Bump version to v0.0.73 (#819)

.env.example

@@ -1 +1 @@
-OPENAI_API_KEY=
+OPENAI_API_KEY="your-openai-api-key"

.github/workflows/cd.yml

@@ -23,10 +23,10 @@ jobs:
         run: |
           curl -sSL https://install.python-poetry.org | python3 -
           echo "$HOME/.local/bin" >> $GITHUB_PATH
-  
+
       - name: Install dependencies
         run: poetry install
-  
+
       - name: Build a binary wheel and a source tarball
         run: poetry build
 

.github/workflows/ci.yml

@@ -23,9 +23,9 @@ jobs:
       - name: Install dependencies
         run: poetry install --all-extras
       - name: Lint with ruff
-        run: make ci_lint
+        run: make lint
       - name: Test with pytest
-        run: make ci_test
+        run: make test
       - name: Generate coverage report
         run: make coverage
       - name: Upload coverage reports to Codecov

.gitignore

@@ -76,7 +76,7 @@ docs/_build/
 target/
 
 # Jupyter Notebook
-.ipynb_checkpoints
+*.yaml
 
 # IPython
 profile_default/
@@ -171,3 +171,6 @@ db
 .idea/
 
 .DS_Store
+
+notebooks/*.yaml
+.ipynb_checkpoints/

Makefile

@@ -18,6 +18,9 @@ install_es:
 install_opensearch:
 	poetry install --extras opensearch
 
+install_milvus:
+	poetry install --extras milvus
+
 shell:
 	poetry shell
 
@@ -28,19 +31,13 @@ format:
 	$(PYTHON) -m black .
 	$(PYTHON) -m isort .
 
-lint:
-	$(PYTHON) -m ruff .
-
 clean:
 	rm -rf dist build *.egg-info
 
-test:
-	$(PYTHON) -m pytest
-
-ci_lint:
+lint:
 	poetry run ruff .
 
-ci_test:
+test:
 	poetry run pytest
 
 coverage:

README.md

@@ -8,7 +8,7 @@
 [![Open in Colab](https://camo.githubusercontent.com/84f0493939e0c4de4e6dbe113251b4bfb5353e57134ffd9fcab6b8714514d4d1/68747470733a2f2f636f6c61622e72657365617263682e676f6f676c652e636f6d2f6173736574732f636f6c61622d62616467652e737667)](https://colab.research.google.com/drive/138lMWhENGeEu7Q1-6lNbNTHGLZXBBz_B?usp=sharing)
 [![codecov](https://codecov.io/gh/embedchain/embedchain/graph/badge.svg?token=EMRRHZXW1Q)](https://codecov.io/gh/embedchain/embedchain)
 
-Embedchain is a framework to easily create LLM powered bots over any dataset. If you want a javascript version, check out [embedchain-js](https://github.com/embedchain/embedchain/tree/main/embedchain-js)
+Embedchain is a Data Platform for LLMs - load, index, retrieve, and sync any unstructured data. Using embedchain, you can easily create LLM powered apps over any data. If you want a javascript version, check out [embedchain-js](https://github.com/embedchain/embedchain/tree/main/embedchain-js)
 
 ## Community
 
@@ -36,7 +36,7 @@ The documentation for embedchain can be found at [docs.embedchain.ai](https://do
 
 ## 💻 Usage
 
-Embedchain empowers you to create chatbot models similar to ChatGPT, using your own evolving dataset.
+Embedchain empowers you to create ChatGPT like apps, on your own dynamic dataset.
 
 ### Data Types Supported
 
@@ -46,7 +46,9 @@ Embedchain empowers you to create chatbot models similar to ChatGPT, using your
 * Sitemap
 * Doc file
 * Code documentation website loader
-* Notion
+* Notion and many more.
+
+You can find the full list of data types on [our documentation](https://docs.embedchain.ai/data-sources/csv).
 
 ### Queries
 
@@ -81,14 +83,18 @@ For more reference, please go through [Development Guide](https://docs.embedchai
   <img src="https://contrib.rocks/image?repo=embedchain/embedchain" />
 </a>
 
+## Telemetry
+
+We collect anonymous usage metrics to enhance our package's quality and user experience. This includes data like feature usage frequency and system info, but never personal details. The data helps us prioritize improvements and ensure compatibility. If you wish to opt-out, set the `app.config.collect_metrics = False` in the code. We prioritize data security and don't share this data externally.
+
 ## Citation
 
 If you utilize this repository, please consider citing it with:
 
 ```
 @misc{embedchain,
-  author = {Taranjeet Singh},
-  title = {Embedchain: Framework to easily create LLM powered bots over any dataset},
+  author = {Taranjeet Singh, Deshraj Yadav},
+  title = {Embedchain: Data platform for LLMs - load, index, retrieve, and sync any unstructured data},
   year = {2023},
   publisher = {GitHub},
   journal = {GitHub repository},

configs/anthropic.yaml

@@ -0,0 +1,8 @@
+llm:
+  provider: anthropic
+  model: 'claude-instant-1'
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+    stream: false

configs/azure_openai.yaml

@@ -0,0 +1,19 @@
+app:
+  config:
+    id: azure-openai-app
+
+llm:
+  provider: azure_openai
+  model: gpt-35-turbo
+  config:
+    deployment_name: your_llm_deployment_name
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+    stream: false
+
+embedder:
+  provider: azure_openai
+  config:
+    model: text-embedding-ada-002
+    deployment_name: you_embedding_model_deployment_name

configs/chroma.yaml

@@ -0,0 +1,26 @@
+app:
+  config:
+    id: 'my-app'
+    collection_name: 'my-app'
+
+llm:
+  provider: openai
+  model: 'gpt-3.5-turbo'
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+    stream: false
+
+vectordb:
+  provider: chroma
+  config:
+    collection_name: 'my-app'
+    dir: db
+    allow_reset: true
+
+embedder:
+  provider: openai
+  config:
+    model: 'text-embedding-ada-002'
+    deployment_name: null

configs/cohere.yaml

@@ -0,0 +1,7 @@
+llm:
+  provider: cohere
+  model: large
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1

configs/full-stack.yaml

@@ -0,0 +1,35 @@
+app:
+  config:
+    id: 'full-stack-app'
+
+llm:
+  provider: openai
+  model: 'gpt-3.5-turbo'
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+    stream: false
+    template: |
+      Use the following pieces of context to answer the query at the end.
+      If you don't know the answer, just say that you don't know, don't try to make up an answer.
+
+      $context
+
+      Query: $query
+
+      Helpful Answer:
+    system_prompt: |
+      Act as William Shakespeare. Answer the following questions in the style of William Shakespeare.
+
+vectordb:
+  provider: chroma
+  config:
+    collection_name: 'my-collection-name'
+    dir: db
+    allow_reset: true
+
+embedder:
+  provider: openai
+  config:
+    model: 'text-embedding-ada-002'

configs/gpt4all.yaml

@@ -0,0 +1,13 @@
+llm:
+  provider: gpt4all
+  model: 'orca-mini-3b.ggmlv3.q4_0.bin'
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+    stream: false
+
+embedder:
+  provider: gpt4all
+  config:
+    model: 'all-MiniLM-L6-v2'

configs/huggingface.yaml

@@ -0,0 +1,8 @@
+llm:
+  provider: huggingface
+  model: 'google/flan-t5-xxl'
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 0.5
+    stream: false

configs/jina.yaml

@@ -0,0 +1,7 @@
+llm:
+  provider: jina
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+    stream: false

configs/llama2.yaml

@@ -0,0 +1,8 @@
+llm:
+  provider: llama2
+  model: 'a16z-infra/llama13b-v2-chat:df7690f1994d94e96ad9d568eac121aecf50684a0b0963b25a41cc40061269e5'
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 0.5
+    stream: false

configs/opensearch.yaml

@@ -0,0 +1,33 @@
+app:
+  config:
+    id: 'my-app'
+    log_level: 'WARN'
+    collect_metrics: true
+    collection_name: 'my-app'
+
+llm:
+  provider: openai
+  model: 'gpt-3.5-turbo'
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+    stream: false
+
+vectordb:
+  provider: opensearch
+  config:
+    opensearch_url: 'https://localhost:9200'
+    http_auth:
+      - admin
+      - admin
+    vector_dimension: 1536
+    collection_name: 'my-app'
+    use_ssl: false
+    verify_certs: false
+
+embedder:
+  provider: openai
+  config:
+    model: 'text-embedding-ada-002'
+    deployment_name: null

configs/opensource.yaml

@@ -0,0 +1,27 @@
+app:
+  config:
+    id: 'open-source-app'
+    collection_name: 'open-source-app'
+    collect_metrics: false
+
+llm:
+  provider: gpt4all
+  model: 'orca-mini-3b.ggmlv3.q4_0.bin'
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+    stream: false
+
+vectordb:
+  provider: chroma
+  config:
+    collection_name: 'open-source-app'
+    dir: db
+    allow_reset: true
+
+embedder:
+  provider: gpt4all
+  config:
+    model: 'all-MiniLM-L6-v2'
+    deployment_name: null

configs/pinecone.yaml

@@ -0,0 +1,6 @@
+vectordb:
+  provider: pinecone
+  config:
+    metric: cosine
+    vector_dimension: 1536
+    collection_name: my-pinecone-index

configs/vertexai.yaml

@@ -0,0 +1,6 @@
+llm:
+  provider: vertexai
+  model: 'chat-bison'
+  config:
+    temperature: 0.5
+    top_p: 0.5

configs/weaviate.yaml

@@ -0,0 +1,4 @@
+vectordb:
+  provider: weaviate
+  config:
+    collection_name: my_weaviate_index

docs/Makefile

@@ -0,0 +1,10 @@
+install:
+	npm i -g mintlify
+
+run_local:
+	mintlify dev
+
+troubleshoot:
+	mintlify install
+
+.PHONY: install run_local troubleshoot

docs/_snippets/get-help.mdx

@@ -0,0 +1,11 @@
+<CardGroup cols={3}>
+  <Card title="Slack" icon="slack" href="https://join.slack.com/t/embedchain/shared_invite/zt-22uwz3c46-Zg7cIh5rOBteT_xe1jwLDw" color="#4A154B">
+    Join our slack community
+  </Card>
+  <Card title="Discord" icon="discord" href="https://discord.gg/6PzXDgEjG5" color="#7289DA">
+    Join our discord community
+  </Card>
+  <Card title="Schedule a call" icon="calendar" href="https://cal.com/taranjeetio/ec">
+  Schedule a call with Embedchain founder
+  </Card>
+</CardGroup>

docs/_snippets/missing-data-source-tip.mdx

@@ -0,0 +1,18 @@
+<Tip>
+If you can't find the specific data source, please feel free to request through one of the following channels and help us prioritize.
+
+<CardGroup cols={2}>
+  <Card title="Slack" icon="slack" href="https://join.slack.com/t/embedchain/shared_invite/zt-22uwz3c46-Zg7cIh5rOBteT_xe1jwLDw" color="#4A154B">
+    Let us know on our slack community
+  </Card>
+  <Card title="Discord" icon="discord" href="https://discord.gg/6PzXDgEjG5" color="#7289DA">
+    Let us know on discord community
+  </Card>
+  <Card title="GitHub" icon="github" href="https://github.com/embedchain/embedchain/issues/new?assignees=&labels=&projects=&template=feature_request.yml" color="#181717">
+  Open an issue on our GitHub
+  </Card>
+  <Card title="Schedule a call" icon="calendar" href="https://cal.com/taranjeetio/ec">
+  Schedule a call with Embedchain founder
+  </Card>
+</CardGroup>
+</Tip>

docs/_snippets/missing-llm-tip.mdx

@@ -0,0 +1,18 @@
+<Tip>
+If you can't find the specific LLM you need, no need to fret. We're continuously expanding our support for additional LLMs, and you can help us prioritize by opening an issue on our GitHub or simply reaching out to us on our Slack or Discord community.
+
+<CardGroup cols={2}>
+  <Card title="Slack" icon="slack" href="https://join.slack.com/t/embedchain/shared_invite/zt-22uwz3c46-Zg7cIh5rOBteT_xe1jwLDw" color="#4A154B">
+    Let us know on our slack community
+  </Card>
+  <Card title="Discord" icon="discord" href="https://discord.gg/6PzXDgEjG5" color="#7289DA">
+    Let us know on discord community
+  </Card>
+  <Card title="GitHub" icon="github" href="https://github.com/embedchain/embedchain/issues/new?assignees=&labels=&projects=&template=feature_request.yml" color="#181717">
+  Open an issue on our GitHub
+  </Card>
+  <Card title="Schedule a call" icon="calendar" href="https://cal.com/taranjeetio/ec">
+  Schedule a call with Embedchain founder
+  </Card>
+</CardGroup>
+</Tip>

docs/_snippets/missing-vector-db-tip.mdx

@@ -0,0 +1,18 @@
+<Tip>
+If you can't find the specific vector database, please feel free to request through one of the following channels and help us prioritize.
+
+<CardGroup cols={2}>
+  <Card title="Slack" icon="slack" href="https://join.slack.com/t/embedchain/shared_invite/zt-22uwz3c46-Zg7cIh5rOBteT_xe1jwLDw" color="#4A154B">
+    Let us know on our slack community
+  </Card>
+  <Card title="Discord" icon="discord" href="https://discord.gg/6PzXDgEjG5" color="#7289DA">
+    Let us know on discord community
+  </Card>
+  <Card title="GitHub" icon="github" href="https://github.com/embedchain/embedchain/issues/new?assignees=&labels=&projects=&template=feature_request.yml" color="#181717">
+  Open an issue on our GitHub
+  </Card>
+  <Card title="Schedule a call" icon="calendar" href="https://cal.com/taranjeetio/ec">
+  Schedule a call with Embedchain founder
+  </Card>
+</CardGroup>
+</Tip>

docs/advanced/app_types.mdx

@@ -1,213 +0,0 @@
----
-title: '📱 App types'
----
-
-## App Types
-
-Embedchain supports a variety of LLMs, embedding functions/models and vector databases.
-
-Our app gives you full control over which components you want to use, you can mix and match them to your hearts content.
-
-<Tip>
-Out of the box, if you just use `app = App()`, Embedchain uses what we believe to be the best configuration available. This might include paid/proprietary components. Currently, this is
-
-* LLM: OpenAi (gpt-3.5-turbo)
-* Embedder: OpenAi (text-embedding-ada-002)
-* Database: ChromaDB
-</Tip>
-
-### LLM
-
-#### Choosing an LLM
-
-The following LLM providers are supported by Embedchain:
-- OPENAI
-- ANTHPROPIC
-- VERTEX_AI
-- GPT4ALL
-- AZURE_OPENAI
-- LLAMA2
-
-You can choose one by importing it from `embedchain.llm`. E.g.:
-
-```python
-from embedchain import App
-from embedchain.llm.llama2 import Llama2Llm
-
-app = App(llm=Llama2Llm())
-```
-
-#### Configuration
-
-The LLMs can be configured by passing an LlmConfig object.
-
-The config options can be found [here](/advanced/query_configuration#llmconfig)
-
-```python
-from embedchain import App
-from embedchain.llm.llama2 import Llama2Llm
-from embedchain.config import LlmConfig
-
-app = App(llm=Llama2Llm(), llm_config=LlmConfig(number_documents=3, temperature=0))
-```
-
-### Embedder
-
-#### Choosing an Embedder
-
-The following providers for embedding functions are supported by Embedchain:
-- OPENAI
-- HUGGING_FACE
-- VERTEX_AI
-- GPT4ALL
-- AZURE_OPENAI
-
-You can choose one by importing it from `embedchain.embedder`. E.g.:
-
-```python
-from embedchain import App
-from embedchain.embedder.vertexai import VertexAiEmbedder
-
-app = App(embedder=VertexAiEmbedder())
-```
-
-#### Configuration
-
-The LLMs can be configured by passing an EmbedderConfig object.
-
-```python
-from embedchain import App
-from embedchain.embedder.openai import OpenAiEmbedder
-from embedchain.config import EmbedderConfig
-
-app = App(embedder=OpenAiEmbedder(), embedder_config=EmbedderConfig(model="text-embedding-ada-002"))
-```
-
-<Tip>
-You can also pass an `LlmConfig` instance directly to the `query` or `chat` method.
-This creates a temporary config for that request alone, so you could, for example, use a different model (from the same provider) or get more context documents for a specific query.
-</Tip>
-
-### Vector Database
-
-#### Choosing a Vector Database
-
-The following vector databases are supported by Embedchain:
-- ChromaDB
-- Elasticsearch
-
-You can choose one by importing it from `embedchain.vectordb`. E.g.:
-
-```python
-from embedchain import App
-from embedchain.vectordb.elasticsearch import ElasticsearchDB
-
-app = App(db=ElasticsearchDB())
-```
-
-#### Configuration
-
-The vector databases can be configured by passing a specific config object.
-
-These vary greatly between the different vector databases.
-
-```python
-from embedchain import App
-from embedchain.vectordb.elasticsearch import ElasticsearchDB
-from embedchain.config import ElasticsearchDBConfig
-
-app = App(db=ElasticsearchDB(), db_config=ElasticsearchDBConfig())
-```
-
-### PersonApp
-
-```python
-from embedchain import PersonApp
-naval_chat_bot = PersonApp("name_of_person_or_character") #Like "Yoda"
-```
-
-- `PersonApp` uses OpenAI's model, so these are paid models. 💸 You will be charged for embedding model usage and LLM usage.
-- `PersonApp` uses OpenAI's embedding model to create embeddings for chunks and ChatGPT API as LLM to get answer given the relevant docs. Make sure that you have an OpenAI account and an API key. If you don't have an API key, you can create one by visiting [this link](https://platform.openai.com/account/api-keys).
-- Once you have the API key, set it in an environment variable called `OPENAI_API_KEY`
-
-```python
-import os
-os.environ["OPENAI_API_KEY"] = "sk-xxxx"
-```
-
-### Full Configuration Examples
-
-Embedchain previously offered fully configured classes, namely `App`, `OpenSourceApp`, `CustomApp` and `Llama2App`.
-We deprecated these apps. The reason for this decision was that it was hard to switch from to a different LLM, embedder or vector db, if you one day decided that that's what you want to do.
-The new app allows drop-in replacements, such as changing `App(llm=OpenAiLlm())` to `App(llm=Llama2Llm())`.
-
-To make the switch to our new, fully configurable app easier, we provide you with full examples for what the old classes would look like implemented as a new app.
-You can swap these in, and if you decide you want to try a different model one day, you don't have to rewrite your whole bot.
-
-#### App
-App without any configuration is still using the best options available, so you can keep using:
-
-```python
-from embedchain import App
-
-app = App()
-```
-
-#### OpenSourceApp
-
-Use this snippet to run an open source app.
-
-```python
-from embedchain import App
-from embedchain.llm.gpt4all import GPT4ALLLlm
-from embedchain.embedder.gpt4all import GPT4AllEmbedder
-from embedchain.vectordb.chroma import ChromaDB
-
-app = App(llm=GPT4ALLLlm(), embedder=GPT4AllEmbedder(), db=ChromaDB())
-```
-
-#### Llama2App
-```python
-from embedchain import App
-from embedchain.llm.llama2 import Llama2Llm
-
-app = App(llm=Llama2Llm())
-```
-
-#### CustomApp
-
-Every app is a custom app now.
-If you were previously using a `CustomApp`, you can now just change it to `App`.
-
-Here's one example, what you could do if we combined everything shown on this page.
-
-```python
-from embedchain import App
-from embedchain.config import ElasticsearchDBConfig, EmbedderConfig, LlmConfig
-from embedchain.embedder.openai import OpenAiEmbedder
-from embedchain.llm.llama2 import Llama2Llm
-from embedchain.vectordb.elasticsearch import ElasticsearchDB
-
-app = App(
-    llm=Llama2Llm(),
-    llm_config=LlmConfig(number_documents=3, temperature=0),
-    embedder=OpenAiEmbedder(),
-    embedder_config=EmbedderConfig(model="text-embedding-ada-002"),
-    db=ElasticsearchDB(),
-    db_config=ElasticsearchDBConfig(),
-)
-```
-
-### Compatibility with other apps
-
-- If there is any other app instance in your script or app, you can change the import as
-
-```python
-from embedchain import App as EmbedChainApp
-from embedchain import PersonApp as EmbedChainPersonApp
-
-# or
-
-from embedchain import App as ECApp
-from embedchain import PersonApp as ECPApp
-```

docs/advanced/configuration.mdx

@@ -4,101 +4,72 @@ title: '⚙️ Custom configurations'
 
 Embedchain is made to work out of the box. However, for advanced users we're also offering configuration options. All of these configuration options are optional and have sane defaults.
 
-## Concept
-The main `App` class is available in the following varieties: `CustomApp`, `OpenSourceApp` and `Llama2App` and `App`. The first is fully configurable, the others are opinionated in some aspects.
+You can configure different components of your app (`llm`, `embedding model`, or `vector database`) through a simple yaml configuration that Embedchain offers. Here is a generic full-stack example of the yaml config:
 
-The `App` class has three subclasses: `llm`, `db` and `embedder`. These are the core ingredients that make up an EmbedChain app.
-App plus each one of the subclasses have a `config` attribute.
-You can pass a `Config` instance as an argument during initialization to persistently configure a class.
-These configs can be imported from `embedchain.config`
+```yaml
+app:
+  config:
+    id: 'full-stack-app'
 
-There are `set` methods for some things that should not (only) be set at start-up, like `app.db.set_collection_name`.
+llm:
+  provider: openai
+  model: 'gpt-3.5-turbo'
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+    stream: false
+    template: |
+      Use the following pieces of context to answer the query at the end.
+      If you don't know the answer, just say that you don't know, don't try to make up an answer.
 
-## Examples
+      $context
 
-### General
+      Query: $query
 
-Here's the readme example with configuration options.
+      Helpful Answer:
+    system_prompt: |
+      Act as William Shakespeare. Answer the following questions in the style of William Shakespeare.
 
-```python
-from embedchain import App
-from embedchain.config import AppConfig, AddConfig, LlmConfig, ChunkerConfig
+vectordb:
+  provider: chroma
+  config:
+    collection_name: 'full-stack-app'
+    dir: db
+    allow_reset: true
 
-# Example: set the log level for debugging
-config = AppConfig(log_level="DEBUG")
-naval_chat_bot = App(config)
-
-# Example: specify a custom collection name
-naval_chat_bot.db.set_collection_name("naval_chat_bot")
-
-# Example: define your own chunker config for `youtube_video`
-chunker_config = ChunkerConfig(chunk_size=1000, chunk_overlap=100, length_function=len)
-# Example: Add your chunker config to an AddConfig to actually use it
-add_config = AddConfig(chunker=chunker_config)
-naval_chat_bot.add("https://www.youtube.com/watch?v=3qHkcs3kG44", config=add_config)
-
-# Example: Reset to default
-add_config = AddConfig()
-naval_chat_bot.add("https://navalmanack.s3.amazonaws.com/Eric-Jorgenson_The-Almanack-of-Naval-Ravikant_Final.pdf", config=add_config)
-naval_chat_bot.add("https://nav.al/feedback", config=add_config)
-naval_chat_bot.add("https://nav.al/agi", config=add_config)
-naval_chat_bot.add(("Who is Naval Ravikant?", "Naval Ravikant is an Indian-American entrepreneur and investor."), config=add_config)
-
-# Change the number of documents.
-query_config = LlmConfig(number_documents=5)
-print(naval_chat_bot.query("What unique capacity does Naval argue humans possess when it comes to understanding explanations or concepts?", config=query_config))
+embedder:
+  provider: openai
+  config:
+    model: 'text-embedding-ada-002'
 ```
 
-### Custom prompt template
+Alright, let's dive into what each key means in the yaml config above:
 
-Here's the example of using custom prompt template with `.query`
+1. `app` Section:
+    - `config`:
+        - `id` (String): The ID or name of your full-stack application.
+2. `llm` Section:
+    - `provider` (String): The provider for the language model, which is set to 'openai'. You can find the full list of llm providers in [our docs](/components/llms).
+    - `model` (String): The specific model being used, 'gpt-3.5-turbo'.
+    - `config`:
+        - `temperature` (Float): Controls the randomness of the model's output. A higher value (closer to 1) makes the output more random.
+        - `max_tokens` (Integer): Controls how many tokens are used in the response.
+        - `top_p` (Float): Controls the diversity of word selection. A higher value (closer to 1) makes word selection more diverse.
+        - `stream` (Boolean): Controls if the response is streamed back to the user (set to false).
+        - `template` (String): A custom template for the prompt that the model uses to generate responses.
+        - `system_prompt` (String): A system prompt for the model to follow when generating responses, in this case, it's set to the style of William Shakespeare.
+3. `vectordb` Section:
+    - `provider` (String): The provider for the vector database, set to 'chroma'. You can find the full list of vector database providers in [our docs](/components/vector-databases).
+    - `config`:
+        - `collection_name` (String): The initial collection name for the database, set to 'full-stack-app'.
+        - `dir` (String): The directory for the database, set to 'db'.
+        - `allow_reset` (Boolean): Indicates whether resetting the database is allowed, set to true.
+4. `embedder` Section:
+    - `provider` (String): The provider for the embedder, set to 'openai'. You can find the full list of embedding model providers in [our docs](/components/embedding-models).
+    - `config`:
+        - `model` (String): The specific model used for text embedding, 'text-embedding-ada-002'.
 
-```python
-from string import Template
+If you have questions about the configuration above, please feel free to reach out to us using one of the following methods:
 
-import wikipedia
-
-from embedchain import App
-from embedchain.config import LlmConfig
-
-einstein_chat_bot = App()
-
-# Embed Wikipedia page
-page = wikipedia.page("Albert Einstein")
-einstein_chat_bot.add(page.content)
-
-# Example: use your own custom template with `$context` and `$query`
-einstein_chat_template = Template(
-    """
-        You are Albert Einstein, a German-born theoretical physicist,
-        widely ranked among the greatest and most influential scientists of all time.
-
-        Use the following information about Albert Einstein to respond to
-        the human's query acting as Albert Einstein.
-        Context: $context
-
-        Keep the response brief. If you don't know the answer, just say that you don't know, don't try to make up an answer.
-
-        Human: $query
-        Albert Einstein:"""
-)
-# Example: Use the template, also add a system prompt.
-llm_config = LlmConfig(template=einstein_chat_template, system_prompt="You are Albert Einstein.")
-queries = [
-    "Where did you complete your studies?",
-    "Why did you win nobel prize?",
-    "Why did you divorce your first wife?",
-]
-for query in queries:
-    response = einstein_chat_bot.query(query, config=llm_config)
-    print("Query: ", query)
-    print("Response: ", response)
-
-# Output
-# Query:  Where did you complete your studies?
-# Response:  I completed my secondary education at the Argovian cantonal school in Aarau, Switzerland.
-# Query:  Why did you win nobel prize?
-# Response:  I won the Nobel Prize in Physics in 1921 for my services to Theoretical Physics, particularly for my discovery of the law of the photoelectric effect.
-# Query:  Why did you divorce your first wife?
-# Response:  We divorced due to living apart for five years.
-```
+<Snippet file="get-help.mdx" />

docs/advanced/interface_types.mdx

@@ -1,75 +0,0 @@
----
-title: '🤝 Interface types'
----
-
-## Interface Types
-
-The embedchain app exposes the following methods.
-
-### Query Interface
-
-- This interface is like a question answering bot. It takes a question and gets the answer. It does not maintain context about the previous chats.❓
-
-- To use this, call `.query()` function to get the answer for any query.
-
-```python
-print(naval_chat_bot.query("What unique capacity does Naval argue humans possess when it comes to understanding explanations or concepts?"))
-# answer: Naval argues that humans possess the unique capacity to understand explanations or concepts to the maximum extent possible in this physical reality.
-```
-
-### Chat Interface
-
-- This interface is a chat interface that remembers previous conversations. Right now it remembers 5 conversations by default. 💬
-
-- To use this, call `.chat` function to get the answer for any query.
-
-```python
-print(naval_chat_bot.chat("How to be happy in life?"))
-# answer: The most important trick to being happy is to realize happiness is a skill you develop and a choice you make. You choose to be happy, and then you work at it. It's just like building muscles or succeeding at your job. It's about recognizing the abundance and gifts around you at all times.
-
-print(naval_chat_bot.chat("who is naval ravikant?"))
-# answer: Naval Ravikant is an Indian-American entrepreneur and investor.
-
-print(naval_chat_bot.chat("what did the author say about happiness?"))
-# answer: The author, Naval Ravikant, believes that happiness is a choice you make and a skill you develop. He compares the mind to the body, stating that just as the body can be molded and changed, so can the mind. He emphasizes the importance of being present in the moment and not getting caught up in regrets of the past or worries about the future. By being present and grateful for where you are, you can experience true happiness.
-```
-
-#### Dry Run
-
-Dry Run is an option in the `add`, `query` and `chat` methods that allows the user to display the data chunks and their constructed prompt which is not sent to the LLM, to save money. It's used for [testing](/advanced/testing#dry-run).
-
-
-### Stream Response
-
-- You can add config to your query method to stream responses like ChatGPT does. You would require a downstream handler to render the chunk in your desirable format. Supports both OpenAI model and OpenSourceApp. 📊
-
-- To use this, instantiate a `LlmConfig` or `ChatConfig` object with `stream=True`. Then pass it to the `.chat()` or `.query()` method. The following example iterates through the chunks and prints them as they appear.
-
-```python
-app = App()
-query_config = LlmConfig(stream = True)
-resp = app.query("What unique capacity does Naval argue humans possess when it comes to understanding explanations or concepts?", query_config)
-
-for chunk in resp:
-    print(chunk, end="", flush=True)
-# answer: Naval argues that humans possess the unique capacity to understand explanations or concepts to the maximum extent possible in this physical reality.
-```
-
-### Other Methods
-
-#### Reset
-
-Resets the database and deletes all embeddings. Irreversible. Requires reinitialization afterwards.
-
-```python
-app.reset()
-```
-
-#### Count
-
-Counts the number of embeddings (chunks) in the database.
-
-```python
-print(app.db.count())
-# returns: 481
-```

docs/advanced/query_configuration.mdx

@@ -1,79 +0,0 @@
----
-title: '🔍 Query configurations'
----
-
-## AppConfig
-
-| option    | description           | type                            | default                |
-|-----------|-----------------------|---------------------------------|------------------------|
-| log_level | log level             | string                          | WARNING                |
-| embedding_fn| embedding function    | chromadb.utils.embedding_functions | \{text-embedding-ada-002\} |
-| db        | vector database (experimental) | BaseVectorDB               | ChromaDB               |
-| collection_name | initial collection name for the database | string             | embedchain_store |
-| collect_metrics | collect anonymous telemetry data to improve embedchain | boolean | true |
-
-
-## AddConfig
-
-|option|description|type|default|
-|---|---|---|---|
-|chunker|chunker config|ChunkerConfig|Default values for chunker depends on the `data_type`. Please refer [ChunkerConfig](#chunker-config)|
-|loader|loader config|LoaderConfig|None|
-
-Yes, you are passing `ChunkerConfig` to `AddConfig`, like so:
-
-```python
-chunker_config = ChunkerConfig(chunk_size=100)
-add_config = AddConfig(chunker=chunker_config)
-app.add("lorem ipsum", config=add_config)
-```
-
-### ChunkerConfig
-
-|option|description|type|default|
-|---|---|---|---|
-|chunk_size|Maximum size of chunks to return|int|Default value for various `data_type` mentioned below|
-|chunk_overlap|Overlap in characters between chunks|int|Default value for various `data_type` mentioned below|
-|length_function|Function that measures the length of given chunks|typing.Callable|Default value for various `data_type` mentioned below|
-
-Default values of chunker config parameters for different `data_type`:
-
-|data_type|chunk_size|chunk_overlap|length_function|
-|---|---|---|---|
-|docx|1000|0|len|
-|text|300|0|len|
-|qna_pair|300|0|len|
-|web_page|500|0|len|
-|pdf_file|1000|0|len|
-|youtube_video|2000|0|len|
-|docs_site|500|50|len|
-|notion|300|0|len|
-
-### LoaderConfig
-
-_coming soon_
-
-## LlmConfig
-
-|option|description|type|default|
-|---|---|---|---|
-|number_documents|Absolute number of documents to pull from the database as context.|int|1
-|template|custom template for prompt. If history is used with query, $history has to be included as well.|Template|Template("Use the following pieces of context to answer the query at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer. \$context Query: \$query Helpful Answer:")|
-|model|name of the model used.|string|depends on app type|
-|temperature|Controls the randomness of the model's output. Higher values (closer to 1) make output more random, lower values make it more deterministic.|float|0|
-|max_tokens|Controls how many tokens are used. Exact implementation (whether it counts prompt and/or response) depends on the model.|int|1000|
-|top_p|Controls the diversity of words. Higher values (closer to 1) make word selection more diverse, lower values make words less diverse.|float|1|
-|history|include conversation history from your client or database.|any (recommendation: list[str])|None|
-|stream|control if response is streamed back to the user.|bool|False|
-|deployment_name|t.b.a.|str|None|
-|system_prompt|System prompt string. Unused if none.|str|None|
-|where|filter for context search.|dict|None|
-
-
-## ChatConfig
-
-All options for query and...
-
-_coming soon_
-
-`history` is not supported, as that is handled is handled automatically, the config option is not supported.

docs/advanced/testing.mdx

@@ -1,40 +0,0 @@
----
-title: '🧪 Testing'
----
-
-## Methods for testing
-
-### Dry Run
-
-Before you consume valueable tokens, you should make sure that data chunks are properly created and the embedding you have done works and that it's receiving the correct document from the database.
-
-- For `query` or `chat` method, you can add this to your script:
-
-```python
-print(naval_chat_bot.query('Can you tell me who Naval Ravikant is?', dry_run=True))
-
-'''
-Use the following pieces of context to answer the query at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.
-        Q: Who is Naval Ravikant?
-A: Naval Ravikant is an Indian-American entrepreneur and investor.
-        Query: Can you tell me who Naval Ravikant is?
-        Helpful Answer:
-'''
-```
-
-_The embedding is confirmed to work as expected. It returns the right document, even if the question is asked slightly different. No prompt tokens have been consumed._
-
-The dry run will still consume tokens to embed your query, but it is only **~1/15 of the prompt.**
-
-
-- For `add` method, you can add this to your script:
-
-```python
-print(naval_chat_bot.add('https://navalmanack.s3.amazonaws.com/Eric-Jorgenson_The-Almanack-of-Naval-Ravikant_Final.pdf', dry_run=True))
-
-'''
-{'chunks': ['THE ALMANACK OF NAVAL RAVIKANT', 'GETTING RICH IS NOT JUST ABOUT LUCK;', 'HAPPINESS IS NOT JUST A TRAIT WE ARE'], 'metadata': [{'source': 'C:\\Users\\Dev\\AppData\\Local\\Temp\\tmp3g5mjoiz\\tmp.pdf', 'page': 0, 'url': 'https://navalmanack.s3.amazonaws.com/Eric-Jorgenson_The-Almanack-of-Naval-Ravikant_Final.pdf', 'data_type': 'pdf_file'}, {'source': 'C:\\Users\\Dev\\AppData\\Local\\Temp\\tmp3g5mjoiz\\tmp.pdf', 'page': 2, 'url': 'https://navalmanack.s3.amazonaws.com/Eric-Jorgenson_The-Almanack-of-Naval-Ravikant_Final.pdf', 'data_type': 'pdf_file'}, {'source': 'C:\\Users\\Dev\\AppData\\Local\\Temp\\tmp3g5mjoiz\\tmp.pdf', 'page': 2, 'url': 'https://navalmanack.s3.amazonaws.com/Eric-Jorgenson_The-Almanack-of-Naval-Ravikant_Final.pdf', 'data_type': 'pdf_file'}], 'count': 7358, 'type': <DataType.PDF_FILE: 'pdf_file'>}
-
-# less items to show for readability
-'''
-```

docs/advanced/vector_database.mdx

@@ -1,118 +0,0 @@
----
-title: '💾 Vector Database'
----
-
-We support `Chroma`, `Elasticsearch` and `OpenSearch` as vector databases.
-`Chroma` is used as a default database.
-
-## Elasticsearch
-
-### Minimal Example
-
-In order to use `Elasticsearch` as vector database we need to use App type `CustomApp`.
-
-1. Set the environment variables in a `.env` file.
-```
-OPENAI_API_KEY=sk-SECRETKEY
-ELASTICSEARCH_API_KEY=SECRETKEY==
-ELASTICSEARCH_URL=https://secret-domain.europe-west3.gcp.cloud.es.io:443
-```
-Please note that the key needs certain privileges. For testing you can just toggle off `restrict privileges` under `/app/management/security/api_keys/` in your web interface.
-
-2. Load the app
-```python
-from embedchain import CustomApp
-from embedchain.embedder.openai import OpenAIEmbedder
-from embedchain.llm.openai import OpenAILlm
-from embedchain.vectordb.elasticsearch import ElasticsearchDB
-
-es_app = CustomApp(
-    llm=OpenAILlm(),
-    embedder=OpenAIEmbedder(),
-    db=ElasticsearchDB(),
-)
-```
-
-### More custom settings
-
-You can get a URL for elasticsearch in the cloud, or run it locally. 
-The following example shows you how to configure embedchain to work with a locally running elasticsearch.
-
-Instead of using an API key, we use http login credentials. The localhost url can be defined in .env or in the config.
-
-```python
-import os
-
-from embedchain import CustomApp
-from embedchain.config import CustomAppConfig, ElasticsearchDBConfig
-from embedchain.embedder.openai import OpenAIEmbedder
-from embedchain.llm.openai import OpenAILlm
-from embedchain.vectordb.elasticsearch import ElasticsearchDB
-
-es_config = ElasticsearchDBConfig(
-    # elasticsearch url or list of nodes url with different hosts and ports.
-    es_url='https://localhost:9200',
-    # pass named parameters supported by Python Elasticsearch client
-    http_auth=("elastic", "secret"),
-    ca_certs="~/binaries/elasticsearch-8.7.0/config/certs/http_ca.crt" # your cert path
-    # verify_certs=False # Alternative, if you aren't using certs
-) # pass named parameters supported by elasticsearch-py
-
-es_app = CustomApp(
-    config=CustomAppConfig(log_level="INFO"),
-    llm=OpenAILlm(),
-    embedder=OpenAIEmbedder(),
-    db=ElasticsearchDB(config=es_config),
-)
-```
-3. This should log your connection details to the console.
-4. Alternatively to a URL, you `ElasticsearchDBConfig` accepts `es_url` as a list of nodes url with different hosts and ports.
-5. Additionally we can pass named parameters supported by Python Elasticsearch client.
-
-
-## OpenSearch 🔍
-
-To use OpenSearch as a vector database with a CustomApp, follow these simple steps:
-
-1. Set the `OPENAI_API_KEY` environment variable:
-
-```
-OPENAI_API_KEY=sk-xxxx
-```
-
-2. Define the OpenSearch configuration in your Python code:
-
-```python
-from embedchain import CustomApp
-from embedchain.config import OpenSearchDBConfig
-from embedchain.embedder.openai import OpenAIEmbedder
-from embedchain.llm.openai import OpenAILlm
-from embedchain.vectordb.opensearch import OpenSearchDB
-
-opensearch_url = "https://localhost:9200"
-http_auth = ("username", "password")
-
-db_config = OpenSearchDBConfig(
-    opensearch_url=opensearch_url,
-    http_auth=http_auth,
-    collection_name="embedchain-app",
-    use_ssl=True,
-    timeout=30,
-)
-db = OpenSearchDB(config=db_config)
-```
-
-2. Instantiate the app and add data:
-
-```python
-app = CustomApp(llm=OpenAILlm(), embedder=OpenAIEmbedder(), db=db)
-app.add("https://en.wikipedia.org/wiki/Elon_Musk")
-app.add("https://www.forbes.com/profile/elon-musk")
-app.add("https://www.britannica.com/biography/Elon-Musk")
-```
-
-3. You're all set! Start querying using the following command:
-
-```python
-app.query("What is the net worth of Elon Musk?")
-```

docs/community/connect-with-us.mdx

@@ -4,15 +4,25 @@ title: 🤝 Connect with Us
 
 We believe in building a vibrant and supportive community around embedchain. There are various channels through which you can connect with us, stay updated, and contribute to the ongoing discussions:
 
-
-* Slack: Our Slack workspace provides a platform for more structured discussions and channels dedicated to different topics. Feel free to jump in and start contributing. [Join Slack](https://join.slack.com/t/embedchain/shared_invite/zt-22uwz3c46-Zg7cIh5rOBteT_xe1jwLDw).
-
-* Discord: Join our Discord server to engage in real-time conversations with the community members and the project maintainers. It’s a great place to seek help and discuss anything related to the project. [Join Discord](https://discord.gg/CUU9FPhRNt).
-
-* Twitter: Follow us on Twitter for the latest news, announcements, and highlights from our community. It’s also a quick way to reach out to us. [Follow @embedchain](https://twitter.com/embedchain).
-
-* LinkedIn: Connect with us on LinkedIn to stay updated on official announcements, job openings, and professional networking opportunities within our community. [Follow Our Page](https://www.linkedin.com/company/embedchain/).
-
-* Newsletter: Subscribe to our newsletter for a curated list of project updates, community contributions, and upcoming events. It’s a compact way to stay in the loop with what’s happening in our community. [Subscribe Now](https://embedchain.substack.com/).
+<CardGroup cols={3}>
+  <Card title="Twitter" icon="twitter" href="https://twitter.com/embedchain">
+    Follow us on Twitter
+  </Card>
+  <Card title="Slack" icon="slack" href="https://join.slack.com/t/embedchain/shared_invite/zt-22uwz3c46-Zg7cIh5rOBteT_xe1jwLDw" color="#4A154B">
+    Join our slack community
+  </Card>
+  <Card title="Discord" icon="discord" href="https://discord.gg/6PzXDgEjG5" color="#7289DA">
+    Join our discord community
+  </Card>
+  <Card title="LinkedIn" icon="linkedin" href="https://www.linkedin.com/company/embedchain/">
+  Connect with us on LinkedIn
+  </Card>
+  <Card title="Schedule a call" icon="calendar" href="https://cal.com/taranjeetio/ec">
+  Schedule a call with Embedchain founder
+  </Card>
+  <Card title="Newsletter" icon="message" href="https://embedchain.substack.com/">
+  Subscribe to our newsletter
+  </Card>
+</CardGroup>
 
 We look forward to connecting with you and seeing how we can create amazing things together!

docs/components/embedding-models.mdx

@@ -0,0 +1,175 @@
+---
+title: 🧩 Embedding models
+---
+
+## Overview
+
+Embedchain supports several embedding models from the following providers:
+
+<CardGroup cols={4}>
+  <Card title="OpenAI" href="#openai"></Card>
+  <Card title="Azure OpenAI" href="#azure-openai"></Card>
+  <Card title="GPT4All" href="#gpt4all"></Card>
+  <Card title="Hugging Face" href="#hugging-face"></Card>
+  <Card title="Vertex AI" href="#vertex-ai"></Card>
+</CardGroup>
+
+## OpenAI
+
+To use OpenAI embedding function, you have to set the `OPENAI_API_KEY` environment variable. You can obtain the OpenAI API key from the [OpenAI Platform](https://platform.openai.com/account/api-keys).
+
+Once you have obtained the key, you can use it like this:
+
+<CodeGroup>
+
+```python main.py
+import os
+from embedchain import App
+
+os.environ['OPENAI_API_KEY'] = 'xxx'
+
+# load embedding model configuration from config.yaml file
+app = App.from_config(yaml_path="config.yaml")
+
+app.add("https://en.wikipedia.org/wiki/OpenAI")
+app.query("What is OpenAI?")
+```
+
+```yaml config.yaml
+embedder:
+  provider: openai
+  config:
+    model: 'text-embedding-ada-002'
+```
+
+</CodeGroup>
+
+## Azure OpenAI
+
+To use Azure OpenAI embedding model, you have to set some of the azure openai related environment variables as given in the code block below:
+
+<CodeGroup>
+
+```python main.py
+import os
+from embedchain import App
+
+os.environ["OPENAI_API_TYPE"] = "azure"
+os.environ["OPENAI_API_BASE"] = "https://xxx.openai.azure.com/"
+os.environ["OPENAI_API_KEY"] = "xxx"
+os.environ["OPENAI_API_VERSION"] = "xxx"
+
+app = App.from_config(yaml_path="config.yaml")
+```
+
+```yaml config.yaml
+llm:
+  provider: azure_openai
+  model: gpt-35-turbo
+  config:
+    deployment_name: your_llm_deployment_name
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+    stream: false
+
+embedder:
+  provider: azure_openai
+  config:
+    model: text-embedding-ada-002
+    deployment_name: you_embedding_model_deployment_name
+```
+</CodeGroup>
+
+You can find the list of models and deployment name on the [Azure OpenAI Platform](https://oai.azure.com/portal).
+
+## GPT4ALL
+
+GPT4All supports generating high quality embeddings of arbitrary length documents of text using a CPU optimized contrastively trained Sentence Transformer.
+
+<CodeGroup>
+
+```python main.py
+from embedchain import App
+
+# load embedding model configuration from config.yaml file
+app = App.from_config(yaml_path="config.yaml")
+```
+
+```yaml config.yaml
+llm:
+  provider: gpt4all
+  model: 'orca-mini-3b.ggmlv3.q4_0.bin'
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+    stream: false
+
+embedder:
+  provider: gpt4all
+  config:
+    model: 'all-MiniLM-L6-v2'
+```
+
+</CodeGroup>
+
+## Hugging Face
+
+Hugging Face supports generating embeddings of arbitrary length documents of text using Sentence Transformer library. Example of how to generate embeddings using hugging face is given below:
+
+<CodeGroup>
+
+```python main.py
+from embedchain import App
+
+# load embedding model configuration from config.yaml file
+app = App.from_config(yaml_path="config.yaml")
+```
+
+```yaml config.yaml
+llm:
+  provider: huggingface
+  model: 'google/flan-t5-xxl'
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 0.5
+    stream: false
+
+embedder:
+  provider: huggingface
+  config:
+    model: 'sentence-transformers/all-mpnet-base-v2'
+```
+
+</CodeGroup>
+
+## Vertex AI
+
+Embedchain supports Google's VertexAI embeddings model through a simple interface. You just have to pass the `model_name` in the config yaml and it would work out of the box.
+
+<CodeGroup>
+
+```python main.py
+from embedchain import App
+
+# load embedding model configuration from config.yaml file
+app = App.from_config(yaml_path="config.yaml")
+```
+
+```yaml config.yaml
+llm:
+  provider: vertexai
+  model: 'chat-bison'
+  config:
+    temperature: 0.5
+    top_p: 0.5
+
+embedder:
+  provider: vertexai
+  config:
+    model: 'textembedding-gecko'
+```
+
+</CodeGroup>

docs/components/llms.mdx

@@ -0,0 +1,327 @@
+---
+title: 🤖 Large language models (LLMs)
+---
+
+## Overview
+
+Embedchain comes with built-in support for various popular large language models. We handle the complexity of integrating these models for you, allowing you to easily customize your language model interactions through a user-friendly interface.
+
+<CardGroup cols={4}>
+  <Card title="OpenAI" href="#openai"></Card>
+  <Card title="Azure OpenAI" href="#azure-openai"></Card>
+  <Card title="Anthropic" href="#anthropic"></Card>
+  <Card title="Cohere" href="#cohere"></Card>
+  <Card title="GPT4All" href="#gpt4all"></Card>
+  <Card title="JinaChat" href="#jinachat"></Card>
+  <Card title="Hugging Face" href="#hugging-face"></Card>
+  <Card title="Llama2" href="#llama2"></Card>
+  <Card title="Vertex AI" href="#vertex-ai"></Card>
+</CardGroup>
+
+## OpenAI
+
+To use OpenAI LLM models, you have to set the `OPENAI_API_KEY` environment variable. You can obtain the OpenAI API key from the [OpenAI Platform](https://platform.openai.com/account/api-keys).
+
+Once you have obtained the key, you can use it like this:
+
+```python
+import os
+from embedchain import App
+
+os.environ['OPENAI_API_KEY'] = 'xxx'
+
+app = App()
+app.add("https://en.wikipedia.org/wiki/OpenAI")
+app.query("What is OpenAI?")
+```
+
+If you are looking to configure the different parameters of the LLM, you can do so by loading the app using a [yaml config](https://github.com/embedchain/embedchain/blob/main/configs/chroma.yaml) file.
+
+<CodeGroup>
+
+```python main.py
+import os
+from embedchain import App
+
+os.environ['OPENAI_API_KEY'] = 'xxx'
+
+# load llm configuration from config.yaml file
+app = App.from_config(yaml_path="config.yaml")
+```
+
+```yaml config.yaml
+llm:
+  provider: openai
+  model: 'gpt-3.5-turbo'
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+    stream: false
+```
+
+</CodeGroup>
+
+
+## Azure OpenAI
+
+To use Azure OpenAI model, you have to set some of the azure openai related environment variables as given in the code block below:
+
+<CodeGroup>
+
+```python main.py
+import os
+from embedchain import App
+
+os.environ["OPENAI_API_TYPE"] = "azure"
+os.environ["OPENAI_API_BASE"] = "https://xxx.openai.azure.com/"
+os.environ["OPENAI_API_KEY"] = "xxx"
+os.environ["OPENAI_API_VERSION"] = "xxx"
+
+app = App.from_config(yaml_path="config.yaml")
+```
+
+```yaml config.yaml
+llm:
+  provider: azure_openai
+  model: gpt-35-turbo
+  config:
+    deployment_name: your_llm_deployment_name
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+    stream: false
+
+embedder:
+  provider: azure_openai
+  config:
+    model: text-embedding-ada-002
+    deployment_name: you_embedding_model_deployment_name
+```
+</CodeGroup>
+
+You can find the list of models and deployment name on the [Azure OpenAI Platform](https://oai.azure.com/portal).
+
+## Anthropic
+
+To use anthropic's model, please set the `ANTHROPIC_API_KEY` which you find on their [Account Settings Page](https://console.anthropic.com/account/keys).
+
+<CodeGroup>
+
+```python main.py
+import os
+from embedchain import App
+
+os.environ["ANTHROPIC_API_KEY"] = "xxx"
+
+# load llm configuration from config.yaml file
+app = App.from_config(yaml_path="config.yaml")
+```
+
+```yaml config.yaml
+llm:
+  provider: anthropic
+  model: 'claude-instant-1'
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+    stream: false
+```
+
+</CodeGroup>
+
+## Cohere
+
+Install related dependencies using the following command:
+
+```bash
+pip install --upgrade 'embedchain[cohere]'
+```
+
+Set the `COHERE_API_KEY` as environment variable which you can find on their [Account settings page](https://dashboard.cohere.com/api-keys).
+
+Once you have the API key, you are all set to use it with Embedchain.
+
+<CodeGroup>
+
+```python main.py
+import os
+from embedchain import App
+
+os.environ["COHERE_API_KEY"] = "xxx"
+
+# load llm configuration from config.yaml file
+app = App.from_config(yaml_path="config.yaml")
+```
+
+```yaml config.yaml
+llm:
+  provider: cohere
+  model: large
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+```
+
+</CodeGroup>
+
+## GPT4ALL
+
+Install related dependencies using the following command:
+
+```bash
+pip install --upgrade 'embedchain[opensource]'
+```
+
+GPT4all is a free-to-use, locally running, privacy-aware chatbot. No GPU or internet required. You can use this with Embedchain using the following code:
+
+<CodeGroup>
+
+```python main.py
+from embedchain import App
+
+# load llm configuration from config.yaml file
+app = App.from_config(yaml_path="config.yaml")
+```
+
+```yaml config.yaml
+llm:
+  provider: gpt4all
+  model: 'orca-mini-3b.ggmlv3.q4_0.bin'
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+    stream: false
+
+embedder:
+  provider: gpt4all
+  config:
+    model: 'all-MiniLM-L6-v2'
+```
+</CodeGroup>
+
+
+## JinaChat
+
+First, set `JINACHAT_API_KEY` in environment variable which you can obtain from [their platform](https://chat.jina.ai/api).
+
+Once you have the key, load the app using the config yaml file:
+
+<CodeGroup>
+
+```python main.py
+import os
+from embedchain import App
+
+os.environ["JINACHAT_API_KEY"] = "xxx"
+# load llm configuration from config.yaml file
+app = App.from_config(yaml_path="config.yaml")
+```
+
+```yaml config.yaml
+llm:
+  provider: jina
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+    stream: false
+```
+</CodeGroup>
+
+
+## Hugging Face
+
+
+Install related dependencies using the following command:
+
+```bash
+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:
+
+<CodeGroup>
+
+```python main.py
+import os
+from embedchain import App
+
+os.environ["HUGGINGFACE_ACCESS_TOKEN"] = "xxx"
+
+# load llm configuration from config.yaml file
+app = App.from_config(yaml_path="config.yaml")
+```
+
+```yaml config.yaml
+llm:
+  provider: huggingface
+  model: 'google/flan-t5-xxl'
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 0.5
+    stream: false
+```
+</CodeGroup>
+
+## Llama2
+
+Llama2 is integrated through [Replicate](https://replicate.com/).  Set `REPLICATE_API_TOKEN` in environment variable which you can obtain from [their platform](https://replicate.com/account/api-tokens).
+
+Once you have the token, load the app using the config yaml file:
+
+<CodeGroup>
+
+```python main.py
+import os
+from embedchain import App
+
+os.environ["REPLICATE_API_TOKEN"] = "xxx"
+
+# load llm configuration from config.yaml file
+app = App.from_config(yaml_path="config.yaml")
+```
+
+```yaml config.yaml
+llm:
+  provider: llama2
+  model: 'a16z-infra/llama13b-v2-chat:df7690f1994d94e96ad9d568eac121aecf50684a0b0963b25a41cc40061269e5'
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 0.5
+    stream: false
+```
+</CodeGroup>
+
+## Vertex AI
+
+Setup Google Cloud Platform application credentials by following the instruction on [GCP](https://cloud.google.com/docs/authentication/external/set-up-adc). Once setup is done, use the following code to create an app using VertexAI as provider:
+
+<CodeGroup>
+
+```python main.py
+from embedchain import App
+
+# load llm configuration from config.yaml file
+app = App.from_config(yaml_path="config.yaml")
+```
+
+```yaml config.yaml
+llm:
+  provider: vertexai
+  model: 'chat-bison'
+  config:
+    temperature: 0.5
+    top_p: 0.5
+```
+</CodeGroup>
+
+<br/ >
+<Snippet file="missing-llm-tip.mdx" />

docs/components/vector-databases.mdx

@@ -0,0 +1,207 @@
+---
+title: 🗄️ Vector databases
+---
+
+## Overview
+
+Utilizing a vector database alongside Embedchain is a seamless process. All you need to do is configure it within the YAML configuration file. We've provided examples for each supported database below:
+
+<CardGroup cols={4}>
+  <Card title="ChromaDB" href="#chromadb"></Card>
+  <Card title="Elasticsearch" href="#elasticsearch"></Card>
+  <Card title="OpenSearch" href="#opensearch"></Card>
+  <Card title="Zilliz" href="#zilliz"></Card>
+  <Card title="LanceDB" href="#lancedb"></Card>
+  <Card title="Pinecone" href="#pinecone"></Card>
+  <Card title="Qdrant" href="#qdrant"></Card>
+  <Card title="Weaviate" href="#weaviate"></Card>
+</CardGroup>
+
+## ChromaDB
+
+<CodeGroup>
+
+```python main.py
+from embedchain import App
+
+# load chroma configuration from yaml file
+app = App.from_config(yaml_path="config1.yaml")
+```
+
+```yaml config1.yaml
+vectordb:
+  provider: chroma
+  config:
+    collection_name: 'my-collection'
+    dir: db
+    allow_reset: true
+```
+
+```yaml config2.yaml
+vectordb:
+  provider: chroma
+  config:
+    collection_name: 'my-collection'
+    host: localhost
+    port: 5200
+    allow_reset: true
+```
+
+</CodeGroup>
+
+
+## Elasticsearch
+
+Install related dependencies using the following command:
+
+```bash
+pip install --upgrade 'embedchain[elasticsearch]'
+```
+
+<CodeGroup>
+
+```python main.py
+from embedchain import App
+
+# load elasticsearch configuration from yaml file
+app = App.from_config(yaml_path="config.yaml")
+```
+
+```yaml config.yaml
+vectordb:
+  provider: elasticsearch
+  config:
+    collection_name: 'es-index'
+    es_url: http://localhost:9200
+    allow_reset: true
+    api_key: xxx
+```
+</CodeGroup>
+
+## OpenSearch
+
+Install related dependencies using the following command:
+
+```bash
+pip install --upgrade 'embedchain[opensearch]'
+```
+
+<CodeGroup>
+
+```python main.py
+from embedchain import App
+
+# load opensearch configuration from yaml file
+app = App.from_config(yaml_path="config.yaml")
+```
+
+```yaml config.yaml
+vectordb:
+  provider: opensearch
+  config:
+    opensearch_url: 'https://localhost:9200'
+    http_auth:
+      - admin
+      - admin
+    vector_dimension: 1536
+    collection_name: 'my-app'
+    use_ssl: false
+    verify_certs: false
+```
+
+</CodeGroup>
+
+## Zilliz
+
+Install related dependencies using the following command:
+
+```bash
+pip install --upgrade 'embedchain[milvus]'
+```
+
+Set the Zilliz environment variables `ZILLIZ_CLOUD_URI` and `ZILLIZ_CLOUD_TOKEN` which you can find it on their [cloud platform](https://cloud.zilliz.com/).
+
+<CodeGroup>
+
+```python main.py
+import os
+from embedchain import App
+
+os.environ['ZILLIZ_CLOUD_URI'] = 'https://xxx.zillizcloud.com'
+os.environ['ZILLIZ_CLOUD_TOKEN'] = 'xxx'
+
+# load zilliz configuration from yaml file
+app = App.from_config(yaml_path="config.yaml")
+```
+
+```yaml config.yaml
+vectordb:
+  provider: zilliz
+  config:
+    collection_name: 'zilliz-app'
+    uri: https://xxxx.api.gcp-region.zillizcloud.com
+    token: xxx
+    vector_dim: 1536
+    metric_type: L2
+```
+
+</CodeGroup>
+
+## LanceDB
+
+_Coming soon_
+
+## Pinecone
+
+Install pinecone related dependencies using the following command:
+
+```bash
+pip install --upgrade 'embedchain[pinecone]'
+```
+
+In order to use Pinecone as vector database, set the environment variables `PINECONE_API_KEY` and `PINECONE_ENV` which you can find on [Pinecone dashboard](https://app.pinecone.io/).
+
+<CodeGroup>
+
+```python main.py
+from embedchain import App
+
+# load pinecone configuration from yaml file
+app = App.from_config(yaml_path="config.yaml")
+```
+
+```yaml config.yaml
+vectordb:
+  provider: pinecone
+  config:
+    metric: cosine
+    vector_dimension: 1536
+    collection_name: my-pinecone-index
+```
+
+</CodeGroup>
+
+## Qdrant
+
+_Coming soon_
+
+## Weaviate
+
+In order to use Weaviate as a vector database, set the environment variables `WEAVIATE_ENDPOINT` and `WEAVIATE_API_KEY` which you can find on [Weaviate dashboard](https://console.weaviate.cloud/dashboard).
+
+```python main.py
+from embedchain import App
+
+# load weaviate configuration from yaml file
+app = App.from_config(yaml_path="config.yaml")
+```
+
+```yaml config.yaml
+vectordb:
+  provider: weaviate
+  config:
+    collection_name: my_weaviate_index
+```
+
+
+<Snippet file="missing-vector-db-tip.mdx" />

docs/contribution/dev.mdx

@@ -35,12 +35,9 @@ embedchain is built on the following stack:
 
 ## Team
 
-### Author
+### Authors
 
 - Taranjeet Singh ([@taranjeetio](https://twitter.com/taranjeetio))
-
-### Maintainer
-
 - Deshraj Yadav ([@deshrajdry](https://twitter.com/taranjeetio))
 
 ### Citation
@@ -49,8 +46,8 @@ If you utilize this repository, please consider citing it with:
 
 ```
 @misc{embedchain,
-  author = {Taranjeet Singh},
-  title = {Embechain: Framework to easily create LLM powered bots over any dataset},
+  author = {Taranjeet Singh, Deshraj Yadav},
+  title = {Embechain: Data platform for LLMs - Load, index, retrieve and sync any unstructured data},
   year = {2023},
   publisher = {GitHub},
   journal = {GitHub repository},

docs/data-sources/csv.mdx

@@ -1,14 +1,19 @@
 ---
-title: 'CSV'
+title: '📊 CSV'
 ---
 
-### CSV file
-
 To add any csv file, use the data_type as `csv`. `csv` allows remote urls and conventional file paths. Headers are included for each line, so if you have an `age` column, `18` will be added as `age: 18`. Eg:
 
 ```python
-app.add('https://example.com/content/sheet.csv', data_type="csv")
-app.add('content/sheet.csv', data_type="csv")
+from embedchain import App
+
+app = App()
+app.add('https://people.sc.fsu.edu/~jburkardt/data/csv/airtravel.csv', data_type="csv")
+# Or add using the local file path
+# app.add('/path/to/file.csv', data_type="csv")
+
+app.query("Summarize the air travel data")
+# Answer: The air travel data shows the number of flights for the months of July in the years 1958, 1959, and 1960. In July 1958, there were 491 flights, in July 1959 there were 548 flights, and in July 1960 there were 622 flights.
 ```
 
-Note: There is a size limit allowed for csv file beyond which it can throw error. This limit is set by the LLMs. Please consider chunking large csv files into smaller csv files.
+Note: There is a size limit allowed for csv file beyond which it can throw error. This limit is set by the LLMs. Please consider chunking large csv files into smaller csv files.

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

@@ -1,18 +1,16 @@
 ---
-title: 'Data Type Handling'
+title: 'Data type handling'
 ---
 
 ## Automatic data type detection
+
 The add method automatically tries to detect the data_type, based on your input for the source argument. So `app.add('https://www.youtube.com/watch?v=dQw4w9WgXcQ')` is enough to embed a YouTube video.
 
 This detection is implemented for all formats. It is based on factors such as whether it's a URL, a local file, the source data type, etc.
 
 ### Debugging automatic detection
 
-
-Set `log_level=DEBUG` (in [AppConfig](http://localhost:3000/advanced/query_configuration#appconfig)) and make sure it's working as intended.
-
-Otherwise, you will not know when, for instance, an invalid filepath is interpreted as raw text instead.
+Set `log_level: DEBUG` in the config yaml to debug if the data type detection is done right or not. Otherwise, you will not know when, for instance, an invalid filepath is interpreted as raw text instead.
 
 ### Forcing a data type
 
@@ -21,7 +19,7 @@ The examples below show you the keyword to force the respective `data_type`.
 
 Forcing can also be used for edge cases, such as interpreting a sitemap as a web_page, for reading its raw text instead of following links.
 
-## Remote Data Types
+## Remote data types
 
 <Tip>
 **Use local files in remote data types**
@@ -32,7 +30,7 @@ You can pass local files by formatting the path using the `file:` [URI scheme](h
 
 ## Reusing a vector database
 
-Default behavior is to create a persistent vector DB in the directory **./db**. You can split your application into two Python scripts: one to create a local vector DB and the other to reuse this local persistent vector DB. This is useful when you want to index hundreds of documents and separately implement a chat interface.
+Default behavior is to create a persistent vector db in the directory **./db**. You can split your application into two Python scripts: one to create a local vector db and the other to reuse this local persistent vector db. This is useful when you want to index hundreds of documents and separately implement a chat interface.
 
 Create a local index:
 

docs/data-sources/docs-site.mdx

@@ -1,11 +1,14 @@
 ---
-title: 'Code Documentation'
+title: '📚🌐 Code documentation'
 ---
 
-### Code documentation
-
 To add any code documentation website as a loader, use the data_type as `docs_site`. Eg:
 
 ```python
+from embedchain import App
+
+app = App()
 app.add("https://docs.embedchain.ai/", data_type="docs_site")
-```
+app.query("What is Embedchain?")
+# Answer: Embedchain is a platform that utilizes various components, including paid/proprietary ones, to provide what is believed to be the best configuration available. It uses LLM (Language Model) providers such as OpenAI, Anthpropic, Vertex_AI, GPT4ALL, Azure_OpenAI, LLAMA2, JINA, and COHERE. Embedchain allows users to import and utilize these LLM providers for their applications.'
+```

docs/data-sources/docx.mdx

@@ -1,5 +1,5 @@
 ---
-title: 'Docx File'
+title: '📄 Docx file'
 ---
 
 ### Docx file
@@ -7,6 +7,12 @@ title: 'Docx File'
 To add any doc/docx file, use the data_type as `docx`. `docx` allows remote urls and conventional file paths. Eg:
 
 ```python
+from embedchain import App
+
+app = App()
 app.add('https://example.com/content/intro.docx', data_type="docx")
-app.add('content/intro.docx', data_type="docx")
-```
+# Or add file using the local file path on your system
+# app.add('content/intro.docx', data_type="docx")
+
+app.query("Summarize the docx data?")
+```

docs/data-sources/how-to-add-data.mdx

@@ -1,24 +0,0 @@
----
-title: 'How to add data'
----
-
-## Add Dataset
-
-- This step assumes that you have already created an `App`. We are calling our app instance as `naval_chat_bot` 🤖
-
-- Now use `.add` method to add any dataset.
-
-```python
-naval_chat_bot = App()
-
-# Embed Online Resources
-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")
-naval_chat_bot.add("https://nav.al/feedback")
-naval_chat_bot.add("https://nav.al/agi")
-
-# Embed Local Resources
-naval_chat_bot.add(("Who is Naval Ravikant?", "Naval Ravikant is an Indian-American entrepreneur and investor."))
-```
-
-The possible formats to add data can be found on the [Supported Data Formats](/advanced/data_types) page.

docs/data-sources/mdx.mdx

@@ -1,12 +1,14 @@
 ---
-title: 'Mdx'
+title: '📝 Mdx file'
 ---
 
-
-### Mdx file
-
-To add any mdx file to your app, use the data_type (first argument to `.add()` method) as `mdx`. Note that this supports support mdx file present on machine, so this should be a file path. Eg:
+To add any `.mdx` file to your app, use the data_type (first argument to `.add()` method) as `mdx`. Note that this supports support mdx file present on machine, so this should be a file path. Eg:
 
 ```python
+from embedchain import App
+
+app = App()
 app.add('path/to/file.mdx', data_type='mdx')
-```
+
+app.query("What are the docs about?")
+```

docs/data-sources/notion.mdx

@@ -1,15 +1,20 @@
 ---
-title: 'Notion'
+title: '📓 Notion'
 ---
 
-### Notion
 To use notion you must install the extra dependencies with `pip install --upgrade embedchain[notion]`.
 
-To load a notion page, use the data_type as `notion`. Since it is hard to automatically detect, forcing this is advised.
+To load a notion page, use the data_type as `notion`. Since it is hard to automatically detect, it is advised to specify the `data_type` when adding a notion document.
 The next argument must **end** with the `notion page id`. The id is a 32-character string. Eg:
 
 ```python
-app.add("cfbc134ca6464fc980d0391613959196", "notion")
-app.add("my-page-cfbc134ca6464fc980d0391613959196", "notion")
-app.add("https://www.notion.so/my-page-cfbc134ca6464fc980d0391613959196", "notion")
-```
+from embedchain import App
+
+app = App()
+
+app.add("cfbc134ca6464fc980d0391613959196", data_type="notion")
+app.add("my-page-cfbc134ca6464fc980d0391613959196", data_type="notion")
+app.add("https://www.notion.so/my-page-cfbc134ca6464fc980d0391613959196", data_type="notion")
+
+app.query("Summarize the notion doc")
+```

docs/data-sources/overview.mdx

@@ -0,0 +1,24 @@
+---
+title: Overview
+---
+
+Embedchain comes with built-in support for various data sources. We handle the complexity of loading unstructured data from these data sources, allowing you to easily customize your app through a user-friendly interface.
+
+<CardGroup cols={4}>
+  <Card title="📊 csv" href="/data-sources/csv"></Card>
+  <Card title="📚🌐 docs site" href="/data-sources/docs-site"></Card>
+  <Card title="📄 docx" href="/data-sources/docx"></Card>
+  <Card title="📝 mdx" href="/data-sources/mdx"></Card>
+  <Card title="📓 notion" href="/data-sources/notion"></Card>
+  <Card title="📰 pdf" href="/data-sources/pdf-file"></Card>
+  <Card title="❓💬 q&a pair" href="/data-sources/qna"></Card>
+  <Card title="🗺️ sitemap" href="/data-sources/sitemap"></Card>
+  <Card title="📝 text" href="/data-sources/text"></Card>
+  <Card title="🌐📄 web page" href="/data-sources/web-page"></Card>
+  <Card title="🧾 xml" href="/data-sources/xml"></Card>
+  <Card title="🎥📺 youtube video" href="/data-sources/youtube-video"></Card>
+</CardGroup>
+
+<br/ >
+
+<Snippet file="missing-data-source-tip.mdx" />

docs/data-sources/pdf-file.mdx

@@ -1,14 +1,17 @@
 ---
-title: 'PDF File'
+title: '📰 PDF file'
 ---
 
-
-### PDF File
-
 To add any pdf file, use the data_type as `pdf_file`. Eg:
 
 ```python
-app.add('a_valid_url_where_pdf_file_can_be_accessed', data_type='pdf_file')
+from embedchain import App
+
+app = App()
+
+app.add('https://arxiv.org/pdf/1706.03762.pdf', data_type='pdf_file')
+app.query("What is the paper 'attention is all you need' about?")
+# Answer: The paper "Attention Is All You Need" proposes a new network architecture called the Transformer, which is based solely on attention mechanisms. It suggests moving away from complex recurrent or convolutional neural networks and instead using attention mechanisms to connect the encoder and decoder in sequence transduction models.
 ```
 
 Note that we do not support password protected pdfs.

docs/data-sources/qna.mdx

@@ -1,11 +1,13 @@
 ---
-title: 'QnA Pair'
+title: '❓💬 Queston and answer pair'
 ---
 
-### QnA pair
-
 QnA pair is a local data type. To supply your own QnA pair, use the data_type as `qna_pair` and enter a tuple. Eg:
 
 ```python
+from embedchain import App
+
+app = App()
+
 app.add(("Question", "Answer"), data_type="qna_pair")
 ```

docs/data-sources/request-new-format.mdx

@@ -1,4 +0,0 @@
----
-title: 'Request New Format'
-url: https://forms.gle/gB5La14tjgy4p94dA
----

docs/data-sources/sitemap.mdx

@@ -1,11 +1,13 @@
 ---
-title: 'Sitemap'
+title: '🗺️ Sitemap'
 ---
 
-### Sitemap
-
 Add all web pages from an xml-sitemap. Filters non-text files. Use the data_type as `sitemap`. Eg:
 
 ```python
+from embedchain import App
+
+app = App()
+
 app.add('https://example.com/sitemap.xml', data_type='sitemap')
 ```

docs/data-sources/text.mdx

@@ -1,5 +1,5 @@
 ---
-title: 'Text'
+title: '📝 Text'
 ---
 
 ### Text
@@ -7,7 +7,11 @@ title: 'Text'
 Text is a local data type. To supply your own text, use the data_type as `text` and enter a string. The text is not processed, this can be very versatile. Eg:
 
 ```python
+from embedchain import App
+
+app = App()
+
 app.add('Seek wealth, not money or status. Wealth is having assets that earn while you sleep. Money is how we transfer time and wealth. Status is your place in the social hierarchy.', data_type='text')
 ```
 
-Note: This is not used in the examples because in most cases you will supply a whole paragraph or file, which did not fit.
+Note: This is not used in the examples because in most cases you will supply a whole paragraph or file, which did not fit.

docs/data-sources/web-page.mdx

@@ -1,11 +1,13 @@
 ---
-title: 'Web page'
+title: '🌐📄 Web page'
 ---
 
-### Web page
-
 To add any web page, use the data_type as `web_page`. Eg:
 
 ```python
+from embedchain import App
+
+app = App()
+
 app.add('a_valid_web_page_url', data_type='web_page')
-```
+```

docs/data-sources/xml.mdx

@@ -0,0 +1,17 @@
+---
+title: '🧾 XML file'
+---
+
+### XML file
+
+To add any xml file, use the data_type as `xml`. Eg:
+
+```python
+from embedchain import App
+
+app = App()
+
+app.add('content/data.xml')
+```
+
+Note: Only the text content of the xml file will be added to the app. The tags will be ignored.

docs/data-sources/youtube-video.mdx

@@ -1,12 +1,13 @@
 ---
-title: 'Youtube Video'
+title: '🎥📺 Youtube video'
 ---
 
 
-### Youtube video
-
 To add any youtube video to your app, use the data_type (first argument to `.add()` method) as `youtube_video`. Eg:
 
 ```python
+from embedchain import App
+
+app = App()
 app.add('a_valid_youtube_url_here', data_type='youtube_video')
 ```

docs/get-start/faq.mdx

@@ -1,16 +0,0 @@
----
-title: ❓ Frequently Asked Questions
-description: 'Collections of all the frequently asked questions about Embedchain'
----
-
-## How to use GPT-4 as the LLM model
-
-```python
-
-from embedchain import App
-from embedchain.config import LlmConfig
-
-app = App()
-app.add("https://en.wikipedia.org/wiki/Elon_Musk")
-app.query("How many companies does Elon Musk run and name those?", config=LlmConfig(model="gpt-4"))
-```

docs/get-start/introduction.mdx

@@ -1,60 +0,0 @@
----
-title: 📚 Introduction
-description: '📝 Embedchain is a framework to easily create LLM powered bots over any dataset.'
----
-
-## 🤔 What is Embedchain?
-
-Embedchain abstracts the entire process of loading a dataset, chunking it, creating embeddings, and storing it in a vector database.
-
-You can add a single or multiple datasets using the `.add` method. Then, simply use the `.query` method to find answers from the added datasets.
-
-If you want to create a Naval Ravikant bot with a YouTube video, a book in PDF format, two blog posts, and a question and answer pair, all you need to do is add the respective links. Embedchain will take care of the rest, creating a bot for you.
-
-```python
-from embedchain import App
-
-naval_chat_bot = App()
-# Embed Online Resources
-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")
-naval_chat_bot.add("https://nav.al/feedback")
-naval_chat_bot.add("https://nav.al/agi")
-naval_chat_bot.add("The Meanings of Life", 'text', metadata={'chapter': 'philosphy'})
-
-# Embed Local Resources
-naval_chat_bot.add(("Who is Naval Ravikant?", "Naval Ravikant is an Indian-American entrepreneur and investor."))
-
-naval_chat_bot.query("What unique capacity does Naval argue humans possess when it comes to understanding explanations or concepts?")
-# Answer: Naval argues that humans possess the unique capacity to understand explanations or concepts to the maximum extent possible in this physical reality.
-
-# with where context filter
-naval_chat_bot.query("What unique capacity does Naval argue humans possess when it comes to understanding explanations or concepts?", where={'chapter': 'philosophy'})
-```
-
-## 🚀 How it works?
-
-Creating a chat bot over any dataset involves the following steps:
-
-1. Detect the data type and load the data
-2. Create meaningful chunks
-3. Create embeddings for each chunk
-4. Store the chunks in a vector database
-
-When a user asks a query, the following process happens to find the answer:
-
-1. Create an embedding for the query
-2. Find similar documents for the query from the vector database
-3. Pass the similar documents as context to LLM to get the final answer.
-
-The process of loading the dataset and querying involves multiple steps, each with its own nuances:
-
-- How should I chunk the data? What is a meaningful chunk size?
-- How should I create embeddings for each chunk? Which embedding model should I use?
-- How should I store the chunks in a vector database? Which vector database should I use?
-- Should I store metadata along with the embeddings?
-- How should I find similar documents for a query? Which ranking model should I use?
-
-Embedchain takes care of all these nuances and provides a simple interface to create bots over any dataset.
-
-In the first release, we make it easier for anyone to get a chatbot over any dataset up and running in less than a minute. Just create an app instance, add the datasets using the `.add` method, and use the `.query` method to get the relevant answers.

docs/get-start/quickstart.mdx

@@ -1,35 +0,0 @@
----
-title: '🚀 Quickstart'
-description: '💡 Start building LLM powered bots under 30 seconds'
----
-
-Install embedchain python package:
-
-```bash
-pip install --upgrade embedchain
-```
-
-Creating a chatbot involves 3 steps:
-
-- ⚙️ Import the App instance
-- 🗃️ Add Dataset
-- 💬 Query or Chat on the dataset and get answers (Interface Types)
-
-Run your first bot in python using the following code. Make sure to set the `OPENAI_API_KEY` 🔑 environment variable in the code.
-
-```python
-import os
-
-from embedchain import App
-
-os.environ["OPENAI_API_KEY"] = "xxx"
-elon_musk_bot = App()
-
-# Embed Online Resources
-elon_musk_bot.add("https://en.wikipedia.org/wiki/Elon_Musk")
-elon_musk_bot.add("https://www.forbes.com/profile/elon-musk")
-
-response = elon_musk_bot.query("How many companies does Elon Musk run and name those?")
-print(response)
-# 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.'
-```

docs/get-started/faq.mdx

@@ -0,0 +1,68 @@
+---
+title: ❓ FAQs
+description: 'Collections of all the frequently asked questions'
+---
+
+#### How to use GPT-4 as the LLM model?
+
+<CodeGroup>
+
+```python main.py
+import os
+from embedchain import App
+
+os.environ['OPENAI_API_KEY'] = 'xxx'
+
+# load llm configuration from gpt4.yaml file
+app = App.from_config(yaml_path="gpt4.yaml")
+```
+
+```yaml gpt4.yaml
+llm:
+  provider: openai
+  model: 'gpt-4'
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+    stream: false
+```
+
+</CodeGroup>
+
+#### I don't have OpenAI credits. How can I use some open source model?
+
+<CodeGroup>
+
+```python main.py
+import os
+from embedchain import App
+
+os.environ['OPENAI_API_KEY'] = 'xxx'
+
+# load llm configuration from opensource.yaml file
+app = App.from_config(yaml_path="opensource.yaml")
+```
+
+```yaml opensource.yaml
+llm:
+  provider: gpt4all
+  model: 'orca-mini-3b.ggmlv3.q4_0.bin'
+  config:
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+    stream: false
+
+embedder:
+  provider: gpt4all
+  config:
+    model: 'all-MiniLM-L6-v2'
+```
+</CodeGroup>
+
+#### How to contact support?
+
+If docs aren't sufficient, please feel free to reach out to us using one of the following methods:
+
+<Snippet file="get-help.mdx" />

docs/get-started/introduction.mdx

@@ -0,0 +1,55 @@
+---
+title: 📚 Introduction
+description: '📝 Embedchain is a Data Platform for LLMs - load, index, retrieve, and sync any unstructured data'
+---
+
+## 🤔 What is Embedchain?
+
+Embedchain abstracts the entire process of loading data, chunking it, creating embeddings, and storing it in a vector database.
+
+You can add data from different data sources using the `.add()` method. Then, simply use the `.query()` method to find answers from the added datasets.
+
+If you want to create a Naval Ravikant bot with a YouTube video, a book in PDF format, two blog posts, and a question and answer pair, all you need to do is add the respective links. Embedchain will take care of the rest, creating a bot for you.
+
+```python
+from embedchain import App
+
+naval_bot = App()
+# Add online data
+naval_bot.add("https://www.youtube.com/watch?v=3qHkcs3kG44")
+naval_bot.add("https://navalmanack.s3.amazonaws.com/Eric-Jorgenson_The-Almanack-of-Naval-Ravikant_Final.pdf")
+naval_bot.add("https://nav.al/feedback")
+naval_bot.add("https://nav.al/agi")
+naval_bot.add("The Meanings of Life", 'text', metadata={'chapter': 'philosphy'})
+
+# Add local resources
+naval_bot.add(("Who is Naval Ravikant?", "Naval Ravikant is an Indian-American entrepreneur and investor."))
+
+naval_bot.query("What unique capacity does Naval argue humans possess when it comes to understanding explanations or concepts?")
+# Answer: Naval argues that humans possess the unique capacity to understand explanations or concepts to the maximum extent possible in this physical reality.
+```
+
+## 🚀 How it works?
+
+Embedchain abstracts out the following steps from you to easily create LLM powered apps:
+
+1. Detect the data type and load data
+2. Create meaningful chunks
+3. Create embeddings for each chunk
+4. Store chunks in a vector database
+
+When a user asks a query, the following process happens to find the answer:
+
+1. Create an embedding for the query
+2. Find similar documents for the query from the vector database
+3. Pass the similar documents as context to LLM to get the final answer
+
+The process of loading the dataset and querying involves multiple steps, each with its own nuances:
+
+- How should I chunk the data? What is a meaningful chunk size?
+- How should I create embeddings for each chunk? Which embedding model should I use?
+- How should I store the chunks in a vector database? Which vector database should I use?
+- Should I store metadata along with the embeddings?
+- How should I find similar documents for a query? Which ranking model should I use?
+
+Embedchain takes care of all these nuances and provides a simple interface to create apps on any data.

docs/get-started/quickstart.mdx

@@ -0,0 +1,58 @@
+---
+title: '🚀 Quickstart'
+description: '💡 Start building LLM powered apps under 30 seconds'
+---
+
+Embedchain is a Data Platform for LLMs - load, index, retrieve, and sync any unstructured data. Using embedchain, you can easily create LLM powered apps over any data. 
+
+Install embedchain python package:
+
+```bash
+pip install embedchain
+```
+
+Creating an app involves 3 steps:
+
+<Steps>
+  <Step title="⚙️ Import app instance">
+```python
+from embedchain import App
+app = App()
+```
+  </Step>
+  <Step title="🗃️ Add data sources">
+```python
+# Add different data sources
+elon_bot.add("https://en.wikipedia.org/wiki/Elon_Musk")
+elon_bot.add("https://www.forbes.com/profile/elon-musk")
+# You can also add local data sources such as pdf, csv files etc.
+# elon_bot.add("/path/to/file.pdf")
+```
+  </Step>
+  <Step title="💬 Query or chat on your data and get answers">
+```python
+elon_bot.query("What is the net worth of Elon Musk today?")
+# Answer: The net worth of Elon Musk today is $258.7 billion.
+```
+  </Step>
+</Steps>
+
+Putting it together, you can run your first app using the following code. Make sure to set the `OPENAI_API_KEY` 🔑 environment variable in the code.
+
+```python
+import os
+from embedchain import App
+
+os.environ["OPENAI_API_KEY"] = "xxx"
+elon_bot = App()
+
+# Add different data sources
+elon_bot.add("https://en.wikipedia.org/wiki/Elon_Musk")
+elon_bot.add("https://www.forbes.com/profile/elon-musk")
+# You can also add local data sources such as pdf, csv files etc.
+# elon_bot.add("/path/to/file.pdf")
+
+response = elon_bot.query("What is the net worth of Elon Musk today?")
+print(response)
+# Answer: The net worth of Elon Musk today is $258.7 billion.
+```

docs/mint.json

@@ -16,13 +16,13 @@
       "name": "Twitter",
       "url": "https://twitter.com/embedchain"
     },
-    {
-      "name": "Discord",
-      "url": "https://discord.gg/6PzXDgEjG5"
-    },
     {
       "name":"Slack",
       "url":"https://join.slack.com/t/embedchain/shared_invite/zt-22uwz3c46-Zg7cIh5rOBteT_xe1jwLDw"
+    },
+    {
+      "name": "Discord",
+      "url": "https://discord.gg/6PzXDgEjG5"
     }
   ],
   "topbarCtaButton": {
@@ -32,20 +32,18 @@
   "navigation": [
     {
       "group": "Get started",
-      "pages": ["get-start/quickstart", "get-start/introduction", "get-start/faq"]
-    },
-
-    {
-      "group": "Advanced",
-      "pages": ["advanced/app_types", "advanced/interface_types", "advanced/query_configuration", "advanced/configuration", "advanced/testing", "advanced/vector_database"]
+      "pages": ["get-started/quickstart", "get-started/introduction", "get-started/faq"]
     },
     {
-      "group": "Data Sources",
+      "group": "Components",
+      "pages": ["components/llms", "components/embedding-models", "components/vector-databases"]
+    },
+    {
+      "group": "Data sources",
       "pages": [
-        "data-sources/how-to-add-data",
-        "data-sources/data-type-handling",
+        "data-sources/overview",
         {
-          "group": "Supported Data Sources",
+          "group": "Supported data sources",
           "pages": [
             "data-sources/csv",
             "data-sources/docs-site",
@@ -60,9 +58,13 @@
             "data-sources/youtube-video"
           ]
         },
-        "data-sources/request-new-format"
+        "data-sources/data-type-handling"
       ]
     },
+    {
+      "group": "Advanced",
+      "pages": ["advanced/configuration"]
+    },
     {
       "group": "Examples",
       "pages": ["examples/full_stack", "examples/api_server", "examples/discord_bot", "examples/slack_bot", "examples/telegram_bot", "examples/whatsapp_bot", "examples/poe_bot"]
@@ -75,7 +77,7 @@
       ]
     },
     {
-      "group": "Integration",
+      "group": "Integrations",
       "pages": ["integration/langsmith"]
     },
     {
@@ -98,12 +100,14 @@
   ],
 
   "footerSocials": {
-    "twitter": "https://twitter.com/embedchain",
-    "github": "https://github.com/embedchain/embedchain",
-    "linkedin": "https://www.linkedin.com/company/embedchain",
     "website": "https://embedchain.ai",
-    "slack":"https://join.slack.com/t/embedchain/shared_invite/zt-22uwz3c46-Zg7cIh5rOBteT_xe1jwLDw"
+    "github": "https://github.com/embedchain/embedchain",
+    "slack":"https://join.slack.com/t/embedchain/shared_invite/zt-22uwz3c46-Zg7cIh5rOBteT_xe1jwLDw",
+    "discord": "https://discord.gg/6PzXDgEjG5",
+    "twitter": "https://twitter.com/embedchain",
+    "linkedin": "https://www.linkedin.com/company/embedchain"
   },
   "backgroundImage": "/background.png",
-  "isWhiteLabeled": true
+  "isWhiteLabeled": true,
+  "feedback.thumbsRating": true
 }

embedchain/__init__.py

@@ -6,6 +6,6 @@ from embedchain.apps.app import App  # noqa: F401
 from embedchain.apps.custom_app import CustomApp  # noqa: F401
 from embedchain.apps.Llama2App import Llama2App  # noqa: F401
 from embedchain.apps.open_source_app import OpenSourceApp  # noqa: F401
-from embedchain.apps.PersonApp import (PersonApp,  # noqa: F401
-                                       PersonOpenSourceApp)
+from embedchain.apps.person_app import (PersonApp,  # noqa: F401
+                                        PersonOpenSourceApp)
 from embedchain.vectordb.chroma import ChromaDB  # noqa: F401

embedchain/apps/app.py

@@ -1,12 +1,13 @@
-import logging
 from typing import Optional
 
-from embedchain.config import (AppConfig, BaseEmbedderConfig, BaseLlmConfig,
-                               ChromaDbConfig)
+import yaml
+
+from embedchain.config import AppConfig, BaseEmbedderConfig, BaseLlmConfig
 from embedchain.config.vectordb.base import BaseVectorDbConfig
 from embedchain.embedchain import EmbedChain
 from embedchain.embedder.base import BaseEmbedder
 from embedchain.embedder.openai import OpenAIEmbedder
+from embedchain.factory import EmbedderFactory, LlmFactory, VectorDBFactory
 from embedchain.helper.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 from embedchain.llm.openai import OpenAILlm
@@ -35,7 +36,6 @@ class App(EmbedChain):
         db_config: Optional[BaseVectorDbConfig] = None,
         embedder: BaseEmbedder = None,
         embedder_config: Optional[BaseEmbedderConfig] = None,
-        chromadb_config: Optional[ChromaDbConfig] = None,
         system_prompt: Optional[str] = None,
     ):
         """
@@ -46,7 +46,7 @@ class App(EmbedChain):
         :param llm:  LLM Class instance. example: `from embedchain.llm.openai import OpenAILlm`, defaults to OpenAiLlm
         :type llm: BaseLlm, optional
         :param llm_config: Allows you to configure the LLM, e.g. how many documents to return,
-        example: `from embedchain.config import LlmConfig`, defaults to None
+        example: `from embedchain.config import BaseLlmConfig`, defaults to None
         :type llm_config: Optional[BaseLlmConfig], optional
         :param db: The database to use for storing and retrieving embeddings,
         example: `from embedchain.vectordb.chroma_db import ChromaDb`, defaults to ChromaDb
@@ -60,20 +60,10 @@ class App(EmbedChain):
         :param embedder_config: Allows you to configure the Embedder.
         example: `from embedchain.config import BaseEmbedderConfig`, defaults to None
         :type embedder_config: Optional[BaseEmbedderConfig], optional
-        :param chromadb_config: Deprecated alias of `db_config`, defaults to None
-        :type chromadb_config: Optional[ChromaDbConfig], optional
         :param system_prompt: System prompt that will be provided to the LLM as such, defaults to None
         :type system_prompt: Optional[str], optional
         :raises TypeError: LLM, database or embedder or their config is not a valid class instance.
         """
-        # Overwrite deprecated arguments
-        if chromadb_config:
-            logging.warning(
-                "DEPRECATION WARNING: Please use `db_config` argument instead of `chromadb_config`."
-                "`chromadb_config` will be removed in a future release."
-            )
-            db_config = chromadb_config
-
         # Type check configs
         if config and not isinstance(config, AppConfig):
             raise TypeError(
@@ -123,3 +113,33 @@ class App(EmbedChain):
                 "Please make sure the type is right and that you are passing an instance."
             )
         super().__init__(config, llm=llm, db=db, embedder=embedder, system_prompt=system_prompt)
+
+    @classmethod
+    def from_config(cls, yaml_path: str):
+        """
+        Instantiate an App object from a YAML configuration file.
+
+        :param yaml_path: Path to the YAML configuration file.
+        :type yaml_path: str
+        :return: An instance of the App class.
+        :rtype: App
+        """
+        with open(yaml_path, "r") as file:
+            config_data = yaml.safe_load(file)
+
+        app_config_data = config_data.get("app", {})
+        llm_config_data = config_data.get("llm", {})
+        db_config_data = config_data.get("vectordb", {})
+        embedder_config_data = config_data.get("embedder", {})
+
+        app_config = AppConfig(**app_config_data.get("config", {}))
+
+        llm_provider = llm_config_data.get("provider", "openai")
+        llm = LlmFactory.create(llm_provider, llm_config_data.get("config", {}))
+
+        db_provider = db_config_data.get("provider", "chroma")
+        db = VectorDBFactory.create(db_provider, db_config_data.get("config", {}))
+
+        embedder_provider = embedder_config_data.get("provider", "openai")
+        embedder = EmbedderFactory.create(embedder_provider, embedder_config_data.get("config", {}))
+        return cls(config=app_config, llm=llm, db=db, embedder=embedder)

embedchain/apps/open_source_app.py

@@ -46,7 +46,7 @@ class OpenSourceApp(App):
         that does not fall into the LLM, database or embedder category, defaults to None
         :type config: OpenSourceAppConfig, optional
         :param llm_config: Allows you to configure the LLM, e.g. how many documents to return.
-        example: `from embedchain.config import LlmConfig`, defaults to None
+        example: `from embedchain.config import BaseLlmConfig`, defaults to None
         :type llm_config: BaseLlmConfig, optional
         :param chromadb_config: Allows you to configure the open source database,
         example: `from embedchain.config import ChromaDbConfig`, defaults to None
@@ -54,7 +54,7 @@ class OpenSourceApp(App):
         :param system_prompt: System prompt that will be provided to the LLM as such.
         Please don't use for the time being, as it's not supported., defaults to None
         :type system_prompt: Optional[str], optional
-        :raises TypeError: `OpenSourceAppConfig` or `LlmConfig` invalid.
+        :raises TypeError: `OpenSourceAppConfig` or `BaseLlmConfig` invalid.
         """
         logging.warning(
             "DEPRECATION WARNING: Please use `App` instead of `OpenSourceApp`."

embedchain/apps/person_app.py

@@ -2,10 +2,9 @@ from string import Template
 
 from embedchain.apps.app import App
 from embedchain.apps.open_source_app import OpenSourceApp
-from embedchain.config import BaseLlmConfig
-from embedchain.config.apps.base_app_config import BaseAppConfig
-from embedchain.config.llm.base_llm_config import (DEFAULT_PROMPT,
-                                                   DEFAULT_PROMPT_WITH_HISTORY)
+from embedchain.config import AppConfig, BaseLlmConfig
+from embedchain.config.llm.base import (DEFAULT_PROMPT,
+                                        DEFAULT_PROMPT_WITH_HISTORY)
 from embedchain.helper.json_serializable import register_deserializable
 
 
@@ -16,16 +15,16 @@ class EmbedChainPersonApp:
     This bot behaves and speaks like a person.
 
     :param person: name of the person, better if its a well known person.
-    :param config: BaseAppConfig instance to load as configuration.
+    :param config: AppConfig instance to load as configuration.
     """
 
-    def __init__(self, person: str, config: BaseAppConfig = None):
+    def __init__(self, person: str, config: AppConfig = None):
         """Initialize a new person app
 
         :param person: Name of the person that's imitated.
         :type person: str
         :param config: Configuration class instance, defaults to None
-        :type config: BaseAppConfig, optional
+        :type config: AppConfig, optional
         """
         self.person = person
         self.person_prompt = f"You are {person}. Whatever you say, you will always say in {person} style."  # noqa:E501
@@ -70,7 +69,7 @@ class PersonApp(EmbedChainPersonApp, App):
     """
 
     def query(self, input_query, config: BaseLlmConfig = None, dry_run=False):
-        config = self.add_person_template_to_config(DEFAULT_PROMPT, config, where=None)
+        config = self.add_person_template_to_config(DEFAULT_PROMPT, config)
         return super().query(input_query, config, dry_run, where=None)
 
     def chat(self, input_query, config: BaseLlmConfig = None, dry_run=False, where=None):

embedchain/bots/base.py

@@ -1,7 +1,7 @@
 from typing import Any
 
-from embedchain import CustomApp
-from embedchain.config import AddConfig, CustomAppConfig, LlmConfig
+from embedchain import App
+from embedchain.config import AddConfig, AppConfig, BaseLlmConfig
 from embedchain.embedder.openai import OpenAIEmbedder
 from embedchain.helper.json_serializable import (JSONSerializable,
                                                  register_deserializable)
@@ -12,7 +12,7 @@ from embedchain.vectordb.chroma import ChromaDB
 @register_deserializable
 class BaseBot(JSONSerializable):
     def __init__(self):
-        self.app = CustomApp(config=CustomAppConfig(), llm=OpenAILlm(), db=ChromaDB(), embedder=OpenAIEmbedder())
+        self.app = App(config=AppConfig(), llm=OpenAILlm(), db=ChromaDB(), embedder=OpenAIEmbedder())
 
     def add(self, data: Any, config: AddConfig = None):
         """
@@ -27,14 +27,14 @@ class BaseBot(JSONSerializable):
         config = config if config else AddConfig()
         self.app.add(data, config=config)
 
-    def query(self, query: str, config: LlmConfig = None) -> str:
+    def query(self, query: str, config: BaseLlmConfig = None) -> str:
         """
         Query the bot
 
         :param query: the user query
         :type query: str
         :param config: configuration class instance, defaults to None
-        :type config: LlmConfig, optional
+        :type config: BaseLlmConfig, optional
         :return: Answer
         :rtype: str
         """

embedchain/chunkers/sitemap.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.helper.json_serializable import register_deserializable
+
+
+@register_deserializable
+class SitemapChunker(BaseChunker):
+    """Chunker for sitemap."""
+
+    def __init__(self, config: Optional[ChunkerConfig] = None):
+        if config is None:
+            config = ChunkerConfig(chunk_size=500, 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/chunkers/xml.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.helper.json_serializable import register_deserializable
+
+
+@register_deserializable
+class XmlChunker(BaseChunker):
+    """Chunker for XML files."""
+
+    def __init__(self, config: Optional[ChunkerConfig] = None):
+        if config is None:
+            config = ChunkerConfig(chunk_size=500, chunk_overlap=50, 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/config/__init__.py

@@ -7,8 +7,8 @@ from .apps.open_source_app_config import OpenSourceAppConfig
 from .base_config import BaseConfig
 from .embedder.base import BaseEmbedderConfig
 from .embedder.base import BaseEmbedderConfig as EmbedderConfig
-from .llm.base_llm_config import BaseLlmConfig
-from .llm.base_llm_config import BaseLlmConfig as LlmConfig
+from .llm.base import BaseLlmConfig
 from .vectordb.chroma import ChromaDbConfig
 from .vectordb.elasticsearch import ElasticsearchDBConfig
 from .vectordb.opensearch import OpenSearchDBConfig
+from .vectordb.zilliz import ZillizDBConfig

embedchain/config/llm/base.py

@@ -73,7 +73,6 @@ class BaseLlmConfig(BaseConfig):
         Initializes a configuration class instance for the LLM.
 
         Takes the place of the former `QueryConfig` or `ChatConfig`.
-        Use `LlmConfig` as an alias to `BaseLlmConfig`.
 
         :param number_documents:  Number of documents to pull from the database as
         context, defaults to 1
@@ -115,6 +114,9 @@ class BaseLlmConfig(BaseConfig):
         self.system_prompt = system_prompt
         self.query_type = query_type
 
+        if type(template) is str:
+            template = Template(template)
+
         if self.validate_template(template):
             self.template = template
         else:

embedchain/config/vectordb/base.py

@@ -10,6 +10,7 @@ class BaseVectorDbConfig(BaseConfig):
         dir: str = "db",
         host: Optional[str] = None,
         port: Optional[str] = None,
+        **kwargs,
     ):
         """
         Initializes a configuration class instance for the vector database.
@@ -22,8 +23,14 @@ class BaseVectorDbConfig(BaseConfig):
         :type host: Optional[str], optional
         :param host: Database connection remote port. Use this if you run Embedchain as a client, defaults to None
         :type port: Optional[str], optional
+        :param kwargs: Additional keyword arguments
+        :type kwargs: dict
         """
         self.collection_name = collection_name or "embedchain_store"
         self.dir = dir
         self.host = host
         self.port = port
+        # Assign additional keyword arguments
+        if kwargs:
+            for key, value in kwargs.items():
+                setattr(self, key, value)

embedchain/config/vectordb/pinecone.py

@@ -0,0 +1,20 @@
+from typing import Dict, Optional
+
+from embedchain.config.vectordb.base import BaseVectorDbConfig
+from embedchain.helper.json_serializable import register_deserializable
+
+
+@register_deserializable
+class PineconeDBConfig(BaseVectorDbConfig):
+    def __init__(
+        self,
+        collection_name: Optional[str] = None,
+        dir: Optional[str] = None,
+        vector_dimension: int = 1536,
+        metric: Optional[str] = "cosine",
+        **extra_params: Dict[str, any],
+    ):
+        self.metric = metric
+        self.vector_dimension = vector_dimension
+        self.extra_params = extra_params
+        super().__init__(collection_name=collection_name, dir=dir)

embedchain/config/vectordb/weaviate.py

@@ -0,0 +1,16 @@
+from typing import Dict, Optional
+
+from embedchain.config.vectordb.base import BaseVectorDbConfig
+from embedchain.helper.json_serializable import register_deserializable
+
+
+@register_deserializable
+class WeaviateDBConfig(BaseVectorDbConfig):
+    def __init__(
+        self,
+        collection_name: Optional[str] = None,
+        dir: Optional[str] = None,
+        **extra_params: Dict[str, any],
+    ):
+        self.extra_params = extra_params
+        super().__init__(collection_name=collection_name, dir=dir)

embedchain/config/vectordb/zilliz.py

@@ -0,0 +1,49 @@
+import os
+from typing import Optional
+
+from embedchain.config.vectordb.base import BaseVectorDbConfig
+from embedchain.helper.json_serializable import register_deserializable
+
+
+@register_deserializable
+class ZillizDBConfig(BaseVectorDbConfig):
+    def __init__(
+        self,
+        collection_name: Optional[str] = None,
+        dir: Optional[str] = None,
+        uri: Optional[str] = None,
+        token: Optional[str] = None,
+        vector_dim: Optional[str] = None,
+        metric_type: Optional[str] = None,
+    ):
+        """
+        Initializes a configuration class instance for the vector database.
+
+        :param collection_name: Default name for the collection, defaults to None
+        :type collection_name: Optional[str], optional
+        :param dir: Path to the database directory, where the database is stored, defaults to "db"
+        :type dir: str, optional
+        :param uri: Cluster endpoint obtained from the Zilliz Console, defaults to None
+        :type uri: Optional[str], optional
+        :param token: API Key, if a Serverless Cluster, username:password, if a Dedicated Cluster, defaults to None
+        :type port: Optional[str], optional
+        """
+        self.uri = uri or os.environ.get("ZILLIZ_CLOUD_URI")
+        if not self.uri:
+            raise AttributeError(
+                "Zilliz needs a URI attribute, "
+                "this can either be passed to `ZILLIZ_CLOUD_URI` or as `ZILLIZ_CLOUD_URI` in `.env`"
+            )
+
+        self.token = token or os.environ.get("ZILLIZ_CLOUD_TOKEN")
+        if not self.token:
+            raise AttributeError(
+                "Zilliz needs a token attribute, "
+                "this can either be passed to `ZILLIZ_CLOUD_TOKEN` or as `ZILLIZ_CLOUD_TOKEN` in `.env`,"
+                "if having a username and password, pass it in the form 'username:password' to `ZILLIZ_CLOUD_TOKEN`"
+            )
+
+        self.metric_type = metric_type if metric_type else "L2"
+
+        self.vector_dim = vector_dim
+        super().__init__(collection_name=collection_name, dir=dir)

embedchain/data_formatter/data_formatter.py

@@ -6,9 +6,11 @@ from embedchain.chunkers.mdx import MdxChunker
 from embedchain.chunkers.notion import NotionChunker
 from embedchain.chunkers.pdf_file import PdfFileChunker
 from embedchain.chunkers.qna_pair import QnaPairChunker
+from embedchain.chunkers.sitemap import SitemapChunker
 from embedchain.chunkers.table import TableChunker
 from embedchain.chunkers.text import TextChunker
 from embedchain.chunkers.web_page import WebPageChunker
+from embedchain.chunkers.xml import XmlChunker
 from embedchain.chunkers.youtube_video import YoutubeVideoChunker
 from embedchain.config import AddConfig
 from embedchain.config.add_config import ChunkerConfig, LoaderConfig
@@ -24,6 +26,7 @@ from embedchain.loaders.mdx import MdxLoader
 from embedchain.loaders.pdf_file import PdfFileLoader
 from embedchain.loaders.sitemap import SitemapLoader
 from embedchain.loaders.web_page import WebPageLoader
+from embedchain.loaders.xml import XmlLoader
 from embedchain.loaders.youtube_video import YoutubeVideoLoader
 from embedchain.models.data_type import DataType
 
@@ -67,6 +70,7 @@ class DataFormatter(JSONSerializable):
             DataType.TEXT: LocalTextLoader,
             DataType.DOCX: DocxFileLoader,
             DataType.SITEMAP: SitemapLoader,
+            DataType.XML: XmlLoader,
             DataType.DOCS_SITE: DocsSiteLoader,
             DataType.CSV: CsvLoader,
             DataType.MDX: MdxLoader,
@@ -106,10 +110,12 @@ class DataFormatter(JSONSerializable):
             DataType.TEXT: TextChunker,
             DataType.DOCX: DocxFileChunker,
             DataType.DOCS_SITE: DocsSiteChunker,
+            DataType.SITEMAP: SitemapChunker,
             DataType.NOTION: NotionChunker,
             DataType.CSV: TableChunker,
             DataType.MDX: MdxChunker,
             DataType.IMAGES: ImagesChunker,
+            DataType.XML: XmlChunker,
         }
         if data_type in chunker_classes:
             chunker_class: type = chunker_classes[data_type]

embedchain/embedchain.py

@@ -339,7 +339,6 @@ class EmbedChain(JSONSerializable):
         metadatas = embeddings_data["metadatas"]
         ids = embeddings_data["ids"]
         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")
             return [], [], [], 0
@@ -351,12 +350,15 @@ class EmbedChain(JSONSerializable):
 
         # get existing ids, and discard doc if any common id exist.
         where = {"url": src}
+        # if data type is qna_pair, we check for question
+        if chunker.data_type == DataType.QNA_PAIR:
+            where = {"question": src[0]}
+
         if self.config.id is not None:
-            where.update({"metadata.app_id": self.config.id})
+            where["app_id"] = self.config.id
 
         db_result = self.db.get(ids=ids, where=where)  # optional filter
         existing_ids = set(db_result["ids"])
-
         if len(existing_ids):
             data_dict = {id: (doc, meta) for id, doc, meta in zip(ids, documents, metadatas)}
             data_dict = {id: value for id, value in data_dict.items() if id not in existing_ids}
@@ -404,6 +406,7 @@ class EmbedChain(JSONSerializable):
             skip_embedding=(chunker.data_type == DataType.IMAGES),
         )
         count_new_chunks = self.db.count() - chunks_before_addition
+
         print((f"Successfully saved {src} ({chunker.data_type}). New chunks count: {count_new_chunks}"))
         return list(documents), metadatas, ids, count_new_chunks
 
@@ -432,7 +435,6 @@ class EmbedChain(JSONSerializable):
         :rtype: List[str]
         """
         query_config = config or self.llm.config
-
         if where is not None:
             where = where
         elif query_config is not None and query_config.where is not None:
@@ -459,7 +461,6 @@ class EmbedChain(JSONSerializable):
             where=where,
             skip_embedding=(hasattr(config, "query_type") and config.query_type == "Images"),
         )
-
         return contents
 
     def query(self, input_query: str, config: BaseLlmConfig = None, dry_run=False, where: Optional[Dict] = None) -> str:
@@ -470,7 +471,7 @@ class EmbedChain(JSONSerializable):
 
         :param input_query: The query to use.
         :type input_query: str
-        :param config: The `LlmConfig` instance to use as configuration options. This is used for one method call.
+        :param config: The `BaseLlmConfig` instance to use as configuration options. This is used for one method call.
         To persistently use a config, declare it during app init., defaults to None
         :type config: Optional[BaseLlmConfig], optional
         :param dry_run: A dry run does everything except send the resulting prompt to
@@ -506,7 +507,7 @@ class EmbedChain(JSONSerializable):
 
         :param input_query: The query to use.
         :type input_query: str
-        :param config: The `LlmConfig` instance to use as configuration options. This is used for one method call.
+        :param config: The `BaseLlmConfig` instance to use as configuration options. This is used for one method call.
         To persistently use a config, declare it during app init., defaults to None
         :type config: Optional[BaseLlmConfig], optional
         :param dry_run: A dry run does everything except send the resulting prompt to

embedchain/embedder/vertexai.py

@@ -7,7 +7,7 @@ from embedchain.embedder.base import BaseEmbedder
 from embedchain.models import VectorDimensions
 
 
-class VertexAiEmbedder(BaseEmbedder):
+class VertexAIEmbedder(BaseEmbedder):
     def __init__(self, config: Optional[BaseEmbedderConfig] = None):
         super().__init__(config=config)
 

embedchain/factory.py

@@ -0,0 +1,94 @@
+import importlib
+
+
+def load_class(class_type):
+    module_path, class_name = class_type.rsplit(".", 1)
+    module = importlib.import_module(module_path)
+    return getattr(module, class_name)
+
+
+class LlmFactory:
+    provider_to_class = {
+        "anthropic": "embedchain.llm.anthropic.AnthropicLlm",
+        "azure_openai": "embedchain.llm.azure_openai.AzureOpenAILlm",
+        "cohere": "embedchain.llm.cohere.CohereLlm",
+        "gpt4all": "embedchain.llm.gpt4all.GPT4ALLLlm",
+        "huggingface": "embedchain.llm.huggingface.HuggingFaceLlm",
+        "jina": "embedchain.llm.jina.JinaLlm",
+        "llama2": "embedchain.llm.llama2.Llama2Llm",
+        "openai": "embedchain.llm.openai.OpenAILlm",
+        "vertexai": "embedchain.llm.vertex_ai.VertexAILlm",
+    }
+    provider_to_config_class = {
+        "embedchain": "embedchain.config.llm.base.BaseLlmConfig",
+        "openai": "embedchain.config.llm.base.BaseLlmConfig",
+        "anthropic": "embedchain.config.llm.base.BaseLlmConfig",
+    }
+
+    @classmethod
+    def create(cls, provider_name, config_data):
+        class_type = cls.provider_to_class.get(provider_name)
+        # Default to embedchain base config if the provider is not in the config map
+        config_name = "embedchain" if provider_name not in cls.provider_to_config_class else provider_name
+        config_class_type = cls.provider_to_config_class.get(config_name)
+        if class_type:
+            llm_class = load_class(class_type)
+            llm_config_class = load_class(config_class_type)
+            return llm_class(config=llm_config_class(**config_data))
+        else:
+            raise ValueError(f"Unsupported Llm provider: {provider_name}")
+
+
+class EmbedderFactory:
+    provider_to_class = {
+        "gpt4all": "embedchain.embedder.gpt4all.GPT4AllEmbedder",
+        "huggingface": "embedchain.embedder.huggingface.HuggingFaceEmbedder",
+        "vertexai": "embedchain.embedder.vertexai.VertexAIEmbedder",
+        "azure_openai": "embedchain.embedder.openai.OpenAIEmbedder",
+        "openai": "embedchain.embedder.openai.OpenAIEmbedder",
+    }
+    provider_to_config_class = {
+        "openai": "embedchain.config.embedder.base.BaseEmbedderConfig",
+        "azure_openai": "embedchain.config.embedder.base.BaseEmbedderConfig",
+    }
+
+    @classmethod
+    def create(cls, provider_name, config_data):
+        class_type = cls.provider_to_class.get(provider_name)
+        # Default to openai config if the provider is not in the config map
+        config_name = "openai" if provider_name not in cls.provider_to_config_class else provider_name
+        config_class_type = cls.provider_to_config_class.get(config_name)
+        if class_type:
+            embedder_class = load_class(class_type)
+            embedder_config_class = load_class(config_class_type)
+            return embedder_class(config=embedder_config_class(**config_data))
+        else:
+            raise ValueError(f"Unsupported Embedder provider: {provider_name}")
+
+
+class VectorDBFactory:
+    provider_to_class = {
+        "chroma": "embedchain.vectordb.chroma.ChromaDB",
+        "elasticsearch": "embedchain.vectordb.elasticsearch.ElasticsearchDB",
+        "opensearch": "embedchain.vectordb.opensearch.OpenSearchDB",
+        "pinecone": "embedchain.vectordb.pinecone.PineconeDB",
+        "weaviate": "embedchain.vectordb.weaviate.WeaviateDB",
+    }
+    provider_to_config_class = {
+        "chroma": "embedchain.config.vectordb.chroma.ChromaDbConfig",
+        "elasticsearch": "embedchain.config.vectordb.elasticsearch.ElasticsearchDBConfig",
+        "opensearch": "embedchain.config.vectordb.opensearch.OpenSearchDBConfig",
+        "pinecone": "embedchain.config.vectordb.pinecone.PineconeDBConfig",
+        "weaviate": "embedchain.config.vectordb.weaviate.WeaviateDBConfig",
+    }
+
+    @classmethod
+    def create(cls, provider_name, config_data):
+        class_type = cls.provider_to_class.get(provider_name)
+        config_class_type = cls.provider_to_config_class.get(provider_name)
+        if class_type:
+            embedder_class = load_class(class_type)
+            embedder_config_class = load_class(config_class_type)
+            return embedder_class(config=embedder_config_class(**config_data))
+        else:
+            raise ValueError(f"Unsupported Embedder provider: {provider_name}")

embedchain/llm/anthropic.py

@@ -7,12 +7,12 @@ from embedchain.llm.base import BaseLlm
 
 
 @register_deserializable
-class AntrophicLlm(BaseLlm):
+class AnthropicLlm(BaseLlm):
     def __init__(self, config: Optional[BaseLlmConfig] = None):
         super().__init__(config=config)
 
     def get_llm_model_answer(self, prompt):
-        return AntrophicLlm._get_answer(prompt=prompt, config=self.config)
+        return AnthropicLlm._get_answer(prompt=prompt, config=self.config)
 
     @staticmethod
     def _get_answer(prompt: str, config: BaseLlmConfig) -> str:

embedchain/llm/base.py

@@ -5,9 +5,9 @@ from langchain.memory import ConversationBufferMemory
 from langchain.schema import BaseMessage
 
 from embedchain.config import BaseLlmConfig
-from embedchain.config.llm.base_llm_config import (
-    DEFAULT_PROMPT, DEFAULT_PROMPT_WITH_HISTORY_TEMPLATE,
-    DOCS_SITE_PROMPT_TEMPLATE)
+from embedchain.config.llm.base import (DEFAULT_PROMPT,
+                                        DEFAULT_PROMPT_WITH_HISTORY_TEMPLATE,
+                                        DOCS_SITE_PROMPT_TEMPLATE)
 from embedchain.helper.json_serializable import JSONSerializable
 
 
@@ -129,8 +129,12 @@ class BaseLlm(JSONSerializable):
         :return: Search results
         :rtype: Unknown
         """
-        from langchain.tools import DuckDuckGoSearchRun
-
+        try:
+            from langchain.tools import DuckDuckGoSearchRun
+        except ImportError:
+            raise ImportError(
+                '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}")
         return search.run(input_query)
@@ -174,7 +178,7 @@ class BaseLlm(JSONSerializable):
         :type input_query: str
         :param contexts: Embeddings retrieved from the database to be used as context.
         :type contexts: List[str]
-        :param config: The `LlmConfig` instance to use as configuration options. This is used for one method call.
+        :param config: The `BaseLlmConfig` instance to use as configuration options. This is used for one method call.
         To persistently use a config, declare it during app init., defaults to None
         :type config: Optional[BaseLlmConfig], optional
         :param dry_run: A dry run does everything except send the resulting prompt to
@@ -202,7 +206,6 @@ 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}")
-
             if dry_run:
                 return prompt
 
@@ -230,7 +233,7 @@ class BaseLlm(JSONSerializable):
         :type input_query: str
         :param contexts: Embeddings retrieved from the database to be used as context.
         :type contexts: List[str]
-        :param config: The `LlmConfig` instance to use as configuration options. This is used for one method call.
+        :param config: The `BaseLlmConfig` instance to use as configuration options. This is used for one method call.
         To persistently use a config, declare it during app init., defaults to None
         :type config: Optional[BaseLlmConfig], optional
         :param dry_run: A dry run does everything except send the resulting prompt to

embedchain/llm/cohere.py

@@ -0,0 +1,43 @@
+import importlib
+import os
+from typing import Optional
+
+from langchain.llms import Cohere
+
+from embedchain.config import BaseLlmConfig
+from embedchain.helper.json_serializable import register_deserializable
+from embedchain.llm.base import BaseLlm
+
+
+@register_deserializable
+class CohereLlm(BaseLlm):
+    def __init__(self, config: Optional[BaseLlmConfig] = None):
+        if "COHERE_API_KEY" not in os.environ:
+            raise ValueError("Please set the COHERE_API_KEY environment variable.")
+
+        try:
+            importlib.import_module("cohere")
+        except ModuleNotFoundError:
+            raise ModuleNotFoundError(
+                "The required dependencies for Cohere are not installed."
+                'Please install with `pip install --upgrade "embedchain[cohere]"`'
+            ) from None
+
+        super().__init__(config=config)
+
+    def get_llm_model_answer(self, prompt):
+        if self.config.system_prompt:
+            raise ValueError("CohereLlm does not support `system_prompt`")
+        return CohereLlm._get_answer(prompt=prompt, config=self.config)
+
+    @staticmethod
+    def _get_answer(prompt: str, config: BaseLlmConfig) -> str:
+        llm = Cohere(
+            cohere_api_key=os.environ["COHERE_API_KEY"],
+            model=config.model,
+            max_tokens=config.max_tokens,
+            temperature=config.temperature,
+            p=config.top_p,
+        )
+
+        return llm(prompt)

embedchain/llm/gpt4all.py

@@ -30,11 +30,11 @@ class GPT4ALLLlm(BaseLlm):
     def _get_answer(self, prompt: str, config: BaseLlmConfig) -> Union[str, Iterable]:
         if config.model and config.model != self.config.model:
             raise RuntimeError(
-                "OpenSourceApp does not support switching models at runtime. Please create a new app instance."
+                "GPT4ALLLlm does not support switching models at runtime. Please create a new app instance."
             )
 
         if config.system_prompt:
-            raise ValueError("OpenSourceApp does not support `system_prompt`")
+            raise ValueError("GPT4ALLLlm does not support `system_prompt`")
 
         response = self.instance.generate(
             prompt=prompt,

embedchain/llm/huggingface.py

@@ -0,0 +1,51 @@
+import importlib
+import os
+from typing import Optional
+
+from langchain.llms import HuggingFaceHub
+
+from embedchain.config import BaseLlmConfig
+from embedchain.helper.json_serializable import register_deserializable
+from embedchain.llm.base import BaseLlm
+
+
+@register_deserializable
+class HuggingFaceLlm(BaseLlm):
+    def __init__(self, config: Optional[BaseLlmConfig] = None):
+        if "HUGGINGFACE_ACCESS_TOKEN" not in os.environ:
+            raise ValueError("Please set the HUGGINGFACE_ACCESS_TOKEN environment variable.")
+
+        try:
+            importlib.import_module("huggingface_hub")
+        except ModuleNotFoundError:
+            raise ModuleNotFoundError(
+                "The required dependencies for HuggingFaceHub are not installed."
+                'Please install with `pip install --upgrade "embedchain[huggingface_hub]"`'
+            ) from None
+
+        super().__init__(config=config)
+
+    def get_llm_model_answer(self, prompt):
+        if self.config.system_prompt:
+            raise ValueError("HuggingFaceLlm does not support `system_prompt`")
+        return HuggingFaceLlm._get_answer(prompt=prompt, config=self.config)
+
+    @staticmethod
+    def _get_answer(prompt: str, config: BaseLlmConfig) -> str:
+        model_kwargs = {
+            "temperature": config.temperature or 0.1,
+            "max_new_tokens": config.max_tokens,
+        }
+
+        if config.top_p > 0.0 and 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 = HuggingFaceHub(
+            huggingfacehub_api_token=os.environ["HUGGINGFACE_ACCESS_TOKEN"],
+            repo_id=config.model or "google/flan-t5-xxl",
+            model_kwargs=model_kwargs,
+        )
+
+        return llm(prompt)

embedchain/llm/jina.py

@@ -0,0 +1,43 @@
+import os
+from typing import Optional
+
+from langchain.chat_models import JinaChat
+from langchain.schema import HumanMessage, SystemMessage
+
+from embedchain.config import BaseLlmConfig
+from embedchain.helper.json_serializable import register_deserializable
+from embedchain.llm.base import BaseLlm
+
+
+@register_deserializable
+class JinaLlm(BaseLlm):
+    def __init__(self, config: Optional[BaseLlmConfig] = None):
+        if "JINACHAT_API_KEY" not in os.environ:
+            raise ValueError("Please set the JINACHAT_API_KEY environment variable.")
+        super().__init__(config=config)
+
+    def get_llm_model_answer(self, prompt):
+        response = JinaLlm._get_answer(prompt, self.config)
+        return response
+
+    @staticmethod
+    def _get_answer(prompt: str, config: BaseLlmConfig) -> str:
+        messages = []
+        if config.system_prompt:
+            messages.append(SystemMessage(content=config.system_prompt))
+        messages.append(HumanMessage(content=prompt))
+        kwargs = {
+            "temperature": config.temperature,
+            "max_tokens": config.max_tokens,
+            "model_kwargs": {},
+        }
+        if config.top_p:
+            kwargs["model_kwargs"]["top_p"] = config.top_p
+        if config.stream:
+            from langchain.callbacks.streaming_stdout import \
+                StreamingStdOutCallbackHandler
+
+            chat = JinaChat(**kwargs, streaming=config.stream, callbacks=[StreamingStdOutCallbackHandler()])
+        else:
+            chat = JinaChat(**kwargs)
+        return chat(messages).content

embedchain/llm/openai.py

@@ -13,13 +13,9 @@ class OpenAILlm(BaseLlm):
     def __init__(self, config: Optional[BaseLlmConfig] = None):
         super().__init__(config=config)
 
-    def get_llm_model_answer(self, prompt):
+    def get_llm_model_answer(self, prompt) -> str:
         response = OpenAILlm._get_answer(prompt, self.config)
-
-        if self.config.stream:
-            return response
-        else:
-            return response.content
+        return response
 
     def _get_answer(prompt: str, config: BaseLlmConfig) -> str:
         messages = []
@@ -35,10 +31,9 @@ class OpenAILlm(BaseLlm):
         if config.top_p:
             kwargs["model_kwargs"]["top_p"] = config.top_p
         if config.stream:
-            from langchain.callbacks.streaming_stdout import \
-                StreamingStdOutCallbackHandler
+            from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 
             chat = ChatOpenAI(**kwargs, streaming=config.stream, callbacks=[StreamingStdOutCallbackHandler()])
         else:
             chat = ChatOpenAI(**kwargs)
-        return chat(messages)
+        return chat(messages).content

embedchain/llm/vertex_ai.py

@@ -7,15 +7,15 @@ from embedchain.llm.base import BaseLlm
 
 
 @register_deserializable
-class VertexAiLlm(BaseLlm):
+class VertexAILlm(BaseLlm):
     def __init__(self, config: Optional[BaseLlmConfig] = None):
         super().__init__(config=config)
 
     def get_llm_model_answer(self, prompt):
-        return VertexAiLlm._get_athrophic_answer(prompt=prompt, config=self.config)
+        return VertexAILlm._get_answer(prompt=prompt, config=self.config)
 
     @staticmethod
-    def _get_athrophic_answer(prompt: str, config: BaseLlmConfig) -> str:
+    def _get_answer(prompt: str, config: BaseLlmConfig) -> str:
         from langchain.chat_models import ChatVertexAI
 
         chat = ChatVertexAI(temperature=config.temperature, model=config.model)

embedchain/loaders/docs_site_loader.py

@@ -3,7 +3,14 @@ import logging
 from urllib.parse import urljoin, urlparse
 
 import requests
-from bs4 import BeautifulSoup
+
+try:
+    from bs4 import BeautifulSoup
+except ImportError:
+    raise ImportError(
+        'DocsSite requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
+    ) from None
+
 
 from embedchain.helper.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader

embedchain/loaders/docx_file.py

@@ -1,7 +1,11 @@
 import hashlib
 
-from langchain.document_loaders import Docx2txtLoader
-
+try:
+    from langchain.document_loaders import Docx2txtLoader
+except ImportError:
+    raise ImportError(
+        'Docx file requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
+    ) from None
 from embedchain.helper.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 

embedchain/loaders/images.py

@@ -16,15 +16,15 @@ class ImagesLoader(BaseLoader):
         # load model and image preprocessing
         from embedchain.models.clip_processor import ClipProcessor
 
-        model, preprocess = ClipProcessor.load_model()
+        model = ClipProcessor.load_model()
         if os.path.isfile(image_url):
-            data = [ClipProcessor.get_image_features(image_url, model, preprocess)]
+            data = [ClipProcessor.get_image_features(image_url, model)]
         else:
             data = []
             for filename in os.listdir(image_url):
                 filepath = os.path.join(image_url, filename)
                 try:
-                    data.append(ClipProcessor.get_image_features(filepath, model, preprocess))
+                    data.append(ClipProcessor.get_image_features(filepath, model))
                 except Exception as e:
                     # Log the file that was not loaded
                     logging.exception("Failed to load the file {}. Exception {}".format(filepath, e))

embedchain/loaders/pdf_file.py

@@ -1,7 +1,11 @@
 import hashlib
 
-from langchain.document_loaders import PyPDFLoader
-
+try:
+    from langchain.document_loaders import PyPDFLoader
+except ImportError:
+    raise ImportError(
+        'PDF File requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
+    ) from None
 from embedchain.helper.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils import clean_string

embedchain/loaders/sitemap.py

@@ -2,8 +2,14 @@ import hashlib
 import logging
 
 import requests
-from bs4 import BeautifulSoup
-from bs4.builder import ParserRejectedMarkup
+
+try:
+    from bs4 import BeautifulSoup
+    from bs4.builder import ParserRejectedMarkup
+except ImportError:
+    raise ImportError(
+        'Sitemap requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
+    ) from None
 
 from embedchain.helper.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
@@ -36,9 +42,8 @@ class SitemapLoader(BaseLoader):
         for link in links:
             try:
                 each_load_data = web_page_loader.load_data(link)
-
-                if is_readable(each_load_data[0].get("content")):
-                    output.append(each_load_data)
+                if is_readable(each_load_data.get("data")[0].get("content")):
+                    output.append(each_load_data.get("data"))
                 else:
                     logging.warning(f"Page is not readable (too many invalid characters): {link}")
             except ParserRejectedMarkup as e:

embedchain/loaders/web_page.py

@@ -2,7 +2,13 @@ import hashlib
 import logging
 
 import requests
-from bs4 import BeautifulSoup
+
+try:
+    from bs4 import BeautifulSoup
+except ImportError:
+    raise ImportError(
+        'Webpage requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
+    ) from None
 
 from embedchain.helper.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
@@ -15,7 +21,25 @@ class WebPageLoader(BaseLoader):
         """Load data from a web page."""
         response = requests.get(url)
         data = response.content
-        soup = BeautifulSoup(data, "html.parser")
+        content = self._get_clean_content(data, url)
+
+        meta_data = {
+            "url": url,
+        }
+
+        doc_id = hashlib.sha256((content + url).encode()).hexdigest()
+        return {
+            "doc_id": doc_id,
+            "data": [
+                {
+                    "content": content,
+                    "meta_data": meta_data,
+                }
+            ],
+        }
+
+    def _get_clean_content(self, html, url) -> str:
+        soup = BeautifulSoup(html, "html.parser")
         original_size = len(str(soup.get_text()))
 
         tags_to_exclude = [
@@ -61,17 +85,4 @@ class WebPageLoader(BaseLoader):
                 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
             )
 
-        meta_data = {
-            "url": url,
-        }
-        content = content
-        doc_id = hashlib.sha256((content + url).encode()).hexdigest()
-        return {
-            "doc_id": doc_id,
-            "data": [
-                {
-                    "content": content,
-                    "meta_data": meta_data,
-                }
-            ],
-        }
+        return content

embedchain/loaders/xml.py

@@ -0,0 +1,30 @@
+import hashlib
+
+try:
+    from langchain.document_loaders import UnstructuredXMLLoader
+except ImportError:
+    raise ImportError(
+        'XML file requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
+    ) from None
+from embedchain.helper.json_serializable import register_deserializable
+from embedchain.loaders.base_loader import BaseLoader
+from embedchain.utils import clean_string
+
+
+@register_deserializable
+class XmlLoader(BaseLoader):
+    def load_data(self, xml_url):
+        """Load data from a XML file."""
+        loader = UnstructuredXMLLoader(xml_url)
+        data = loader.load()
+        content = data[0].page_content
+        content = clean_string(content)
+        meta_data = data[0].metadata
+        meta_data["url"] = meta_data["source"]
+        del meta_data["source"]
+        output = [{"content": content, "meta_data": meta_data}]
+        doc_id = hashlib.sha256((content + xml_url).encode()).hexdigest()
+        return {
+            "doc_id": doc_id,
+            "data": output,
+        }

embedchain/loaders/youtube_video.py

@@ -1,7 +1,11 @@
 import hashlib
 
-from langchain.document_loaders import YoutubeLoader
-
+try:
+    from langchain.document_loaders import YoutubeLoader
+except ImportError:
+    raise ImportError(
+        'YouTube video requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
+    ) from None
 from embedchain.helper.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils import clean_string

embedchain/models/clip_processor.py

@@ -1,31 +1,25 @@
 try:
-    import clip
-    import torch
     from PIL import Image, UnidentifiedImageError
+    from sentence_transformers import SentenceTransformer
 except ImportError:
-    raise ImportError(
-        "Images requires extra dependencies. Install with `pip install 'embedchain[images]' git+https://github.com/openai/CLIP.git#a1d0717`"  # noqa: E501
-    ) from None
+    raise ImportError("Images requires extra dependencies. Install with `pip install 'embedchain[images]'") from None
 
-MODEL_NAME = "ViT-B/32"
+MODEL_NAME = "clip-ViT-B-32"
 
 
 class ClipProcessor:
     @staticmethod
     def load_model():
         """Load data from a director of images."""
-        device = "cuda" if torch.cuda.is_available() else "cpu"
-
         # load model and image preprocessing
-        model, preprocess = clip.load(MODEL_NAME, device=device, jit=False)
-        return model, preprocess
+        model = SentenceTransformer(MODEL_NAME)
+        return model
 
     @staticmethod
-    def get_image_features(image_url, model, preprocess):
+    def get_image_features(image_url, model):
         """
         Applies the CLIP model to evaluate the vector representation of the supplied image
         """
-        device = "cuda" if torch.cuda.is_available() else "cpu"
         try:
             # load image
             image = Image.open(image_url)
@@ -34,27 +28,15 @@ class ClipProcessor:
         except UnidentifiedImageError:
             raise UnidentifiedImageError("The supplied file is not an image`")
 
-        # pre-process image
-        processed_image = preprocess(image).unsqueeze(0).to(device)
-        with torch.no_grad():
-            image_features = model.encode_image(processed_image)
-            image_features /= image_features.norm(dim=-1, keepdim=True)
-
-        image_features = image_features.cpu().detach().numpy().tolist()[0]
+        image_features = model.encode(image)
         meta_data = {"url": image_url}
-        return {"content": image_url, "embedding": image_features, "meta_data": meta_data}
+        return {"content": image_url, "embedding": image_features.tolist(), "meta_data": meta_data}
 
     @staticmethod
     def get_text_features(query):
         """
         Applies the CLIP model to evaluate the vector representation of the supplied text
         """
-        device = "cuda" if torch.cuda.is_available() else "cpu"
-
-        model, preprocess = ClipProcessor.load_model()
-        text = clip.tokenize(query).to(device)
-        with torch.no_grad():
-            text_features = model.encode_text(text)
-            text_features /= text_features.norm(dim=-1, keepdim=True)
-
-        return text_features.cpu().numpy().tolist()[0]
+        model = ClipProcessor.load_model()
+        text_features = model.encode(query)
+        return text_features.tolist()

embedchain/models/data_type.py

@@ -18,6 +18,7 @@ class IndirectDataType(Enum):
     PDF_FILE = "pdf_file"
     WEB_PAGE = "web_page"
     SITEMAP = "sitemap"
+    XML = "xml"
     DOCX = "docx"
     DOCS_SITE = "docs_site"
     NOTION = "notion"
@@ -40,6 +41,7 @@ class DataType(Enum):
     PDF_FILE = IndirectDataType.PDF_FILE.value
     WEB_PAGE = IndirectDataType.WEB_PAGE.value
     SITEMAP = IndirectDataType.SITEMAP.value
+    XML = IndirectDataType.XML.value
     DOCX = IndirectDataType.DOCX.value
     DOCS_SITE = IndirectDataType.DOCS_SITE.value
     NOTION = IndirectDataType.NOTION.value

embedchain/models/vector_databases.py

@@ -5,3 +5,4 @@ class VectorDatabases(Enum):
     CHROMADB = "CHROMADB"
     ELASTICSEARCH = "ELASTICSEARCH"
     OPENSEARCH = "OPENSEARCH"
+    ZILLIZ = "ZILLIZ"

embedchain/utils.py

@@ -190,6 +190,10 @@ def detect_datatype(source: Any) -> DataType:
             logging.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`.")
+            return DataType.XML
+
         # If the source is a valid file, that's not detectable as a type, an error is raised.
         # It does not fallback to text.
         raise ValueError(

embedchain/vectordb/chroma.py

@@ -37,7 +37,7 @@ class ChromaDB(BaseVectorDB):
             self.config = ChromaDbConfig()
 
         self.settings = Settings()
-        self.settings.allow_reset = self.config.allow_reset
+        self.settings.allow_reset = self.config.allow_reset if hasattr(self.config, "allow_reset") else False
         if self.config.chroma_settings:
             for key, value in self.config.chroma_settings.items():
                 if hasattr(self.settings, key):
@@ -72,6 +72,17 @@ class ChromaDB(BaseVectorDB):
         """Called during initialization"""
         return self.client
 
+    def _generate_where_clause(self, where: Dict[str, any]) -> str:
+        # If only one filter is supplied, return it as is
+        # (no need to wrap in $and based on chroma docs)
+        if len(where.keys()) == 1:
+            return where
+        where_filters = []
+        for k, v in where.items():
+            if isinstance(v, str):
+                where_filters.append({k: v})
+        return {"$and": where_filters}
+
     def _get_or_create_collection(self, name: str) -> Collection:
         """
         Get or create a named collection.
@@ -107,13 +118,14 @@ class ChromaDB(BaseVectorDB):
         if ids:
             args["ids"] = ids
         if where:
-            args["where"] = where
+            args["where"] = self._generate_where_clause(where)
         if limit:
             args["limit"] = limit
         return self.collection.get(**args)
 
     def get_advanced(self, where):
-        return self.collection.get(where=where, limit=1)
+        where_clause = self._generate_where_clause(where)
+        return self.collection.get(where=where_clause, limit=1)
 
     def add(
         self,
@@ -126,12 +138,16 @@ class ChromaDB(BaseVectorDB):
         """
         Add vectors to chroma database
 
+        :param embeddings: list of embeddings to add
+        :type embeddings: List[List[str]]
         :param documents: Documents
         :type documents: List[str]
         :param metadatas: Metadatas
         :type metadatas: List[object]
         :param ids: ids
         :type ids: List[str]
+        :param skip_embedding: Optional. If True, then the embeddings are assumed to be already generated.
+        :type skip_embedding: bool
         """
         if skip_embedding:
             self.collection.add(embeddings=embeddings, documents=documents, metadatas=metadatas, ids=ids)
@@ -158,7 +174,7 @@ class ChromaDB(BaseVectorDB):
 
     def query(self, input_query: List[str], n_results: int, where: Dict[str, any], skip_embedding: bool) -> List[str]:
         """
-        Query contents from vector data base based on vector similarity
+        Query contents from vector database based on vector similarity
 
         :param input_query: list of query string
         :type input_query: List[str]
@@ -166,6 +182,8 @@ class ChromaDB(BaseVectorDB):
         :type n_results: int
         :param where: to filter data
         :type where: Dict[str, Any]
+        :param skip_embedding: Optional. If True, then the input_query is assumed to be already embedded.
+        :type skip_embedding: bool
         :raises InvalidDimensionException: Dimensions do not match.
         :return: The content of the document that matched your query.
         :rtype: List[str]

embedchain/vectordb/elasticsearch.py

@@ -1,5 +1,5 @@
 import logging
-from typing import Any, Dict, List, Optional, Set
+from typing import Any, Dict, List, Optional
 
 try:
     from elasticsearch import Elasticsearch
@@ -74,9 +74,7 @@ class ElasticsearchDB(BaseVectorDB):
     def _get_or_create_collection(self, name):
         """Note: nothing to return here. Discuss later"""
 
-    def get(
-        self, ids: Optional[List[str]] = None, where: Optional[Dict[str, any]] = None, limit: Optional[int] = None
-    ) -> Set[str]:
+    def get(self, ids: Optional[List[str]] = None, where: Optional[Dict[str, any]] = None, limit: Optional[int] = None):
         """
         Get existing doc ids present in vector database
 
@@ -110,12 +108,16 @@ class ElasticsearchDB(BaseVectorDB):
     ) -> Any:
         """
         add data in vector database
+        :param embeddings: list of embeddings to add
+        :type embeddings: List[List[str]]
         :param documents: list of texts to add
         :type documents: List[str]
         :param metadatas: list of metadata associated with docs
         :type metadatas: List[object]
         :param ids: ids of docs
         :type ids: List[str]
+        :param skip_embedding: Optional. If True, then the input_query is assumed to be already embedded.
+        :type skip_embedding: bool
         """
 
         docs = []
@@ -143,6 +145,8 @@ class ElasticsearchDB(BaseVectorDB):
         :type n_results: int
         :param where: Optional. to filter data
         :type where: Dict[str, any]
+        :param skip_embedding: Optional. If True, then the input_query is assumed to be already embedded.
+        :type skip_embedding: bool
         :return: Database contents that are the result of the query
         :rtype: List[str]
         """

embedchain/vectordb/opensearch.py

@@ -93,7 +93,7 @@ class OpenSearchDB(BaseVectorDB):
 
         if "app_id" in where:
             app_id = where["app_id"]
-            query["query"]["bool"]["must"].append({"term": {"metadata.app_id": app_id}})
+            query["query"]["bool"]["must"].append({"term": {"metadata.app_id.keyword": app_id}})
 
         # OpenSearch syntax is different from Elasticsearch
         response = self.client.search(index=self._get_index(), body=query, _source=True, size=limit)
@@ -110,12 +110,17 @@ class OpenSearchDB(BaseVectorDB):
         return result
 
     def add(
-        self, embeddings: List[str], documents: List[str], metadatas: List[object], ids: List[str], skip_embedding: bool
+        self,
+        embeddings: List[List[str]],
+        documents: List[str],
+        metadatas: List[object],
+        ids: List[str],
+        skip_embedding: bool,
     ):
         """add data in vector database
 
         :param embeddings: list of embeddings to add
-        :type embeddings: List[str]
+        :type embeddings: List[List[str]]
         :param documents: list of texts to add
         :type documents: List[str]
         :param metadatas: list of metadata associated with docs
@@ -127,8 +132,8 @@ class OpenSearchDB(BaseVectorDB):
         """
 
         docs = []
-        # TODO(rupeshbansal, deshraj): Add support for skip embeddings here if already exists
-        embeddings = self.embedder.embedding_fn(documents)
+        if not skip_embedding:
+            embeddings = self.embedder.embedding_fn(documents)
         for id, text, metadata, embeddings in zip(ids, documents, metadatas, embeddings):
             docs.append(
                 {
@@ -162,13 +167,14 @@ class OpenSearchDB(BaseVectorDB):
             embedding_function=embeddings,
             opensearch_url=f"{self.config.opensearch_url}",
             http_auth=self.config.http_auth,
-            use_ssl=True,
+            use_ssl=hasattr(self.config, "use_ssl") and self.config.use_ssl,
+            verify_certs=hasattr(self.config, "verify_certs") and self.config.verify_certs,
         )
 
         pre_filter = {"match_all": {}}  # default
         if "app_id" in where:
             app_id = where["app_id"]
-            pre_filter = {"bool": {"must": [{"term": {"metadata.app_id": app_id}}]}}
+            pre_filter = {"bool": {"must": [{"term": {"metadata.app_id.keyword": app_id}}]}}
         docs = docsearch.similarity_search(
             input_query,
             search_type="script_scoring",

embedchain/vectordb/pinecone.py

@@ -0,0 +1,182 @@
+import os
+from typing import Dict, List, Optional
+
+try:
+    import pinecone
+except ImportError:
+    raise ImportError(
+        "Pinecone requires extra dependencies. Install with `pip install --upgrade 'embedchain[pinecone]'`"
+    ) from None
+
+from embedchain.config.vectordb.pinecone import PineconeDBConfig
+from embedchain.helper.json_serializable import register_deserializable
+from embedchain.vectordb.base import BaseVectorDB
+
+
+@register_deserializable
+class PineconeDB(BaseVectorDB):
+    """
+    Pinecone as vector database
+    """
+
+    BATCH_SIZE = 100
+
+    def __init__(
+        self,
+        config: Optional[PineconeDBConfig] = None,
+    ):
+        """Pinecone as vector database.
+
+        :param config: Pinecone database config, defaults to None
+        :type config: PineconeDBConfig, optional
+        :raises ValueError: No config provided
+        """
+        if config is None:
+            self.config = PineconeDBConfig()
+        else:
+            if not isinstance(config, PineconeDBConfig):
+                raise TypeError(
+                    "config is not a `PineconeDBConfig` instance. "
+                    "Please make sure the type is right and that you are passing an instance."
+                )
+            self.config = config
+        self.client = self._setup_pinecone_index()
+        # Call parent init here because embedder is needed
+        super().__init__(config=self.config)
+
+    def _initialize(self):
+        """
+        This method is needed because `embedder` attribute needs to be set externally before it can be initialized.
+        """
+        if not self.embedder:
+            raise ValueError("Embedder not set. Please set an embedder with `set_embedder` before initialization.")
+
+    # Loads the Pinecone index or creates it if not present.
+    def _setup_pinecone_index(self):
+        pinecone.init(
+            api_key=os.environ.get("PINECONE_API_KEY"),
+            environment=os.environ.get("PINECONE_ENV"),
+            **self.config.extra_params,
+        )
+        self.index_name = self._get_index_name()
+        indexes = pinecone.list_indexes()
+        if indexes is None or self.index_name not in indexes:
+            pinecone.create_index(
+                name=self.index_name, metric=self.config.metric, dimension=self.config.vector_dimension
+            )
+        return pinecone.Index(self.index_name)
+
+    def get(self, ids: Optional[List[str]] = None, where: Optional[Dict[str, any]] = None, limit: Optional[int] = None):
+        """
+        Get existing doc ids present in vector database
+
+        :param ids: _list of doc ids to check for existence
+        :type ids: List[str]
+        :param where: to filter data
+        :type where: Dict[str, any]
+        :return: ids
+        :rtype: Set[str]
+        """
+        existing_ids = list()
+        if ids is not None:
+            for i in range(0, len(ids), 1000):
+                result = self.client.fetch(ids=ids[i : i + 1000])
+                batch_existing_ids = list(result.get("vectors").keys())
+                existing_ids.extend(batch_existing_ids)
+        return {"ids": existing_ids}
+
+    def add(
+        self,
+        embeddings: List[List[float]],
+        documents: List[str],
+        metadatas: List[object],
+        ids: List[str],
+        skip_embedding: bool,
+    ):
+        """add data in vector database
+
+        :param documents: list of texts to add
+        :type documents: List[str]
+        :param metadatas: list of metadata associated with docs
+        :type metadatas: List[object]
+        :param ids: ids of docs
+        :type ids: List[str]
+        """
+        docs = []
+        print("Adding documents to Pinecone...")
+
+        embeddings = self.embedder.embedding_fn(documents)
+        for id, text, metadata, embedding in zip(ids, documents, metadatas, embeddings):
+            docs.append(
+                {
+                    "id": id,
+                    "values": embedding,
+                    "metadata": {**metadata, "text": text},
+                }
+            )
+
+        for i in range(0, len(docs), self.BATCH_SIZE):
+            self.client.upsert(docs[i : i + self.BATCH_SIZE])
+
+    def query(self, input_query: List[str], n_results: int, where: Dict[str, any], skip_embedding: bool) -> List[str]:
+        """
+        query contents from vector database based on vector similarity
+        :param input_query: list of query string
+        :type input_query: List[str]
+        :param n_results: no of similar documents to fetch from database
+        :type n_results: int
+        :param where: Optional. to filter data
+        :type where: Dict[str, any]
+        :param skip_embedding: Optional. if True, input_query is already embedded
+        :type skip_embedding: bool
+        :return: Database contents that are the result of the query
+        :rtype: List[str]
+        """
+        if not skip_embedding:
+            query_vector = self.embedder.embedding_fn([input_query])[0]
+        else:
+            query_vector = input_query
+        contents = self.client.query(vector=query_vector, filter=where, top_k=n_results, include_metadata=True)
+        embeddings = list(map(lambda content: content["metadata"]["text"], contents["matches"]))
+        return embeddings
+
+    def set_collection_name(self, name: str):
+        """
+        Set the name of the collection. A collection is an isolated space for vectors.
+
+        :param name: Name of the collection.
+        :type name: str
+        """
+        if not isinstance(name, str):
+            raise TypeError("Collection name must be a string")
+        self.config.collection_name = name
+
+    def count(self) -> int:
+        """
+        Count number of documents/chunks embedded in the database.
+
+        :return: number of documents
+        :rtype: int
+        """
+        return self.client.describe_index_stats()["total_vector_count"]
+
+    def _get_or_create_db(self):
+        """Called during initialization"""
+        return self.client
+
+    def reset(self):
+        """
+        Resets the database. Deletes all embeddings irreversibly.
+        """
+        # Delete all data from the database
+        pinecone.delete_index(self.index_name)
+        self._setup_pinecone_index()
+
+    # Pinecone only allows alphanumeric characters and "-" in the index name
+    def _get_index_name(self) -> str:
+        """Get the Pinecone index for a collection
+
+        :return: Pinecone index
+        :rtype: str
+        """
+        return f"{self.config.collection_name}-{self.config.vector_dimension}".lower().replace("_", "-")