseLoader):
@@ -102,7 +104,7 @@ class DiscordLoader(BaseLoader):
 
         class DiscordClient(discord.Client):
             async def on_ready(self) -> None:
-                logging.info("Logged on as {0}!".format(self.user))
+                logger.info("Logged on as {0}!".format(self.user))
                 try:
                     channel = self.get_channel(int(channel_id))
                     if not isinstance(channel, discord.TextChannel):
@@ -121,7 +123,7 @@ class DiscordLoader(BaseLoader):
                                 messages.append(DiscordLoader._format_message(thread_message))
 
                 except Exception as e:
-                    logging.error(e)
+                    logger.error(e)
                     await self.close()
                 finally:
                     await self.close()

embedchain/loaders/discourse.py

@@ -8,6 +8,8 @@ import requests
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils.misc import clean_string
 
+logger = logging.getLogger(__name__)
+
 
 class DiscourseLoader(BaseLoader):
     def __init__(self, config: Optional[dict[str, Any]] = None):
@@ -35,7 +37,7 @@ class DiscourseLoader(BaseLoader):
         try:
             response.raise_for_status()
         except Exception as e:
-            logging.error(f"Failed to load post {post_id}: {e}")
+            logger.error(f"Failed to load post {post_id}: {e}")
             return
         response_data = response.json()
         post_contents = clean_string(response_data.get("raw"))
@@ -56,7 +58,7 @@ class DiscourseLoader(BaseLoader):
         self._check_query(query)
         data = []
         data_contents = []
-        logging.info(f"Searching data on discourse url: {self.domain}, for query: {query}")
+        logger.info(f"Searching data on discourse url: {self.domain}, for query: {query}")
         search_url = f"{self.domain}search.json?q={query}"
         response = requests.get(search_url)
         try:

embedchain/loaders/docs_site_loader.py

@@ -15,6 +15,8 @@ except ImportError:
 from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 
+logger = logging.getLogger(__name__)
+
 
 @register_deserializable
 class DocsSiteLoader(BaseLoader):
@@ -28,7 +30,7 @@ class DocsSiteLoader(BaseLoader):
 
         response = requests.get(url)
         if response.status_code != 200:
-            logging.info(f"Failed to fetch the website: {response.status_code}")
+            logger.info(f"Failed to fetch the website: {response.status_code}")
             return
 
         soup = BeautifulSoup(response.text, "html.parser")
@@ -53,7 +55,7 @@ class DocsSiteLoader(BaseLoader):
     def _load_data_from_url(url: str) -> list:
         response = requests.get(url)
         if response.status_code != 200:
-            logging.info(f"Failed to fetch the website: {response.status_code}")
+            logger.info(f"Failed to fetch the website: {response.status_code}")
             return []
 
         soup = BeautifulSoup(response.content, "html.parser")

embedchain/loaders/excel_file.py

@@ -0,0 +1,40 @@
+import hashlib
+import importlib.util
+
+try:
+    from langchain_community.document_loaders import UnstructuredExcelLoader
+except ImportError:
+    raise ImportError(
+        'Excel file requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
+    ) from None
+
+if importlib.util.find_spec("openpyxl") is None and importlib.util.find_spec("xlrd") is None:
+    raise ImportError("Excel file requires extra dependencies. Install with `pip install openpyxl xlrd`") from None
+
+from embedchain.helpers.json_serializable import register_deserializable
+from embedchain.loaders.base_loader import BaseLoader
+from embedchain.utils.misc import clean_string
+
+
+@register_deserializable
+class ExcelFileLoader(BaseLoader):
+    def load_data(self, excel_url):
+        """Load data from a Excel file."""
+        loader = UnstructuredExcelLoader(excel_url)
+        pages = loader.load_and_split()
+
+        data = []
+        for page in pages:
+            content = page.page_content
+            content = clean_string(content)
+
+            metadata = page.metadata
+            metadata["url"] = excel_url
+
+            data.append({"content": content, "meta_data": metadata})
+
+        doc_id = hashlib.sha256((content + excel_url).encode()).hexdigest()
+        return {
+            "doc_id": doc_id,
+            "data": data,
+        }

embedchain/loaders/github.py

@@ -1,7 +1,6 @@
 import concurrent.futures
 import hashlib
 import logging
-import os
 import re
 import shlex
 from typing import Any, Optional
@@ -14,7 +13,7 @@ from embedchain.utils.misc import clean_string
 GITHUB_URL = "https://github.com"
 GITHUB_API_URL = "https://api.github.com"
 
-VALID_SEARCH_TYPES = set(["code", "repo", "pr", "issue", "discussion"])
+VALID_SEARCH_TYPES = set(["code", "repo", "pr", "issue", "discussion", "branch", "file"])
 
 
 class GithubLoader(BaseLoader):
@@ -66,85 +65,56 @@ class GithubLoader(BaseLoader):
             )
         return data
 
-    @staticmethod
-    def _get_github_repo_data(repo_url: str):
-        local_hash = hashlib.sha256(repo_url.encode()).hexdigest()
-        local_path = f"/tmp/{local_hash}"
+    def _get_github_repo_data(self, repo_name: str, branch_name: str = None, file_path: str = None) -> list[dict]:
+        """Get file contents from Repo"""
         data = []
 
-        def _get_repo_tree(repo_url: str, local_path: str):
-            try:
-                from git import Repo
-            except ImportError as e:
-                raise ValueError(
-                    "GithubLoader requires extra dependencies. Install with `pip install --upgrade 'embedchain[github]'`"  # noqa: E501
-                ) from e
+        repo = self.client.get_repo(repo_name)
+        repo_contents = repo.get_contents("")
 
-            if os.path.exists(local_path):
-                logging.info("Repository already exists. Fetching updates...")
-                repo = Repo(local_path)
-                logging.info("Fetch completed.")
-            else:
-                logging.info("Cloning repository...")
-                repo = Repo.clone_from(repo_url, local_path)
-                logging.info("Clone completed.")
-            return repo.head.commit.tree
+        if branch_name:
+            repo_contents = repo.get_contents("", ref=branch_name)
+        if file_path:
+            repo_contents = [repo.get_contents(file_path)]
 
-        def _get_repo_tree_contents(repo_path, tree, progress_bar):
-            for subtree in tree:
-                if subtree.type == "tree":
-                    _get_repo_tree_contents(repo_path, subtree, progress_bar)
-                else:
-                    assert subtree.type == "blob"
+        with tqdm(desc="Loading files:", unit="item") as progress_bar:
+            while repo_contents:
+                file_content = repo_contents.pop(0)
+                if file_content.type == "dir":
                     try:
-                        contents = subtree.data_stream.read().decode("utf-8")
+                        repo_contents.extend(repo.get_contents(file_content.path))
                     except Exception:
-                        logging.warning(f"Failed to read file: {subtree.path}")
-                        progress_bar.update(1) if progress_bar else None
+                        logging.warning(f"Failed to read directory: {file_content.path}")
+                        progress_bar.update(1)
+                        continue
+                else:
+                    try:
+                        file_text = file_content.decoded_content.decode()
+                    except Exception:
+                        logging.warning(f"Failed to read file: {file_content.path}")
+                        progress_bar.update(1)
                         continue
 
-                    url = f"{repo_url.rstrip('.git')}/blob/main/{subtree.path}"
+                    file_path = file_content.path
                     data.append(
                         {
-                            "content": clean_string(contents),
+                            "content": clean_string(file_text),
                             "meta_data": {
-                                "url": url,
+                                "path": file_path,
                             },
                         }
                     )
-                if progress_bar is not None:
-                    progress_bar.update(1)
 
-        repo_tree = _get_repo_tree(repo_url, local_path)
-        tree_list = list(repo_tree.traverse())
-        with tqdm(total=len(tree_list), desc="Loading files:", unit="item") as progress_bar:
-            _get_repo_tree_contents(local_path, repo_tree, progress_bar)
+                progress_bar.update(1)
 
         return data
 
     def _github_search_repo(self, query: str) -> list[dict]:
         """Search GitHub repo."""
-        data = []
-        logging.info(f"Searching github repos with query: {query}")
-        results = self.client.search_repositories(query)
-        # Add repo urls and descriptions
-        urls = list(map(lambda x: x.html_url, results))
-        descriptions = list(map(lambda x: x.description, results))
-        data.append(
-            {
-                "content": clean_string(desc),
-                "meta_data": {
-                    "url": url,
-                },
-            }
-            for url, desc in zip(urls, descriptions)
-        )
 
-        # Add repo contents
-        for result in results:
-            clone_url = result.clone_url
-            logging.info(f"Cloning repository: {clone_url}")
-            data = self._get_github_repo_data(clone_url)
+        logging.info(f"Searching github repos with query: {query}")
+        updated_query = query.split(":")[-1]
+        data = self._get_github_repo_data(updated_query)
         return data
 
     def _github_search_issues_and_pr(self, query: str, type: str) -> list[dict]:
@@ -222,6 +192,43 @@ class GithubLoader(BaseLoader):
                     )
         return data
 
+    def _get_github_repo_branch(self, query: str, type: str) -> list[dict]:
+        """Get file contents for specific branch"""
+
+        logging.info(f"Searching github repo for query: {query} is:{type}")
+        pattern = r"repo:(\S+) name:(\S+)"
+        match = re.search(pattern, query)
+
+        if match:
+            repo_name = match.group(1)
+            branch_name = match.group(2)
+        else:
+            raise ValueError(
+                f"Repository name and Branch name not found, instead found this \
+                    Repo: {repo_name}, Branch: {branch_name}"
+            )
+
+        data = self._get_github_repo_data(repo_name=repo_name, branch_name=branch_name)
+        return data
+
+    def _get_github_repo_file(self, query: str, type: str) -> list[dict]:
+        """Get specific file content"""
+
+        logging.info(f"Searching github repo for query: {query} is:{type}")
+        pattern = r"repo:(\S+) path:(\S+)"
+        match = re.search(pattern, query)
+
+        if match:
+            repo_name = match.group(1)
+            file_path = match.group(2)
+        else:
+            raise ValueError(
+                f"Repository name and File name not found, instead found this Repo: {repo_name}, File: {file_path}"
+            )
+
+        data = self._get_github_repo_data(repo_name=repo_name, file_path=file_path)
+        return data
+
     def _search_github_data(self, search_type: str, query: str):
         """Search github data."""
         if search_type == "code":
@@ -232,6 +239,10 @@ class GithubLoader(BaseLoader):
             data = self._github_search_issues_and_pr(query, search_type)
         elif search_type == "pr":
             data = self._github_search_issues_and_pr(query, search_type)
+        elif search_type == "branch":
+            data = self._get_github_repo_branch(query, search_type)
+        elif search_type == "file":
+            data = self._get_github_repo_file(query, search_type)
         elif search_type == "discussion":
             raise ValueError("GithubLoader does not support searching discussions yet.")
         else:

embedchain/loaders/gmail.py

@@ -22,6 +22,8 @@ except ImportError:
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils.misc import clean_string
 
+logger = logging.getLogger(__name__)
+
 
 class GmailReader:
     SCOPES = ["https://www.googleapis.com/auth/gmail.readonly"]
@@ -114,7 +116,7 @@ class GmailLoader(BaseLoader):
     def load_data(self, query: str):
         reader = GmailReader(query=query)
         emails = reader.load_emails()
-        logging.info(f"Gmail Loader: {len(emails)} emails found for query '{query}'")
+        logger.info(f"Gmail Loader: {len(emails)} emails found for query '{query}'")
 
         data = []
         for email in emails:

embedchain/loaders/mysql.py

@@ -5,6 +5,8 @@ from typing import Any, Optional
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils.misc import clean_string
 
+logger = logging.getLogger(__name__)
+
 
 class MySQLLoader(BaseLoader):
     def __init__(self, config: Optional[dict[str, Any]]):
@@ -32,7 +34,7 @@ class MySQLLoader(BaseLoader):
             self.connection = sqlconnector.connection.MySQLConnection(**config)
             self.cursor = self.connection.cursor()
         except (sqlconnector.Error, IOError) as err:
-            logging.info(f"Connection failed: {err}")
+            logger.info(f"Connection failed: {err}")
             raise ValueError(
                 f"Unable to connect with the given config: {config}.",
                 "Please provide the correct configuration to load data from you MySQL DB. \

embedchain/loaders/notion.py

@@ -9,6 +9,8 @@ from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils.misc import clean_string
 
+logger = logging.getLogger(__name__)
+
 
 class NotionDocument:
     """
@@ -98,7 +100,7 @@ class NotionLoader(BaseLoader):
 
         id = source[-32:]
         formatted_id = f"{id[:8]}-{id[8:12]}-{id[12:16]}-{id[16:20]}-{id[20:]}"
-        logging.debug(f"Extracted notion page id as: {formatted_id}")
+        logger.debug(f"Extracted notion page id as: {formatted_id}")
 
         integration_token = os.getenv("NOTION_INTEGRATION_TOKEN")
         reader = NotionPageLoader(integration_token=integration_token)

embedchain/loaders/postgres.py

@@ -4,6 +4,8 @@ from typing import Any, Optional
 
 from embedchain.loaders.base_loader import BaseLoader
 
+logger = logging.getLogger(__name__)
+
 
 class PostgresLoader(BaseLoader):
     def __init__(self, config: Optional[dict[str, Any]] = None):
@@ -32,7 +34,7 @@ class PostgresLoader(BaseLoader):
                 conn_params.append(f"{key}={value}")
             config_info = " ".join(conn_params)
 
-        logging.info(f"Connecting to postrgres sql: {config_info}")
+        logger.info(f"Connecting to postrgres sql: {config_info}")
         self.connection = psycopg.connect(conninfo=config_info)
         self.cursor = self.connection.cursor()
 

embedchain/loaders/sitemap.py

@@ -19,6 +19,8 @@ from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.loaders.web_page import WebPageLoader
 
+logger = logging.getLogger(__name__)
+
 
 @register_deserializable
 class SitemapLoader(BaseLoader):
@@ -41,7 +43,7 @@ class SitemapLoader(BaseLoader):
                 response.raise_for_status()
                 soup = BeautifulSoup(response.text, "xml")
             except requests.RequestException as e:
-                logging.error(f"Error fetching sitemap from URL: {e}")
+                logger.error(f"Error fetching sitemap from URL: {e}")
                 return
         elif os.path.isfile(sitemap_source):
             with open(sitemap_source, "r") as file:
@@ -60,7 +62,7 @@ class SitemapLoader(BaseLoader):
                 loader_data = web_page_loader.load_data(link)
                 return loader_data.get("data")
             except ParserRejectedMarkup as e:
-                logging.error(f"Failed to parse {link}: {e}")
+                logger.error(f"Failed to parse {link}: {e}")
             return None
 
         with concurrent.futures.ThreadPoolExecutor() as executor:
@@ -72,6 +74,6 @@ class SitemapLoader(BaseLoader):
                     if data:
                         output.extend(data)
                 except Exception as e:
-                    logging.error(f"Error loading page {link}: {e}")
+                    logger.error(f"Error loading page {link}: {e}")
 
         return {"doc_id": doc_id, "data": output}

embedchain/loaders/slack.py

@@ -11,6 +11,8 @@ from embedchain.utils.misc import clean_string
 
 SLACK_API_BASE_URL = "https://www.slack.com/api/"
 
+logger = logging.getLogger(__name__)
+
 
 class SlackLoader(BaseLoader):
     def __init__(self, config: Optional[dict[str, Any]] = None):
@@ -38,7 +40,7 @@ class SlackLoader(BaseLoader):
                 "SLACK_USER_TOKEN environment variables not provided. Check `https://docs.embedchain.ai/data-sources/slack` to learn more."  # noqa:E501
             )
 
-        logging.info(f"Creating Slack Loader with config: {config}")
+        logger.info(f"Creating Slack Loader with config: {config}")
         # get slack client config params
         slack_bot_token = os.getenv("SLACK_USER_TOKEN")
         ssl_cert = ssl.create_default_context(cafile=certifi.where())
@@ -54,7 +56,7 @@ class SlackLoader(BaseLoader):
             headers=headers,
             team_id=team_id,
         )
-        logging.info("Slack Loader setup successful!")
+        logger.info("Slack Loader setup successful!")
 
     @staticmethod
     def _check_query(query):
@@ -69,7 +71,7 @@ class SlackLoader(BaseLoader):
             data = []
             data_content = []
 
-            logging.info(f"Searching slack conversations for query: {query}")
+            logger.info(f"Searching slack conversations for query: {query}")
             results = self.client.search_messages(
                 query=query,
                 sort="timestamp",
@@ -79,7 +81,7 @@ class SlackLoader(BaseLoader):
 
             messages = results.get("messages")
             num_message = len(messages)
-            logging.info(f"Found {num_message} messages for query: {query}")
+            logger.info(f"Found {num_message} messages for query: {query}")
 
             matches = messages.get("matches", [])
             for message in matches:
@@ -107,7 +109,7 @@ class SlackLoader(BaseLoader):
                 "data": data,
             }
         except Exception as e:
-            logging.warning(f"Error in loading slack data: {e}")
+            logger.warning(f"Error in loading slack data: {e}")
             raise ValueError(
                 f"Error in loading slack data: {e}. Check `https://docs.embedchain.ai/data-sources/slack` to learn more."  # noqa:E501
             ) from e

embedchain/loaders/substack.py

@@ -9,6 +9,8 @@ from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils.misc import is_readable
 
+logger = logging.getLogger(__name__)
+
 
 @register_deserializable
 class SubstackLoader(BaseLoader):
@@ -90,9 +92,9 @@ class SubstackLoader(BaseLoader):
                 if is_readable(data):
                     return data
                 else:
-                    logging.warning(f"Page is not readable (too many invalid characters): {link}")
+                    logger.warning(f"Page is not readable (too many invalid characters): {link}")
             except ParserRejectedMarkup as e:
-                logging.error(f"Failed to parse {link}: {e}")
+                logger.error(f"Failed to parse {link}: {e}")
             return None
 
         for link in links:

embedchain/loaders/web_page.py

@@ -14,6 +14,8 @@ from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils.misc import clean_string
 
+logger = logging.getLogger(__name__)
+
 
 @register_deserializable
 class WebPageLoader(BaseLoader):
@@ -87,7 +89,7 @@ class WebPageLoader(BaseLoader):
 
         cleaned_size = len(content)
         if original_size != 0:
-            logging.info(
+            logger.info(
                 f"[{url}] Cleaned page size: {cleaned_size} characters, down from {original_size} (shrunk: {original_size-cleaned_size} chars, {round((1-(cleaned_size/original_size)) * 100, 2)}%)"  # noqa:E501
             )
 

embedchain/loaders/youtube_channel.py

@@ -7,6 +7,8 @@ from tqdm import tqdm
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.loaders.youtube_video import YoutubeVideoLoader
 
+logger = logging.getLogger(__name__)
+
 
 class YoutubeChannelLoader(BaseLoader):
     """Loader for youtube channel."""
@@ -36,7 +38,7 @@ class YoutubeChannelLoader(BaseLoader):
                         videos = [entry["url"] for entry in info_dict["entries"]]
                         return videos
             except Exception:
-                logging.error(f"Failed to fetch youtube videos for channel: {channel_name}")
+                logger.error(f"Failed to fetch youtube videos for channel: {channel_name}")
                 return []
 
         def _load_yt_video(video_link):
@@ -45,12 +47,12 @@ class YoutubeChannelLoader(BaseLoader):
                 if each_load_data:
                     return each_load_data.get("data")
             except Exception as e:
-                logging.error(f"Failed to load youtube video {video_link}: {e}")
+                logger.error(f"Failed to load youtube video {video_link}: {e}")
             return None
 
         def _add_youtube_channel():
             video_links = _get_yt_video_links()
-            logging.info("Loading videos from youtube channel...")
+            logger.info("Loading videos from youtube channel...")
             with concurrent.futures.ThreadPoolExecutor() as executor:
                 # Submitting all tasks and storing the future object with the video link
                 future_to_video = {
@@ -67,7 +69,7 @@ class YoutubeChannelLoader(BaseLoader):
                             data.extend(results)
                             data_urls.extend([result.get("meta_data").get("url") for result in results])
                     except Exception as e:
-                        logging.error(f"Failed to process youtube video {video}: {e}")
+                        logger.error(f"Failed to process youtube video {video}: {e}")
 
         _add_youtube_channel()
         doc_id = hashlib.sha256((youtube_url + ", ".join(data_urls)).encode()).hexdigest()

embedchain/memory/base.py

@@ -1,56 +1,43 @@
 import json
 import logging
-import sqlite3
 import uuid
 from typing import Any, Optional
 
-from embedchain.constants import SQLITE_PATH
+from embedchain.core.db.database import get_session
+from embedchain.core.db.models import ChatHistory as ChatHistoryModel
 from embedchain.memory.message import ChatMessage
 from embedchain.memory.utils import merge_metadata_dict
 
-CHAT_MESSAGE_CREATE_TABLE_QUERY = """
-    CREATE TABLE IF NOT EXISTS ec_chat_history (
-        app_id TEXT,
-        id TEXT,
-        session_id TEXT,
-        question TEXT,
-        answer TEXT,
-        metadata TEXT,
-        created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
-        PRIMARY KEY (id, app_id, session_id)
-    )
-"""
+logger = logging.getLogger(__name__)
 
 
 class ChatHistory:
     def __init__(self) -> None:
-        with sqlite3.connect(SQLITE_PATH, check_same_thread=False) as self.connection:
-            self.cursor = self.connection.cursor()
-            self.cursor.execute(CHAT_MESSAGE_CREATE_TABLE_QUERY)
-            self.connection.commit()
+        self.db_session = get_session()
 
     def add(self, app_id, session_id, chat_message: ChatMessage) -> Optional[str]:
         memory_id = str(uuid.uuid4())
         metadata_dict = merge_metadata_dict(chat_message.human_message.metadata, chat_message.ai_message.metadata)
         if metadata_dict:
             metadata = self._serialize_json(metadata_dict)
-        ADD_CHAT_MESSAGE_QUERY = """
-            INSERT INTO ec_chat_history (app_id, id, session_id, question, answer, metadata)
-            VALUES (?, ?, ?, ?, ?, ?)
-        """
-        self.cursor.execute(
-            ADD_CHAT_MESSAGE_QUERY,
-            (
-                app_id,
-                memory_id,
-                session_id,
-                chat_message.human_message.content,
-                chat_message.ai_message.content,
-                metadata if metadata_dict else "{}",
-            ),
+        self.db_session.add(
+            ChatHistoryModel(
+                app_id=app_id,
+                id=memory_id,
+                session_id=session_id,
+                question=chat_message.human_message.content,
+                answer=chat_message.ai_message.content,
+                metadata=metadata if metadata_dict else "{}",
+            )
         )
-        self.connection.commit()
-        logging.info(f"Added chat memory to db with id: {memory_id}")
+        try:
+            self.db_session.commit()
+        except Exception as e:
+            logger.error(f"Error adding chat memory to db: {e}")
+            self.db_session.rollback()
+            return None
+
+        logger.info(f"Added chat memory to db with id: {memory_id}")
         return memory_id
 
     def delete(self, app_id: str, session_id: Optional[str] = None):
@@ -63,15 +50,15 @@ class ChatHistory:
 
         :return: None
         """
+        params = {"app_id": app_id}
         if session_id:
-            DELETE_CHAT_HISTORY_QUERY = "DELETE FROM ec_chat_history WHERE app_id=? AND session_id=?"
-            params = (app_id, session_id)
-        else:
-            DELETE_CHAT_HISTORY_QUERY = "DELETE FROM ec_chat_history WHERE app_id=?"
-            params = (app_id,)
-
-        self.cursor.execute(DELETE_CHAT_HISTORY_QUERY, params)
-        self.connection.commit()
+            params["session_id"] = session_id
+        self.db_session.query(ChatHistoryModel).filter_by(**params).delete()
+        try:
+            self.db_session.commit()
+        except Exception as e:
+            logger.error(f"Error deleting chat history: {e}")
+            self.db_session.rollback()
 
     def get(
         self, app_id, session_id: str = "default", num_rounds=10, fetch_all: bool = False, display_format=False
@@ -85,50 +72,31 @@ class ChatHistory:
         param: fetch_all (optional) - Whether to fetch all chat history or not. Defaults to False
         param: display_format (optional) - Whether to return the chat history in display format. Defaults to False
         """
-
-        base_query = """
-            SELECT * FROM ec_chat_history
-            WHERE app_id=?
-        """
-
-        if fetch_all:
-            additional_query = "ORDER BY created_at ASC"
-            params = (app_id,)
-        else:
-            additional_query = """
-                AND session_id=?
-                ORDER BY created_at ASC
-                LIMIT ?
-            """
-            params = (app_id, session_id, num_rounds)
-
-        QUERY = base_query + additional_query
-
-        self.cursor.execute(
-            QUERY,
-            params,
+        params = {"app_id": app_id}
+        if not fetch_all:
+            params["session_id"] = session_id
+        results = (
+            self.db_session.query(ChatHistoryModel).filter_by(**params).order_by(ChatHistoryModel.created_at.asc())
         )
-
-        results = self.cursor.fetchall()
+        results = results.limit(num_rounds) if not fetch_all else results
         history = []
         for result in results:
-            app_id, _, session_id, question, answer, metadata, timestamp = result
-            metadata = self._deserialize_json(metadata=metadata)
+            metadata = self._deserialize_json(metadata=result.meta_data or "{}")
             # Return list of dict if display_format is True
             if display_format:
                 history.append(
                     {
-                        "session_id": session_id,
-                        "human": question,
-                        "ai": answer,
-                        "metadata": metadata,
-                        "timestamp": timestamp,
+                        "session_id": result.session_id,
+                        "human": result.question,
+                        "ai": result.answer,
+                        "metadata": result.meta_data,
+                        "timestamp": result.created_at,
                     }
                 )
             else:
                 memory = ChatMessage()
-                memory.add_user_message(question, metadata=metadata)
-                memory.add_ai_message(answer, metadata=metadata)
+                memory.add_user_message(result.question, metadata=metadata)
+                memory.add_ai_message(result.answer, metadata=metadata)
                 history.append(memory)
         return history
 
@@ -141,16 +109,11 @@ class ChatHistory:
 
         :return: The number of chat messages for a given app_id and session_id
         """
+        # Rewrite the logic below with sqlalchemy
+        params = {"app_id": app_id}
         if session_id:
-            QUERY = "SELECT COUNT(*) FROM ec_chat_history WHERE app_id=? AND session_id=?"
-            params = (app_id, session_id)
-        else:
-            QUERY = "SELECT COUNT(*) FROM ec_chat_history WHERE app_id=?"
-            params = (app_id,)
-
-        self.cursor.execute(QUERY, params)
-        count = self.cursor.fetchone()[0]
-        return count
+            params["session_id"] = session_id
+        return self.db_session.query(ChatHistoryModel).filter_by(**params).count()
 
     @staticmethod
     def _serialize_json(metadata: dict[str, Any]):

embedchain/memory/message.py

@@ -3,6 +3,8 @@ from typing import Any, Optional
 
 from embedchain.helpers.json_serializable import JSONSerializable
 
+logger = logging.getLogger(__name__)
+
 
 class BaseMessage(JSONSerializable):
     """
@@ -52,7 +54,7 @@ class ChatMessage(JSONSerializable):
 
     def add_user_message(self, message: str, metadata: Optional[dict] = None):
         if self.human_message:
-            logging.info(
+            logger.info(
                 "Human message already exists in the chat message,\
                 overwriting it with new message."
             )
@@ -61,7 +63,7 @@ class ChatMessage(JSONSerializable):
 
     def add_ai_message(self, message: str, metadata: Optional[dict] = None):
         if self.ai_message:
-            logging.info(
+            logger.info(
                 "AI message already exists in the chat message,\
                 overwriting it with new message."
             )

embedchain/migrations/env.py

@@ -0,0 +1,68 @@
+import os
+
+from alembic import context
+from sqlalchemy import engine_from_config, pool
+
+from embedchain.core.db.models import Base
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+target_metadata = Base.metadata
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+config.set_main_option("sqlalchemy.url", os.environ.get("EMBEDCHAIN_DB_URI"))
+
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section, {}),
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(connection=connection, target_metadata=target_metadata)
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

embedchain/migrations/script.py.mako

@@ -0,0 +1,26 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, None] = ${repr(down_revision)}
+branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
+depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}

embedchain/migrations/versions/40a327b3debd_create_initial_migrations.py

@@ -0,0 +1,62 @@
+"""Create initial migrations
+
+Revision ID: 40a327b3debd
+Revises:
+Create Date: 2024-02-18 15:29:19.409064
+
+"""
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "40a327b3debd"
+down_revision: Union[str, None] = None
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table(
+        "ec_chat_history",
+        sa.Column("app_id", sa.String(), nullable=False),
+        sa.Column("id", sa.String(), nullable=False),
+        sa.Column("session_id", sa.String(), nullable=False),
+        sa.Column("question", sa.Text(), nullable=True),
+        sa.Column("answer", sa.Text(), nullable=True),
+        sa.Column("metadata", sa.Text(), nullable=True),
+        sa.Column("created_at", sa.TIMESTAMP(), nullable=True),
+        sa.PrimaryKeyConstraint("app_id", "id", "session_id"),
+    )
+    op.create_index(op.f("ix_ec_chat_history_created_at"), "ec_chat_history", ["created_at"], unique=False)
+    op.create_index(op.f("ix_ec_chat_history_session_id"), "ec_chat_history", ["session_id"], unique=False)
+    op.create_table(
+        "ec_data_sources",
+        sa.Column("id", sa.String(), nullable=False),
+        sa.Column("app_id", sa.Text(), nullable=True),
+        sa.Column("hash", sa.Text(), nullable=True),
+        sa.Column("type", sa.Text(), nullable=True),
+        sa.Column("value", sa.Text(), nullable=True),
+        sa.Column("metadata", sa.Text(), nullable=True),
+        sa.Column("is_uploaded", sa.Integer(), nullable=True),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_index(op.f("ix_ec_data_sources_hash"), "ec_data_sources", ["hash"], unique=False)
+    op.create_index(op.f("ix_ec_data_sources_app_id"), "ec_data_sources", ["app_id"], unique=False)
+    op.create_index(op.f("ix_ec_data_sources_type"), "ec_data_sources", ["type"], unique=False)
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index(op.f("ix_ec_data_sources_type"), table_name="ec_data_sources")
+    op.drop_index(op.f("ix_ec_data_sources_app_id"), table_name="ec_data_sources")
+    op.drop_index(op.f("ix_ec_data_sources_hash"), table_name="ec_data_sources")
+    op.drop_table("ec_data_sources")
+    op.drop_index(op.f("ix_ec_chat_history_session_id"), table_name="ec_chat_history")
+    op.drop_index(op.f("ix_ec_chat_history_created_at"), table_name="ec_chat_history")
+    op.drop_table("ec_chat_history")
+    # ### end Alembic commands ###

embedchain/models/data_type.py

@@ -40,6 +40,7 @@ class IndirectDataType(Enum):
     SLACK = "slack"
     DROPBOX = "dropbox"
     TEXT_FILE = "text_file"
+    EXCEL_FILE = "excel_file"
 
 
 class SpecialDataType(Enum):
@@ -79,3 +80,4 @@ class DataType(Enum):
     SLACK = IndirectDataType.SLACK.value
     DROPBOX = IndirectDataType.DROPBOX.value
     TEXT_FILE = IndirectDataType.TEXT_FILE.value
+    EXCEL_FILE = IndirectDataType.EXCEL_FILE.value

embedchain/models/vector_dimensions.py

@@ -9,3 +9,5 @@ class VectorDimensions(Enum):
     HUGGING_FACE = 384
     GOOGLE_AI = 768
     MISTRAL_AI = 1024
+    NVIDIA_AI = 1024
+    COHERE = 384

embedchain/store/assistants.py

@@ -17,10 +17,8 @@ from embedchain.models.data_type import DataType
 from embedchain.telemetry.posthog import AnonymousTelemetry
 from embedchain.utils.misc import detect_datatype
 
-logging.basicConfig(level=logging.WARN)
-
 # Set up the user directory if it doesn't exist already
-Client.setup_dir()
+Client.setup()
 
 
 class OpenAIAssistant:
@@ -33,7 +31,7 @@ class OpenAIAssistant:
         model="gpt-4-1106-preview",
         data_sources=None,
         assistant_id=None,
-        log_level=logging.WARN,
+        log_level=logging.INFO,
         collect_metrics=True,
     ):
         self.name = name or "OpenAI Assistant"
@@ -156,11 +154,9 @@ class AIAssistant:
         assistant_id=None,
         thread_id=None,
         data_sources=None,
-        log_level=logging.WARN,
+        log_level=logging.INFO,
         collect_metrics=True,
     ):
-        logging.basicConfig(level=log_level)
-
         self.name = name or "AI Assistant"
         self.data_sources = data_sources or []
         self.log_level = log_level

embedchain/telemetry/posthog.py

@@ -12,8 +12,6 @@ HOME_DIR = str(Path.home())
 CONFIG_DIR = os.path.join(HOME_DIR, ".embedchain")
 CONFIG_FILE = os.path.join(CONFIG_DIR, "config.json")
 
-logger = logging.getLogger(__name__)
-
 
 class AnonymousTelemetry:
     def __init__(self, host="https://app.posthog.com", enabled=True):
@@ -63,4 +61,4 @@ class AnonymousTelemetry:
         try:
             self.posthog.capture(self.user_id, event_name, properties)
         except Exception:
-            logger.exception(f"Failed to send telemetry {event_name=}")
+            logging.exception(f"Failed to send telemetry {event_name=}")

embedchain/utils/misc.py

@@ -11,6 +11,8 @@ from tqdm import tqdm
 
 from embedchain.models.data_type import DataType
 
+logger = logging.getLogger(__name__)
+
 
 def parse_content(content, type):
     implemented = ["html.parser", "lxml", "lxml-xml", "xml", "html5lib"]
@@ -61,7 +63,7 @@ def parse_content(content, type):
 
     cleaned_size = len(content)
     if original_size != 0:
-        logging.info(
+        logger.info(
             f"Cleaned page size: {cleaned_size} characters, down from {original_size} (shrunk: {original_size-cleaned_size} chars, {round((1-(cleaned_size/original_size)) * 100, 2)}%)"  # noqa:E501
         )
 
@@ -208,31 +210,31 @@ def detect_datatype(source: Any) -> DataType:
         }
 
         if url.netloc in YOUTUBE_ALLOWED_NETLOCKS:
-            logging.debug(f"Source of `{formatted_source}` detected as `youtube_video`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `youtube_video`.")
             return DataType.YOUTUBE_VIDEO
 
         if url.netloc in {"notion.so", "notion.site"}:
-            logging.debug(f"Source of `{formatted_source}` detected as `notion`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `notion`.")
             return DataType.NOTION
 
         if url.path.endswith(".pdf"):
-            logging.debug(f"Source of `{formatted_source}` detected as `pdf_file`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `pdf_file`.")
             return DataType.PDF_FILE
 
         if url.path.endswith(".xml"):
-            logging.debug(f"Source of `{formatted_source}` detected as `sitemap`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `sitemap`.")
             return DataType.SITEMAP
 
         if url.path.endswith(".csv"):
-            logging.debug(f"Source of `{formatted_source}` detected as `csv`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `csv`.")
             return DataType.CSV
 
         if url.path.endswith(".mdx") or url.path.endswith(".md"):
-            logging.debug(f"Source of `{formatted_source}` detected as `mdx`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `mdx`.")
             return DataType.MDX
 
         if url.path.endswith(".docx"):
-            logging.debug(f"Source of `{formatted_source}` detected as `docx`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `docx`.")
             return DataType.DOCX
 
         if url.path.endswith(".yaml"):
@@ -242,14 +244,14 @@ def detect_datatype(source: Any) -> DataType:
                 try:
                     yaml_content = yaml.safe_load(response.text)
                 except yaml.YAMLError as exc:
-                    logging.error(f"Error parsing YAML: {exc}")
+                    logger.error(f"Error parsing YAML: {exc}")
                     raise TypeError(f"Not a valid data type. Error loading YAML: {exc}")
 
                 if is_openapi_yaml(yaml_content):
-                    logging.debug(f"Source of `{formatted_source}` detected as `openapi`.")
+                    logger.debug(f"Source of `{formatted_source}` detected as `openapi`.")
                     return DataType.OPENAPI
                 else:
-                    logging.error(
+                    logger.error(
                         f"Source of `{formatted_source}` does not contain all the required \
                         fields of OpenAPI yaml. Check 'https://spec.openapis.org/oas/v3.1.0'"
                     )
@@ -258,35 +260,35 @@ def detect_datatype(source: Any) -> DataType:
                         make sure you have all the required fields in YAML config data"
                     )
             except requests.exceptions.RequestException as e:
-                logging.error(f"Error fetching URL {formatted_source}: {e}")
+                logger.error(f"Error fetching URL {formatted_source}: {e}")
 
         if url.path.endswith(".json"):
-            logging.debug(f"Source of `{formatted_source}` detected as `json_file`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `json_file`.")
             return DataType.JSON
 
         if "docs" in url.netloc or ("docs" in url.path and url.scheme != "file"):
             # `docs_site` detection via path is not accepted for local filesystem URIs,
             # because that would mean all paths that contain `docs` are now doc sites, which is too aggressive.
-            logging.debug(f"Source of `{formatted_source}` detected as `docs_site`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `docs_site`.")
             return DataType.DOCS_SITE
 
         if "github.com" in url.netloc:
-            logging.debug(f"Source of `{formatted_source}` detected as `github`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `github`.")
             return DataType.GITHUB
 
         if is_google_drive_folder(url.netloc + url.path):
-            logging.debug(f"Source of `{formatted_source}` detected as `google drive folder`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `google drive folder`.")
             return DataType.GOOGLE_DRIVE_FOLDER
 
         # If none of the above conditions are met, it's a general web page
-        logging.debug(f"Source of `{formatted_source}` detected as `web_page`.")
+        logger.debug(f"Source of `{formatted_source}` detected as `web_page`.")
         return DataType.WEB_PAGE
 
     elif not isinstance(source, str):
         # For datatypes where source is not a string.
 
         if isinstance(source, tuple) and len(source) == 2 and isinstance(source[0], str) and isinstance(source[1], str):
-            logging.debug(f"Source of `{formatted_source}` detected as `qna_pair`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `qna_pair`.")
             return DataType.QNA_PAIR
 
         # Raise an error if it isn't a string and also not a valid non-string type (one of the previous).
@@ -300,37 +302,37 @@ def detect_datatype(source: Any) -> DataType:
         # Note: checking for string is not necessary anymore.
 
         if source.endswith(".docx"):
-            logging.debug(f"Source of `{formatted_source}` detected as `docx`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `docx`.")
             return DataType.DOCX
 
         if source.endswith(".csv"):
-            logging.debug(f"Source of `{formatted_source}` detected as `csv`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `csv`.")
             return DataType.CSV
 
         if source.endswith(".xml"):
-            logging.debug(f"Source of `{formatted_source}` detected as `xml`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `xml`.")
             return DataType.XML
 
         if source.endswith(".mdx") or source.endswith(".md"):
-            logging.debug(f"Source of `{formatted_source}` detected as `mdx`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `mdx`.")
             return DataType.MDX
 
         if source.endswith(".txt"):
-            logging.debug(f"Source of `{formatted_source}` detected as `text`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `text`.")
             return DataType.TEXT_FILE
 
         if source.endswith(".pdf"):
-            logging.debug(f"Source of `{formatted_source}` detected as `pdf_file`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `pdf_file`.")
             return DataType.PDF_FILE
 
         if source.endswith(".yaml"):
             with open(source, "r") as file:
                 yaml_content = yaml.safe_load(file)
                 if is_openapi_yaml(yaml_content):
-                    logging.debug(f"Source of `{formatted_source}` detected as `openapi`.")
+                    logger.debug(f"Source of `{formatted_source}` detected as `openapi`.")
                     return DataType.OPENAPI
                 else:
-                    logging.error(
+                    logger.error(
                         f"Source of `{formatted_source}` does not contain all the required \
                                   fields of OpenAPI yaml. Check 'https://spec.openapis.org/oas/v3.1.0'"
                     )
@@ -340,11 +342,11 @@ def detect_datatype(source: Any) -> DataType:
                     )
 
         if source.endswith(".json"):
-            logging.debug(f"Source of `{formatted_source}` detected as `json`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `json`.")
             return DataType.JSON
 
         if os.path.exists(source) and is_readable(open(source).read()):
-            logging.debug(f"Source of `{formatted_source}` detected as `text_file`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `text_file`.")
             return DataType.TEXT_FILE
 
         # If the source is a valid file, that's not detectable as a type, an error is raised.
@@ -360,11 +362,11 @@ def detect_datatype(source: Any) -> DataType:
 
         # check if the source is valid json string
         if is_valid_json_string(source):
-            logging.debug(f"Source of `{formatted_source}` detected as `json`.")
+            logger.debug(f"Source of `{formatted_source}` detected as `json`.")
             return DataType.JSON
 
         # Use text as final fallback.
-        logging.debug(f"Source of `{formatted_source}` detected as `text`.")
+        logger.debug(f"Source of `{formatted_source}` detected as `text`.")
         return DataType.TEXT
 
 
@@ -405,9 +407,13 @@ def validate_config(config_data):
                     "google",
                     "aws_bedrock",
                     "mistralai",
+                    "vllm",
+                    "groq",
+                    "nvidia",
                 ),
                 Optional("config"): {
                     Optional("model"): str,
+                    Optional("model_name"): str,
                     Optional("number_documents"): int,
                     Optional("temperature"): float,
                     Optional("max_tokens"): int,
@@ -420,8 +426,11 @@ def validate_config(config_data):
                     Optional("where"): dict,
                     Optional("query_type"): str,
                     Optional("api_key"): str,
+                    Optional("base_url"): str,
                     Optional("endpoint"): str,
                     Optional("model_kwargs"): dict,
+                    Optional("local"): bool,
+                    Optional("base_url"): str,
                 },
             },
             Optional("vectordb"): {
@@ -439,11 +448,13 @@ def validate_config(config_data):
                     "azure_openai",
                     "google",
                     "mistralai",
+                    "nvidia",
                 ),
                 Optional("config"): {
                     Optional("model"): Optional(str),
                     Optional("deployment_name"): Optional(str),
                     Optional("api_key"): str,
+                    Optional("api_base"): str,
                     Optional("title"): str,
                     Optional("task_type"): str,
                     Optional("vector_dimension"): int,
@@ -458,6 +469,7 @@ def validate_config(config_data):
                     "azure_openai",
                     "google",
                     "mistralai",
+                    "nvidia",
                 ),
                 Optional("config"): {
                     Optional("model"): str,

embedchain/vectordb/chroma.py

@@ -22,6 +22,9 @@ except RuntimeError:
     from chromadb.errors import InvalidDimensionException
 
 
+logger = logging.getLogger(__name__)
+
+
 @register_deserializable
 class ChromaDB(BaseVectorDB):
     """Vector database using ChromaDB."""
@@ -47,7 +50,7 @@ class ChromaDB(BaseVectorDB):
                     setattr(self.settings, key, value)
 
         if self.config.host and self.config.port:
-            logging.info(f"Connecting to ChromaDB server: {self.config.host}:{self.config.port}")
+            logger.info(f"Connecting to ChromaDB server: {self.config.host}:{self.config.port}")
             self.settings.chroma_server_host = self.config.host
             self.settings.chroma_server_http_port = self.config.port
             self.settings.chroma_api_impl = "chromadb.api.fastapi.FastAPI"

embedchain/vectordb/elasticsearch.py

@@ -14,6 +14,8 @@ from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.utils.misc import chunks
 from embedchain.vectordb.base import BaseVectorDB
 
+logger = logging.getLogger(__name__)
+
 
 @register_deserializable
 class ElasticsearchDB(BaseVectorDB):
@@ -62,7 +64,7 @@ class ElasticsearchDB(BaseVectorDB):
         """
         This method is needed because `embedder` attribute needs to be set externally before it can be initialized.
         """
-        logging.info(self.client.info())
+        logger.info(self.client.info())
         index_settings = {
             "mappings": {
                 "properties": {

embedchain/vectordb/opensearch.py

@@ -19,6 +19,8 @@ from embedchain.config import OpenSearchDBConfig
 from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.vectordb.base import BaseVectorDB
 
+logger = logging.getLogger(__name__)
+
 
 @register_deserializable
 class OpenSearchDB(BaseVectorDB):
@@ -43,12 +45,12 @@ class OpenSearchDB(BaseVectorDB):
             **self.config.extra_params,
         )
         info = self.client.info()
-        logging.info(f"Connected to {info['version']['distribution']}. Version: {info['version']['number']}")
+        logger.info(f"Connected to {info['version']['distribution']}. Version: {info['version']['number']}")
         # Remove auth credentials from config after successful connection
         super().__init__(config=self.config)
 
     def _initialize(self):
-        logging.info(self.client.info())
+        logger.info(self.client.info())
         index_name = self._get_index()
         if self.client.indices.exists(index=index_name):
             print(f"Index '{index_name}' already exists.")

embedchain/vectordb/pinecone.py

@@ -6,7 +6,7 @@ try:
     import pinecone
 except ImportError:
     raise ImportError(
-        "Pinecone requires extra dependencies. Install with `pip install --upgrade 'embedchain[pinecone]'`"
+        "Pinecone requires extra dependencies. Install with `pip install pinecone-text pinecone-client`"
     ) from None
 
 from pinecone_text.sparse import BM25Encoder
@@ -16,6 +16,8 @@ from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.utils.misc import chunks
 from embedchain.vectordb.base import BaseVectorDB
 
+logger = logging.getLogger(__name__)
+
 
 @register_deserializable
 class PineconeDB(BaseVectorDB):
@@ -49,9 +51,8 @@ class PineconeDB(BaseVectorDB):
         # Setup BM25Encoder if sparse vectors are to be used
         self.bm25_encoder = None
         if self.config.hybrid_search:
-            # TODO: Add support for fitting BM25Encoder on any corpus
-            logging.info("Initializing BM25Encoder for sparse vectors..")
-            self.bm25_encoder = BM25Encoder.default()
+            logger.info("Initializing BM25Encoder for sparse vectors..")
+            self.bm25_encoder = self.config.bm25_encoder if self.config.bm25_encoder else BM25Encoder.default()
 
         # Call parent init here because embedder is needed
         super().__init__(config=self.config)
@@ -102,9 +103,10 @@ class PineconeDB(BaseVectorDB):
         existing_ids = list()
         metadatas = []
 
+        batch_size = 100
         if ids is not None:
-            for i in range(0, len(ids), 1000):
-                result = self.pinecone_index.fetch(ids=ids[i : i + 1000])
+            for i in range(0, len(ids), batch_size):
+                result = self.pinecone_index.fetch(ids=ids[i : i + batch_size])
                 vectors = result.get("vectors")
                 batch_existing_ids = list(vectors.keys())
                 existing_ids.extend(batch_existing_ids)
@@ -230,6 +232,9 @@ class PineconeDB(BaseVectorDB):
     @staticmethod
     def _generate_filter(where: dict):
         query = {}
+        if where is None:
+            return query
+
         for k, v in where.items():
             query[k] = {"$eq": v}
         return query

embedchain/vectordb/qdrant.py

@@ -1,6 +1,5 @@
 import copy
 import os
-import uuid
 from typing import Any, Optional, Union
 
 try:
@@ -146,7 +145,7 @@ class QdrantDB(BaseVectorDB):
         qdrant_ids = []
         for id, document, metadata in zip(ids, documents, metadatas):
             metadata["text"] = document
-            qdrant_ids.append(str(uuid.uuid4()))
+            qdrant_ids.append(id)
             payloads.append({"identifier": id, "text": document, "metadata": copy.deepcopy(metadata)})
 
         for i in tqdm(range(0, len(qdrant_ids), self.BATCH_SIZE), desc="Adding data in batches"):

embedchain/vectordb/zilliz.py

@@ -13,6 +13,8 @@ except ImportError:
         "Zilliz requires extra dependencies. Install with `pip install --upgrade embedchain[milvus]`"
     ) from None
 
+logger = logging.getLogger(__name__)
+
 
 @register_deserializable
 class ZillizVectorDB(BaseVectorDB):
@@ -62,7 +64,7 @@ class ZillizVectorDB(BaseVectorDB):
         :type name: str
         """
         if utility.has_collection(name):
-            logging.info(f"[ZillizDB]: found an existing collection {name}, make sure the auto-id is disabled.")
+            logger.info(f"[ZillizDB]: found an existing collection {name}, make sure the auto-id is disabled.")
             self.collection = Collection(name)
         else:
             fields = [

examples/api_server/api_server.py

@@ -7,6 +7,9 @@ from embedchain import App
 app = Flask(__name__)
 
 
+logger = logging.getLogger(__name__)
+
+
 @app.route("/add", methods=["POST"])
 def add():
     data = request.get_json()
@@ -17,7 +20,7 @@ def add():
             App().add(url_or_text, data_type=data_type)
             return jsonify({"data": f"Added {data_type}: {url_or_text}"}), 200
         except Exception:
-            logging.exception(f"Failed to add {data_type=}: {url_or_text=}")
+            logger.exception(f"Failed to add {data_type=}: {url_or_text=}")
             return jsonify({"error": f"Failed to add {data_type}: {url_or_text}"}), 500
     return jsonify({"error": "Invalid request. Please provide 'data_type' and 'url_or_text' in JSON format."}), 400
 
@@ -31,7 +34,7 @@ def query():
             response = App().query(question)
             return jsonify({"data": response}), 200
         except Exception:
-            logging.exception(f"Failed to query {question=}")
+            logger.exception(f"Failed to query {question=}")
             return jsonify({"error": "An error occurred. Please try again!"}), 500
     return jsonify({"error": "Invalid request. Please provide 'question' in JSON format."}), 400
 
@@ -45,7 +48,7 @@ def chat():
             response = App().chat(question)
             return jsonify({"data": response}), 200
         except Exception:
-            logging.exception(f"Failed to chat {question=}")
+            logger.exception(f"Failed to chat {question=}")
             return jsonify({"error": "An error occurred. Please try again!"}), 500
     return jsonify({"error": "Invalid request. Please provide 'question' in JSON format."}), 400
 

examples/chat-pdf/requirements.txt

@@ -1,3 +1,4 @@
 streamlit
 embedchain
-pysqlite3-binary
+langchain-text-splitters
+pysqlite3-binary

examples/nextjs/nextjs_discord/app.py

@@ -12,10 +12,12 @@ intents.message_content = True
 client = discord.Client(intents=intents)
 discord_bot_name = os.environ["DISCORD_BOT_NAME"]
 
+logger = logging.getLogger(__name__)
+
 
 class NextJSBot:
     def __init__(self) -> None:
-        logging.info("NextJS Bot powered with embedchain.")
+        logger.info("NextJS Bot powered with embedchain.")
 
     def add(self, _):
         raise ValueError("Add is not implemented yet")
@@ -31,11 +33,11 @@ class NextJSBot:
             try:
                 response = response.json()
             except Exception:
-                logging.error(f"Failed to parse response: {response}")
+                logger.error(f"Failed to parse response: {response}")
                 response = {}
             return response
         except Exception:
-            logging.exception(f"Failed to query {message}.")
+            logger.exception(f"Failed to query {message}.")
             response = "An error occurred. Please try again!"
         return response
 
@@ -49,7 +51,7 @@ NEXTJS_BOT = NextJSBot()
 
 @client.event
 async def on_ready():
-    logging.info(f"User {client.user.name} logged in with id: {client.user.id}!")
+    logger.info(f"User {client.user.name} logged in with id: {client.user.id}!")
 
 
 def _get_question(message):

examples/nextjs/nextjs_slack/app.py

@@ -9,6 +9,8 @@ from slack_bolt.adapter.socket_mode import SocketModeHandler
 
 load_dotenv(".env")
 
+logger = logging.getLogger(__name__)
+
 
 def remove_mentions(message):
     mention_pattern = re.compile(r"<@[^>]+>")
@@ -19,7 +21,7 @@ def remove_mentions(message):
 
 class SlackBotApp:
     def __init__(self) -> None:
-        logging.info("Slack Bot using Embedchain!")
+        logger.info("Slack Bot using Embedchain!")
 
     def add(self, _):
         raise ValueError("Add is not implemented yet")
@@ -35,11 +37,11 @@ class SlackBotApp:
             try:
                 response = response.json()
             except Exception:
-                logging.error(f"Failed to parse response: {response}")
+                logger.error(f"Failed to parse response: {response}")
                 response = {}
             return response
         except Exception:
-            logging.exception(f"Failed to query {query}.")
+            logger.exception(f"Failed to query {query}.")
             response = "An error occurred. Please try again!"
         return response
 

examples/rest-api/main.py

@@ -13,6 +13,8 @@ from utils import generate_error_message_for_api_keys
 from embedchain import App
 from embedchain.client import Client
 
+logger = logging.getLogger(__name__)
+
 Base.metadata.create_all(bind=engine)
 
 
@@ -84,7 +86,7 @@ async def create_app_using_default_config(app_id: str, config: UploadFile = None
 
         return DefaultResponse(response=f"App created successfully. App ID: {app_id}")
     except Exception as e:
-        logging.warning(str(e))
+        logger.warning(str(e))
         raise HTTPException(detail=f"Error creating app: {str(e)}", status_code=400)
 
 
@@ -114,13 +116,13 @@ async def get_datasources_associated_with_app_id(app_id: str, db: Session = Depe
         response = app.get_data_sources()
         return {"results": response}
     except ValueError as ve:
-        logging.warning(str(ve))
+        logger.warning(str(ve))
         raise HTTPException(
             detail=generate_error_message_for_api_keys(ve),
             status_code=400,
         )
     except Exception as e:
-        logging.warning(str(e))
+        logger.warning(str(e))
         raise HTTPException(detail=f"Error occurred: {str(e)}", status_code=400)
 
 
@@ -153,13 +155,13 @@ async def add_datasource_to_an_app(body: SourceApp, app_id: str, db: Session = D
         response = app.add(source=body.source, data_type=body.data_type)
         return DefaultResponse(response=response)
     except ValueError as ve:
-        logging.warning(str(ve))
+        logger.warning(str(ve))
         raise HTTPException(
             detail=generate_error_message_for_api_keys(ve),
             status_code=400,
         )
     except Exception as e:
-        logging.warning(str(e))
+        logger.warning(str(e))
         raise HTTPException(detail=f"Error occurred: {str(e)}", status_code=400)
 
 
@@ -191,13 +193,13 @@ async def query_an_app(body: QueryApp, app_id: str, db: Session = Depends(get_db
         response = app.query(body.query)
         return DefaultResponse(response=response)
     except ValueError as ve:
-        logging.warning(str(ve))
+        logger.warning(str(ve))
         raise HTTPException(
             detail=generate_error_message_for_api_keys(ve),
             status_code=400,
         )
     except Exception as e:
-        logging.warning(str(e))
+        logger.warning(str(e))
         raise HTTPException(detail=f"Error occurred: {str(e)}", status_code=400)
 
 
@@ -274,13 +276,13 @@ async def deploy_app(body: DeployAppRequest, app_id: str, db: Session = Depends(
         app.deploy()
         return DefaultResponse(response="App deployed successfully.")
     except ValueError as ve:
-        logging.warning(str(ve))
+        logger.warning(str(ve))
         raise HTTPException(
             detail=generate_error_message_for_api_keys(ve),
             status_code=400,
         )
     except Exception as e:
-        logging.warning(str(e))
+        logger.warning(str(e))
         raise HTTPException(detail=f"Error occurred: {str(e)}", status_code=400)