[Bug fix] Fix issue of missing user directory (#975)

Co-authored-by: Deven Patel <deven298@yahoo.com>

configs/chroma.yaml

@@ -23,4 +23,3 @@ embedder:
   provider: openai
   config:
     model: 'text-embedding-ada-002'
-    deployment_name: 'test-deployment'

configs/gpt4.yaml

@@ -0,0 +1,8 @@
+llm:
+  provider: openai
+  config:
+    model: 'gpt-4'
+    temperature: 0.5
+    max_tokens: 1000
+    top_p: 1
+    stream: false

docs/components/embedding-models.mdx

@@ -55,8 +55,8 @@ import os
 from embedchain import Pipeline as App
 
 os.environ["OPENAI_API_TYPE"] = "azure"
-os.environ["OPENAI_API_BASE"] = "https://xxx.openai.azure.com/"
+os.environ["AZURE_OPENAI_ENDPOINT"] = "https://xxx.openai.azure.com/"
-os.environ["OPENAI_API_KEY"] = "xxx"
+os.environ["AZURE_OPENAI_API_KEY"] = "xxx"
 os.environ["OPENAI_API_VERSION"] = "xxx"
 
 app = App.from_config(yaml_path="config.yaml")

docs/data-sources/discourse.mdx

@@ -0,0 +1,44 @@
+---
+title: '🗨️ Discourse'
+---
+
+You can now easily load data from your community built with [Discourse](https://discourse.org/).
+
+## Example
+
+1. Setup the Discourse Loader with your community url.
+```Python
+from embedchain.loaders.discourse import DiscourseLoader
+
+dicourse_loader = DiscourseLoader(config={"domain": "https://community.openai.com"})
+```
+
+2. Once you setup the loader, you can create an app and load data using the above discourse loader
+```Python
+import os
+from embedchain.pipeline import Pipeline as App
+
+os.environ["OPENAI_API_KEY"] = "sk-xxx"
+
+app = App()
+
+app.add("openai after:2023-10-1", data_type="discourse", loader=dicourse_loader)
+
+question = "Where can I find the OpenAI API status page?"
+app.query(question)
+# Answer: You can find the OpenAI API status page at https:/status.openai.com/.
+```
+
+NOTE: The `add` function of the app will accept any executable search query to load data. Refer [Discourse API Docs](https://docs.discourse.org/#tag/Search) to learn more about search queries.
+
+3. We automatically create a chunker to chunk your discourse data, however if you wish to provide your own chunker class. Here is how you can do that:
+```Python
+
+from embedchain.chunkers.discourse import DiscourseChunker
+from embedchain.config.add_config import ChunkerConfig
+
+discourse_chunker_config = ChunkerConfig(chunk_size=1000, chunk_overlap=0, length_function=len)
+discourse_chunker = DiscourseChunker(config=discourse_chunker_config)
+
+app.add("openai", data_type='discourse', loader=dicourse_loader, chunker=discourse_chunker)
+```

docs/data-sources/overview.mdx

@@ -18,11 +18,12 @@ Embedchain comes with built-in support for various data sources. We handle the c
   <Card title="🌐📄 web page" href="/data-sources/web-page"></Card>
   <Card title="🧾 xml" href="/data-sources/xml"></Card>
   <Card title="🙌 OpenAPI" href="/data-sources/openapi"></Card>
-  <Card title="🎥📺 youtube video" href="/data-sources/youtube-video"></Card>
+  <Card title="📺 youtube video" href="/data-sources/youtube-video"></Card>
   <Card title="📬 Gmail" href="/data-sources/gmail"></Card>
   <Card title="🐘 Postgres" href="/data-sources/postgres"></Card>
   <Card title="🐬 MySQL" href="/data-sources/mysql"></Card>
   <Card title="🤖 Slack" href="/data-sources/slack"></Card>
+  <Card title="🗨️ Discourse" href="/data-sources/discourse"></Card>
 </CardGroup>
 
 <br/ >

docs/data-sources/substack.mdx

@@ -0,0 +1,16 @@
+---
+title: "📝 Substack"
+---
+
+To add any Substack data sources to your app, just add the sitemap.xml of that url as the source and set the data_type to `substack`.
+
+```python
+from embedchain import Pipeline as App
+
+app = App()
+
+# source: for any substack just add the sitemap.xml url
+app.add('https://www.lennysnewsletter.com/sitemap.xml', data_type='substack')
+app.query("Who is Brian Chesky?")
+# Answer: Brian Chesky is the co-founder and CEO of Airbnb.
+```

docs/data-sources/youtube-video.mdx

@@ -1,5 +1,5 @@
 ---
-title: '🎥📺 Youtube video'
+title: '📺 Youtube video'
 ---
 
 

docs/get-started/quickstart.mdx

@@ -83,3 +83,9 @@ app.deploy()
 # 🛠️ Adding data to your pipeline...
 # ✅ Data of type: web_page, value: https://www.forbes.com/profile/elon-musk added successfully.
 ```
+
+You can try it out yourself using the following Google Colab notebook:
+
+<a href="https://colab.research.google.com/drive/17ON1LPonnXAtLaZEebnOktstB_1cJJmh?usp=sharing">
+    <img src="https://camo.githubusercontent.com/84f0493939e0c4de4e6dbe113251b4bfb5353e57134ffd9fcab6b8714514d4d1/68747470733a2f2f636f6c61622e72657365617263682e676f6f676c652e636f6d2f6173736574732f636f6c61622d62616467652e737667" alt="Open in Colab" />
+</a>

docs/mint.json

@@ -87,7 +87,9 @@
             "data-sources/text",
             "data-sources/web-page",
             "data-sources/openapi",
-            "data-sources/youtube-video"
+            "data-sources/youtube-video",
+            "data-sources/discourse",
+            "data-sources/substack"
           ]
         },
         "data-sources/data-type-handling"

embedchain/__init__.py

@@ -6,3 +6,6 @@ from embedchain.apps.app import App  # noqa: F401
 from embedchain.client import Client  # noqa: F401
 from embedchain.pipeline import Pipeline  # noqa: F401
 from embedchain.vectordb.chroma import ChromaDB  # noqa: F401
+
+# Setup the user directory if doesn't exist already
+Client.setup_dir()

embedchain/apps/app.py

@@ -2,15 +2,13 @@ from typing import Optional
 
 import yaml
 
-from embedchain.client import Client
+from embedchain.config import AppConfig, BaseEmbedderConfig, BaseLlmConfig, ChunkerConfig
-from embedchain.config import (AppConfig, BaseEmbedderConfig, BaseLlmConfig,
-                               ChunkerConfig)
 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.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 from embedchain.llm.openai import OpenAILlm
 from embedchain.utils import validate_yaml_config
@@ -68,9 +66,6 @@ class App(EmbedChain):
         :type system_prompt: Optional[str], optional
         :raises TypeError: LLM, database or embedder or their config is not a valid class instance.
         """
-        # Setup user directory if it doesn't exist already
-        Client.setup_dir()
-
         # Type check configs
         if config and not isinstance(config, AppConfig):
             raise TypeError(
@@ -134,9 +129,6 @@ class App(EmbedChain):
         :return: An instance of the App class.
         :rtype: App
         """
-        # Setup user directory if it doesn't exist already
-        Client.setup_dir()
-
         with open(yaml_path, "r") as file:
             config_data = yaml.safe_load(file)
 

embedchain/bots/base.py

@@ -3,8 +3,8 @@ from typing import Any
 from embedchain import Pipeline as App
 from embedchain.config import AddConfig, BaseLlmConfig, PipelineConfig
 from embedchain.embedder.openai import OpenAIEmbedder
-from embedchain.helper.json_serializable import (JSONSerializable,
+from embedchain.helpers.json_serializable import (JSONSerializable,
-                                                 register_deserializable)
+                                                  register_deserializable)
 from embedchain.llm.openai import OpenAILlm
 from embedchain.vectordb.chroma import ChromaDB
 

embedchain/bots/discord.py

@@ -2,7 +2,7 @@ import argparse
 import logging
 import os
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 from .base import BaseBot
 

embedchain/bots/poe.py

@@ -3,7 +3,7 @@ import logging
 import os
 from typing import List, Optional
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 from .base import BaseBot
 

embedchain/bots/slack.py

@@ -5,7 +5,7 @@ import signal
 import sys
 
 from embedchain import App
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 from .base import BaseBot
 

embedchain/bots/whatsapp.py

@@ -4,7 +4,7 @@ import logging
 import signal
 import sys
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 from .base import BaseBot
 

embedchain/chunkers/base_chunker.py

@@ -1,6 +1,6 @@
 import hashlib
 
-from embedchain.helper.json_serializable import JSONSerializable
+from embedchain.helpers.json_serializable import JSONSerializable
 from embedchain.models.data_type import DataType
 
 

embedchain/chunkers/common_chunker.py

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

embedchain/chunkers/discourse.py

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

embedchain/chunkers/docs_site.py

@@ -4,7 +4,7 @@ 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
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/docx_file.py

@@ -4,7 +4,7 @@ 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
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/gmail.py

@@ -4,7 +4,7 @@ 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
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/json.py

@@ -4,7 +4,7 @@ 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
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/mdx.py

@@ -4,7 +4,7 @@ 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
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/mysql.py

@@ -4,7 +4,7 @@ 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
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/notion.py

@@ -4,7 +4,7 @@ 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
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/pdf_file.py

@@ -4,7 +4,7 @@ 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
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/postgres.py

@@ -4,7 +4,7 @@ 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
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/qna_pair.py

@@ -4,7 +4,7 @@ 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
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/sitemap.py

@@ -4,7 +4,7 @@ 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
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/slack.py

@@ -4,7 +4,7 @@ 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
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/substack.py

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

embedchain/chunkers/text.py

@@ -4,7 +4,7 @@ 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
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/unstructured_file.py

@@ -4,7 +4,7 @@ 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
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/web_page.py

@@ -4,7 +4,7 @@ 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
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/xml.py

@@ -4,7 +4,7 @@ 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
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/youtube_video.py

@@ -4,7 +4,7 @@ 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
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/config/add_config.py

@@ -3,7 +3,7 @@ from importlib import import_module
 from typing import Callable, Optional
 
 from embedchain.config.base_config import BaseConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/config/apps/app_config.py

@@ -1,6 +1,6 @@
 from typing import Optional
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 from .base_app_config import BaseAppConfig
 

embedchain/config/apps/base_app_config.py

@@ -2,7 +2,7 @@ import logging
 from typing import Optional
 
 from embedchain.config.base_config import BaseConfig
-from embedchain.helper.json_serializable import JSONSerializable
+from embedchain.helpers.json_serializable import JSONSerializable
 from embedchain.vectordb.base import BaseVectorDB
 
 

embedchain/config/base_config.py

@@ -1,6 +1,6 @@
 from typing import Any, Dict
 
-from embedchain.helper.json_serializable import JSONSerializable
+from embedchain.helpers.json_serializable import JSONSerializable
 
 
 class BaseConfig(JSONSerializable):

embedchain/config/embedder/base.py

@@ -1,6 +1,6 @@
 from typing import Optional
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/config/llm/base.py

@@ -1,9 +1,9 @@
 import re
 from string import Template
-from typing import Any, Dict, Optional
+from typing import Any, Dict, List, Optional
 
 from embedchain.config.base_config import BaseConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 DEFAULT_PROMPT = """
   Use the following pieces of context to answer the query at the end.
@@ -68,6 +68,7 @@ class BaseLlmConfig(BaseConfig):
         system_prompt: Optional[str] = None,
         where: Dict[str, Any] = None,
         query_type: Optional[str] = None,
+        callbacks: Optional[List] = None,
     ):
         """
         Initializes a configuration class instance for the LLM.
@@ -98,6 +99,8 @@ class BaseLlmConfig(BaseConfig):
         :type system_prompt: Optional[str], optional
         :param where: A dictionary of key-value pairs to filter the database results., defaults to None
         :type where: Dict[str, Any], optional
+        :param callbacks: Langchain callback functions to use, defaults to None
+        :type callbacks: Optional[List], optional
         :raises ValueError: If the template is not valid as template should
         contain $context and $query (and optionally $history)
         :raises ValueError: Stream is not boolean
@@ -113,6 +116,7 @@ class BaseLlmConfig(BaseConfig):
         self.deployment_name = deployment_name
         self.system_prompt = system_prompt
         self.query_type = query_type
+        self.callbacks = callbacks
 
         if type(template) is str:
             template = Template(template)

embedchain/config/pipeline_config.py

@@ -1,6 +1,6 @@
 from typing import Optional
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 from .apps.base_app_config import BaseAppConfig
 

embedchain/config/vectordb/chroma.py

@@ -1,7 +1,7 @@
 from typing import Optional
 
 from embedchain.config.vectordb.base import BaseVectorDbConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/config/vectordb/elasticsearch.py

@@ -2,7 +2,7 @@ import os
 from typing import Dict, List, Optional, Union
 
 from embedchain.config.vectordb.base import BaseVectorDbConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/config/vectordb/opensearch.py

@@ -1,7 +1,7 @@
 from typing import Dict, Optional, Tuple
 
 from embedchain.config.vectordb.base import BaseVectorDbConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/config/vectordb/pinecone.py

@@ -1,7 +1,7 @@
 from typing import Dict, Optional
 
 from embedchain.config.vectordb.base import BaseVectorDbConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/config/vectordb/qdrant.py

@@ -1,7 +1,7 @@
 from typing import Dict, Optional
 
 from embedchain.config.vectordb.base import BaseVectorDbConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/config/vectordb/weaviate.py

@@ -1,7 +1,7 @@
 from typing import Dict, Optional
 
 from embedchain.config.vectordb.base import BaseVectorDbConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/config/vectordb/zilliz.py

@@ -2,7 +2,7 @@ import os
 from typing import Optional
 
 from embedchain.config.vectordb.base import BaseVectorDbConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/data_formatter/data_formatter.py

@@ -4,7 +4,7 @@ from typing import Any, Dict
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config import AddConfig
 from embedchain.config.add_config import ChunkerConfig, LoaderConfig
-from embedchain.helper.json_serializable import JSONSerializable
+from embedchain.helpers.json_serializable import JSONSerializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.models.data_type import DataType
 
@@ -63,6 +63,9 @@ class DataFormatter(JSONSerializable):
             DataType.OPENAPI: "embedchain.loaders.openapi.OpenAPILoader",
             DataType.GMAIL: "embedchain.loaders.gmail.GmailLoader",
             DataType.NOTION: "embedchain.loaders.notion.NotionLoader",
+            DataType.SUBSTACK: "embedchain.loaders.substack.SubstackLoader",
+            DataType.GITHUB: "embedchain.loaders.github.GithubLoader",
+            DataType.YOUTUBE_CHANNEL: "embedchain.loaders.youtube_channel.YoutubeChannelLoader",
         }
 
         custom_loaders = set(
@@ -70,6 +73,7 @@ class DataFormatter(JSONSerializable):
                 DataType.POSTGRES,
                 DataType.MYSQL,
                 DataType.SLACK,
+                DataType.DISCOURSE,
             ]
         )
 
@@ -110,6 +114,10 @@ class DataFormatter(JSONSerializable):
             DataType.POSTGRES: "embedchain.chunkers.postgres.PostgresChunker",
             DataType.MYSQL: "embedchain.chunkers.mysql.MySQLChunker",
             DataType.SLACK: "embedchain.chunkers.slack.SlackChunker",
+            DataType.DISCOURSE: "embedchain.chunkers.discourse.DiscourseChunker",
+            DataType.SUBSTACK: "embedchain.chunkers.substack.SubstackChunker",
+            DataType.GITHUB: "embedchain.chunkers.common_chunker.CommonChunker",
+            DataType.YOUTUBE_CHANNEL: "embedchain.chunkers.common_chunker.CommonChunker",
         }
 
         if data_type in chunker_classes:

embedchain/embedchain.py

@@ -13,7 +13,7 @@ from embedchain.config.apps.base_app_config import BaseAppConfig
 from embedchain.constants import SQLITE_PATH
 from embedchain.data_formatter import DataFormatter
 from embedchain.embedder.base import BaseEmbedder
-from embedchain.helper.json_serializable import JSONSerializable
+from embedchain.helpers.json_serializable import JSONSerializable
 from embedchain.llm.base import BaseLlm
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.models.data_type import DataType, DirectDataType, IndirectDataType, SpecialDataType

embedchain/embedder/base.py

@@ -3,12 +3,20 @@ from typing import Any, Callable, Optional
 from embedchain.config.embedder.base import BaseEmbedderConfig
 
 try:
-    from chromadb.api.types import Documents, Embeddings
+    from chromadb.api.types import Embeddable, EmbeddingFunction, Embeddings
 except RuntimeError:
     from embedchain.utils import use_pysqlite3
 
     use_pysqlite3()
-    from chromadb.api.types import Documents, Embeddings
+    from chromadb.api.types import Embeddable, EmbeddingFunction, Embeddings
+
+
+class EmbeddingFunc(EmbeddingFunction):
+    def __init__(self, embedding_fn: Callable[[list[str]], list[str]]):
+        self.embedding_fn = embedding_fn
+
+    def __call__(self, input: Embeddable) -> Embeddings:
+        return self.embedding_fn(input)
 
 
 class BaseEmbedder:
@@ -66,7 +74,4 @@ class BaseEmbedder:
         :rtype: Callable
         """
 
-        def embed_function(texts: Documents) -> Embeddings:
+        return EmbeddingFunc(embeddings.embed_documents)
-            return embeddings.embed_documents(texts)
-
-        return embed_function

embedchain/embedder/chroma_embeddings.py

@@ -1,104 +0,0 @@
-"""
-Note that this file is copied from Chroma repository. We will remove this file once the fix in
-ChromaDB's repository.
-"""
-
-from typing import Optional
-
-from chromadb.api.types import Documents, Embeddings
-
-
-class OpenAIEmbeddingFunction:
-    def __init__(
-        self,
-        api_key: Optional[str] = None,
-        model_name: str = "text-embedding-ada-002",
-        organization_id: Optional[str] = None,
-        api_base: Optional[str] = None,
-        api_type: Optional[str] = None,
-        api_version: Optional[str] = None,
-        deployment_id: Optional[str] = None,
-    ):
-        """
-        Initialize the OpenAIEmbeddingFunction.
-        Args:
-            api_key (str, optional): Your API key for the OpenAI API. If not
-                provided, it will raise an error to provide an OpenAI API key.
-            organization_id(str, optional): The OpenAI organization ID if applicable
-            model_name (str, optional): The name of the model to use for text
-                embeddings. Defaults to "text-embedding-ada-002".
-            api_base (str, optional): The base path for the API. If not provided,
-                it will use the base path for the OpenAI API. This can be used to
-                point to a different deployment, such as an Azure deployment.
-            api_type (str, optional): The type of the API deployment. This can be
-                used to specify a different deployment, such as 'azure'. If not
-                provided, it will use the default OpenAI deployment.
-            api_version (str, optional): The api version for the API. If not provided,
-                it will use the api version for the OpenAI API. This can be used to
-                point to a different deployment, such as an Azure deployment.
-            deployment_id (str, optional): Deployment ID for Azure OpenAI.
-
-        """
-        try:
-            import openai
-        except ImportError:
-            raise ValueError("The openai python package is not installed. Please install it with `pip install openai`")
-
-        if api_key is not None:
-            openai.api_key = api_key
-        # If the api key is still not set, raise an error
-        elif openai.api_key is None:
-            raise ValueError(
-                "Please provide an OpenAI API key. You can get one at https://platform.openai.com/account/api-keys"
-            )
-
-        if api_base is not None:
-            openai.api_base = api_base
-
-        if api_version is not None:
-            openai.api_version = api_version
-
-        self._api_type = api_type
-        if api_type is not None:
-            openai.api_type = api_type
-
-        if organization_id is not None:
-            openai.organization = organization_id
-
-        self._v1 = openai.__version__.startswith("1.")
-        if self._v1:
-            if api_type == "azure":
-                self._client = openai.AzureOpenAI(
-                    api_key=api_key, api_version=api_version, azure_endpoint=api_base
-                ).embeddings
-            else:
-                self._client = openai.OpenAI(api_key=api_key, base_url=api_base).embeddings
-        else:
-            self._client = openai.Embedding
-        self._model_name = model_name
-        self._deployment_id = deployment_id
-
-    def __call__(self, input: Documents) -> Embeddings:
-        # replace newlines, which can negatively affect performance.
-        input = [t.replace("\n", " ") for t in input]
-
-        # Call the OpenAI Embedding API
-        if self._v1:
-            embeddings = self._client.create(input=input, model=self._deployment_id or self._model_name).data
-
-            # Sort resulting embeddings by index
-            sorted_embeddings = sorted(embeddings, key=lambda e: e.index)  # type: ignore
-
-            # Return just the embeddings
-            return [result.embedding for result in sorted_embeddings]
-        else:
-            if self._api_type == "azure":
-                embeddings = self._client.create(input=input, engine=self._deployment_id or self._model_name)["data"]
-            else:
-                embeddings = self._client.create(input=input, model=self._model_name)["data"]
-
-            # Sort resulting embeddings by index
-            sorted_embeddings = sorted(embeddings, key=lambda e: e["index"])  # type: ignore
-
-            # Return just the embeddings
-            return [result["embedding"] for result in sorted_embeddings]

embedchain/embedder/openai.py

@@ -1,23 +1,23 @@
 import os
 from typing import Optional
 
-from langchain.embeddings import OpenAIEmbeddings
+from chromadb.utils.embedding_functions import OpenAIEmbeddingFunction
+from langchain.embeddings import AzureOpenAIEmbeddings
 
 from embedchain.config import BaseEmbedderConfig
 from embedchain.embedder.base import BaseEmbedder
 from embedchain.models import VectorDimensions
 
-from .chroma_embeddings import OpenAIEmbeddingFunction
-
 
 class OpenAIEmbedder(BaseEmbedder):
     def __init__(self, config: Optional[BaseEmbedderConfig] = None):
         super().__init__(config=config)
+
         if self.config.model is None:
             self.config.model = "text-embedding-ada-002"
 
         if self.config.deployment_name:
-            embeddings = OpenAIEmbeddings(deployment=self.config.deployment_name)
+            embeddings = AzureOpenAIEmbeddings(deployment=self.config.deployment_name)
             embedding_fn = BaseEmbedder._langchain_default_concept(embeddings)
         else:
             if os.getenv("OPENAI_API_KEY") is None and os.getenv("OPENAI_ORGANIZATION") is None:

embedchain/helpers/callbacks.py

@@ -0,0 +1,73 @@
+import queue
+from typing import Any, Dict, List, Union
+
+from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+from langchain.schema import LLMResult
+
+STOP_ITEM = "[END]"
+"""
+This is a special item that is used to signal the end of the stream.
+"""
+
+
+class StreamingStdOutCallbackHandlerYield(StreamingStdOutCallbackHandler):
+    """
+    This is a callback handler that yields the tokens as they are generated.
+    For a usage example, see the :func:`generate` function below.
+    """
+
+    q: queue.Queue
+    """
+    The queue to write the tokens to as they are generated.
+    """
+
+    def __init__(self, q: queue.Queue) -> None:
+        """
+        Initialize the callback handler.
+        q: The queue to write the tokens to as they are generated.
+        """
+        super().__init__()
+        self.q = q
+
+    def on_llm_start(self, serialized: Dict[str, Any], prompts: List[str], **kwargs: Any) -> None:
+        """Run when LLM starts running."""
+        with self.q.mutex:
+            self.q.queue.clear()
+
+    def on_llm_new_token(self, token: str, **kwargs: Any) -> None:
+        """Run on new LLM token. Only available when streaming is enabled."""
+        self.q.put(token)
+
+    def on_llm_end(self, response: LLMResult, **kwargs: Any) -> None:
+        """Run when LLM ends running."""
+        self.q.put(STOP_ITEM)
+
+    def on_llm_error(self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any) -> None:
+        """Run when LLM errors."""
+        self.q.put("%s: %s" % (type(error).__name__, str(error)))
+        self.q.put(STOP_ITEM)
+
+
+def generate(rq: queue.Queue):
+    """
+    This is a generator that yields the items in the queue until it reaches the stop item.
+
+    Usage example:
+    ```
+    def askQuestion(callback_fn: StreamingStdOutCallbackHandlerYield):
+        llm = OpenAI(streaming=True, callbacks=[callback_fn])
+        return llm(prompt="Write a poem about a tree.")
+
+    @app.route("/", methods=["GET"])
+    def generate_output():
+        q = Queue()
+        callback_fn = StreamingStdOutCallbackHandlerYield(q)
+        threading.Thread(target=askQuestion, args=(callback_fn,)).start()
+        return Response(generate(q), mimetype="text/event-stream")
+    ```
+    """
+    while True:
+        result: str = rq.get()
+        if result == STOP_ITEM or result is None:
+            break
+        yield result

embedchain/llm/anthropic.py

@@ -3,7 +3,7 @@ import os
 from typing import Optional
 
 from embedchain.config import BaseLlmConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
 

embedchain/llm/azure_openai.py

@@ -2,7 +2,7 @@ import logging
 from typing import Optional
 
 from embedchain.config import BaseLlmConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
 

embedchain/llm/base.py

@@ -7,7 +7,7 @@ from embedchain.config import BaseLlmConfig
 from embedchain.config.llm.base import (DEFAULT_PROMPT,
                                         DEFAULT_PROMPT_WITH_HISTORY_TEMPLATE,
                                         DOCS_SITE_PROMPT_TEMPLATE)
-from embedchain.helper.json_serializable import JSONSerializable
+from embedchain.helpers.json_serializable import JSONSerializable
 from embedchain.memory.base import ECChatMemory
 from embedchain.memory.message import ChatMessage
 

embedchain/llm/cohere.py

@@ -5,7 +5,7 @@ from typing import Optional
 from langchain.llms import Cohere
 
 from embedchain.config import BaseLlmConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
 

embedchain/llm/gpt4all.py

@@ -4,7 +4,7 @@ from langchain.callbacks.stdout import StdOutCallbackHandler
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 
 from embedchain.config import BaseLlmConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
 

embedchain/llm/huggingface.py

@@ -5,7 +5,7 @@ from typing import Optional
 from langchain.llms import HuggingFaceHub
 
 from embedchain.config import BaseLlmConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
 

embedchain/llm/jina.py

@@ -5,7 +5,7 @@ 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.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
 

embedchain/llm/llama2.py

@@ -5,7 +5,7 @@ from typing import Optional
 from langchain.llms import Replicate
 
 from embedchain.config import BaseLlmConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
 

embedchain/llm/openai.py

@@ -4,7 +4,7 @@ from langchain.chat_models import ChatOpenAI
 from langchain.schema import HumanMessage, SystemMessage
 
 from embedchain.config import BaseLlmConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
 
@@ -34,7 +34,8 @@ class OpenAILlm(BaseLlm):
             from langchain.callbacks.streaming_stdout import \
                 StreamingStdOutCallbackHandler
 
-            chat = ChatOpenAI(**kwargs, streaming=config.stream, callbacks=[StreamingStdOutCallbackHandler()])
+            callbacks = config.callbacks if config.callbacks else [StreamingStdOutCallbackHandler()]
+            chat = ChatOpenAI(**kwargs, streaming=config.stream, callbacks=callbacks)
         else:
             chat = ChatOpenAI(**kwargs)
         return chat(messages).content

embedchain/llm/vertex_ai.py

@@ -3,7 +3,7 @@ import logging
 from typing import Optional
 
 from embedchain.config import BaseLlmConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
 

embedchain/loaders/base_loader.py

@@ -1,4 +1,4 @@
-from embedchain.helper.json_serializable import JSONSerializable
+from embedchain.helpers.json_serializable import JSONSerializable
 
 
 class BaseLoader(JSONSerializable):

embedchain/loaders/discourse.py

@@ -0,0 +1,77 @@
+import hashlib
+import logging
+import time
+from typing import Any, Dict, Optional
+
+import requests
+
+from embedchain.loaders.base_loader import BaseLoader
+from embedchain.utils import clean_string
+
+
+class DiscourseLoader(BaseLoader):
+    def __init__(self, config: Optional[Dict[str, Any]] = None):
+        super().__init__()
+        if not config:
+            raise ValueError(
+                "DiscourseLoader requires a config. Check the documentation for the correct format - `https://docs.embedchain.ai/data-sources/discourse`"  # noqa: E501
+            )
+
+        self.domain = config.get("domain")
+        if not self.domain:
+            raise ValueError(
+                "DiscourseLoader requires a domain. Check the documentation for the correct format - `https://docs.embedchain.ai/data-sources/discourse`"  # noqa: E501
+            )
+
+    def _check_query(self, query):
+        if not query or not isinstance(query, str):
+            raise ValueError(
+                "DiscourseLoader requires a query. Check the documentation for the correct format - `https://docs.embedchain.ai/data-sources/discourse`"  # noqa: E501
+            )
+
+    def _load_post(self, post_id):
+        post_url = f"{self.domain}posts/{post_id}.json"
+        response = requests.get(post_url)
+        try:
+            response.raise_for_status()
+        except Exception as e:
+            logging.error(f"Failed to load post {post_id}: {e}")
+            return
+        response_data = response.json()
+        post_contents = clean_string(response_data.get("raw"))
+        meta_data = {
+            "url": post_url,
+            "created_at": response_data.get("created_at", ""),
+            "username": response_data.get("username", ""),
+            "topic_slug": response_data.get("topic_slug", ""),
+            "score": response_data.get("score", ""),
+        }
+        data = {
+            "content": post_contents,
+            "meta_data": meta_data,
+        }
+        return data
+
+    def load_data(self, query):
+        self._check_query(query)
+        data = []
+        data_contents = []
+        logging.info(f"Searching data on discourse url: {self.domain}, for query: {query}")
+        search_url = f"{self.domain}search.json?q={query}"
+        response = requests.get(search_url)
+        try:
+            response.raise_for_status()
+        except Exception as e:
+            raise ValueError(f"Failed to search query {query}: {e}")
+        response_data = response.json()
+        post_ids = response_data.get("grouped_search_result").get("post_ids")
+        for id in post_ids:
+            post_data = self._load_post(id)
+            if post_data:
+                data.append(post_data)
+                data_contents.append(post_data.get("content"))
+            # Sleep for 0.4 sec, to avoid rate limiting. Check `https://meta.discourse.org/t/api-rate-limits/208405/6`
+            time.sleep(0.4)
+        doc_id = hashlib.sha256((query + ", ".join(data_contents)).encode()).hexdigest()
+        response_data = {"doc_id": doc_id, "data": data}
+        return response_data

embedchain/loaders/docs_site_loader.py

@@ -12,7 +12,7 @@ except ImportError:
     ) from None
 
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 
 

embedchain/loaders/docx_file.py

@@ -6,7 +6,7 @@ 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.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 
 

embedchain/loaders/github.py

@@ -0,0 +1,117 @@
+import concurrent.futures
+import hashlib
+import logging
+import os
+
+from tqdm import tqdm
+
+from embedchain.loaders.base_loader import BaseLoader
+from embedchain.loaders.json import JSONLoader
+from embedchain.loaders.mdx import MdxLoader
+from embedchain.utils import detect_datatype
+
+
+def _load_file_data(path):
+    data = []
+    data_content = []
+    try:
+        with open(path, "rb") as f:
+            content = f.read().decode("utf-8")
+    except Exception as e:
+        print(f"Error reading file {path}: {e}")
+        raise ValueError(f"Failed to read file {path}")
+
+    meta_data = {}
+    meta_data["url"] = path
+    data.append(
+        {
+            "content": content,
+            "meta_data": meta_data,
+        }
+    )
+    data_content.append(content)
+    doc_id = hashlib.sha256((" ".join(data_content) + path).encode()).hexdigest()
+    return {
+        "doc_id": doc_id,
+        "data": data,
+    }
+
+
+class GithubLoader(BaseLoader):
+    def load_data(self, repo_url):
+        """Load data from a git repo."""
+        try:
+            from git import Repo
+        except ImportError as e:
+            raise ValueError(
+                "GithubLoader requires extra dependencies. Install with `pip install --upgrade 'embedchain[git]'`"
+            ) from e
+
+        mdx_loader = MdxLoader()
+        json_loader = JSONLoader()
+        data = []
+        data_urls = []
+
+        def _fetch_or_clone_repo(repo_url: str, local_path: str):
+            if os.path.exists(local_path):
+                logging.info("Repository already exists. Fetching updates...")
+                repo = Repo(local_path)
+                origin = repo.remotes.origin
+                origin.fetch()
+                logging.info("Fetch completed.")
+            else:
+                logging.info("Cloning repository...")
+                Repo.clone_from(repo_url, local_path)
+                logging.info("Clone completed.")
+
+        def _load_file(file_path: str):
+            try:
+                data_type = detect_datatype(file_path).value
+            except Exception:
+                data_type = "unstructured"
+
+            if data_type == "mdx":
+                data = mdx_loader.load_data(file_path)
+            elif data_type == "json":
+                data = json_loader.load_data(file_path)
+            else:
+                data = _load_file_data(file_path)
+
+            return data.get("data", [])
+
+        def _is_file_empty(file_path):
+            return os.path.getsize(file_path) == 0
+
+        def _is_whitelisted(file_path):
+            whitelisted_extensions = ["md", "txt", "html", "json", "py", "js", "jsx", "ts", "tsx", "mdx", "rst"]
+            _, file_extension = os.path.splitext(file_path)
+            return file_extension[1:] in whitelisted_extensions
+
+        def _add_repo_files(repo_path: str):
+            with concurrent.futures.ThreadPoolExecutor(max_workers=4) as executor:
+                future_to_file = {
+                    executor.submit(_load_file, os.path.join(root, filename)): os.path.join(root, filename)
+                    for root, _, files in os.walk(repo_path)
+                    for filename in files
+                    if _is_whitelisted(os.path.join(root, filename))
+                    and not _is_file_empty(os.path.join(root, filename))  # noqa:E501
+                }
+                for future in tqdm(concurrent.futures.as_completed(future_to_file), total=len(future_to_file)):
+                    file = future_to_file[future]
+                    try:
+                        results = future.result()
+                        if results:
+                            data.extend(results)
+                            data_urls.extend([result.get("meta_data").get("url") for result in results])
+                    except Exception as e:
+                        logging.warn(f"Failed to process {file}: {e}")
+
+        source_hash = hashlib.sha256(repo_url.encode()).hexdigest()
+        repo_path = f"/tmp/{source_hash}"
+        _fetch_or_clone_repo(repo_url=repo_url, local_path=repo_path)
+        _add_repo_files(repo_path)
+        doc_id = hashlib.sha256((repo_url + ", ".join(data_urls)).encode()).hexdigest()
+        return {
+            "doc_id": doc_id,
+            "data": data,
+        }

embedchain/loaders/local_qna_pair.py

@@ -1,6 +1,6 @@
 import hashlib
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 
 

embedchain/loaders/local_text.py

@@ -1,6 +1,6 @@
 import hashlib
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 
 

embedchain/loaders/mdx.py

@@ -1,6 +1,6 @@
 import hashlib
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 
 

embedchain/loaders/notion.py

@@ -10,7 +10,7 @@ except ImportError:
     ) from None
 
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils import clean_string
 

embedchain/loaders/pdf_file.py

@@ -6,7 +6,7 @@ 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.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils import clean_string
 

embedchain/loaders/sitemap.py

@@ -3,6 +3,7 @@ import hashlib
 import logging
 
 import requests
+from tqdm import tqdm
 
 try:
     from bs4 import BeautifulSoup
@@ -12,7 +13,7 @@ except ImportError:
         'Sitemap requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
     ) from None
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.loaders.web_page import WebPageLoader
 from embedchain.utils import is_readable
@@ -52,13 +53,13 @@ class SitemapLoader(BaseLoader):
 
         with concurrent.futures.ThreadPoolExecutor() as executor:
             future_to_link = {executor.submit(load_link, link): link for link in links}
-            for future in concurrent.futures.as_completed(future_to_link):
+            for future in tqdm(concurrent.futures.as_completed(future_to_link), total=len(links), desc="Loading pages"):
                 link = future_to_link[future]
                 try:
                     data = future.result()
                     if data:
-                        output.append(data)
+                        output.extend(data)
                 except Exception as e:
                     logging.error(f"Error loading page {link}: {e}")
 
-        return {"doc_id": doc_id, "data": [data[0] for data in output if data]}
+        return {"doc_id": doc_id, "data": output}

embedchain/loaders/substack.py

@@ -0,0 +1,86 @@
+import hashlib
+import logging
+import time
+
+import requests
+
+from embedchain.helpers.json_serializable import register_deserializable
+from embedchain.loaders.base_loader import BaseLoader
+from embedchain.utils import is_readable
+
+
+@register_deserializable
+class SubstackLoader(BaseLoader):
+    """
+    This method takes a sitemap URL as input and retrieves
+    all the URLs to use the WebPageLoader to load content
+    of each page.
+    """
+
+    def load_data(self, url: str):
+        try:
+            from bs4 import BeautifulSoup
+            from bs4.builder import ParserRejectedMarkup
+        except ImportError:
+            raise ImportError(
+                'Substack requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
+            ) from None
+
+        output = []
+        response = requests.get(url)
+        response.raise_for_status()
+
+        soup = BeautifulSoup(response.text, "xml")
+        links = [link.text for link in soup.find_all("loc") if link.parent.name == "url" and "/p/" in link.text]
+        if len(links) == 0:
+            links = [link.text for link in soup.find_all("loc") if "/p/" in link.text]
+
+        doc_id = hashlib.sha256((" ".join(links) + url).encode()).hexdigest()
+
+        def serialize_response(soup: BeautifulSoup):
+            data = {}
+
+            h1_els = soup.find_all("h1")
+            if h1_els is not None and len(h1_els) > 0:
+                data["title"] = h1_els[1].text
+
+            description_el = soup.find("meta", {"name": "description"})
+            if description_el is not None:
+                data["description"] = description_el["content"]
+
+            content_el = soup.find("div", {"class": "available-content"})
+            if content_el is not None:
+                data["content"] = content_el.text
+
+            like_btn = soup.find("div", {"class": "like-button-container"})
+            if like_btn is not None:
+                no_of_likes_div = like_btn.find("div", {"class": "label"})
+                if no_of_likes_div is not None:
+                    data["no_of_likes"] = no_of_likes_div.text
+
+            return data
+
+        def load_link(link: str):
+            try:
+                each_load_data = requests.get(link)
+                each_load_data.raise_for_status()
+
+                soup = BeautifulSoup(response.text, "html.parser")
+                data = serialize_response(soup)
+                data = str(data)
+                if is_readable(data):
+                    return data
+                else:
+                    logging.warning(f"Page is not readable (too many invalid characters): {link}")
+            except ParserRejectedMarkup as e:
+                logging.error(f"Failed to parse {link}: {e}")
+            return None
+
+        for link in links:
+            data = load_link(link)
+            if data:
+                output.append({"content": data, "meta_data": {"url": link}})
+            # TODO: allow users to configure this
+            time.sleep(1.0)  # added to avoid rate limiting
+
+        return {"doc_id": doc_id, "data": output}

embedchain/loaders/unstructured_file.py

@@ -1,12 +1,6 @@
 import hashlib
 
-try:
+from embedchain.helpers.json_serializable import register_deserializable
-    from langchain.document_loaders import UnstructuredFileLoader
-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
 
@@ -15,6 +9,13 @@ from embedchain.utils import clean_string
 class UnstructuredLoader(BaseLoader):
     def load_data(self, url):
         """Load data from a Unstructured file."""
+        try:
+            from langchain.document_loaders import UnstructuredFileLoader
+        except ImportError:
+            raise ImportError(
+                'Unstructured file requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'  # noqa: E501
+            ) from None
+
         loader = UnstructuredFileLoader(url)
         data = []
         all_content = []

embedchain/loaders/web_page.py

@@ -10,22 +10,24 @@ except ImportError:
         'Webpage requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
     ) from None
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils import clean_string
 
 
 @register_deserializable
 class WebPageLoader(BaseLoader):
+    # Shared session for all instances
+    _session = requests.Session()
+
     def load_data(self, url):
-        """Load data from a web page."""
+        """Load data from a web page using a shared requests session."""
-        response = requests.get(url)
+        response = self._session.get(url, timeout=30)
+        response.raise_for_status()
         data = response.content
         content = self._get_clean_content(data, url)
 
-        meta_data = {
+        meta_data = {"url": url}
-            "url": url,
-        }
 
         doc_id = hashlib.sha256((content + url).encode()).hexdigest()
         return {
@@ -86,3 +88,7 @@ class WebPageLoader(BaseLoader):
             )
 
         return content
+
+    @classmethod
+    def close_session(cls):
+        cls._session.close()

embedchain/loaders/xml.py

@@ -6,7 +6,7 @@ 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.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils import clean_string
 

embedchain/loaders/youtube_channel.py

@@ -0,0 +1,77 @@
+import concurrent.futures
+import hashlib
+import logging
+
+from tqdm import tqdm
+
+from embedchain.loaders.base_loader import BaseLoader
+from embedchain.loaders.youtube_video import YoutubeVideoLoader
+
+
+class YoutubeChannelLoader(BaseLoader):
+    """Loader for youtube channel."""
+
+    def load_data(self, channel_name):
+        try:
+            import yt_dlp
+        except ImportError as e:
+            raise ValueError(
+                "YoutubeLoader requires extra dependencies. Install with `pip install --upgrade 'embedchain[youtube_channel]'`"  # noqa: E501
+            ) from e
+
+        data = []
+        data_urls = []
+        youtube_url = f"https://www.youtube.com/{channel_name}/videos"
+        youtube_video_loader = YoutubeVideoLoader()
+
+        def _get_yt_video_links():
+            try:
+                ydl_opts = {
+                    "quiet": True,
+                    "extract_flat": True,
+                }
+                with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+                    info_dict = ydl.extract_info(youtube_url, download=False)
+                    if "entries" in info_dict:
+                        videos = [entry["url"] for entry in info_dict["entries"]]
+                        return videos
+            except Exception:
+                logging.error(f"Failed to fetch youtube videos for channel: {channel_name}")
+                return []
+
+        def _load_yt_video(video_link):
+            try:
+                each_load_data = youtube_video_loader.load_data(video_link)
+                if each_load_data:
+                    return each_load_data.get("data")
+            except Exception as e:
+                logging.error(f"Failed to load youtube video {video_link}: {e}")
+            return None
+
+        def _add_youtube_channel():
+            video_links = _get_yt_video_links()
+            logging.info("Loading videos from youtube channel...")
+            with concurrent.futures.ThreadPoolExecutor() as executor:
+                # Submitting all tasks and storing the future object with the video link
+                future_to_video = {
+                    executor.submit(_load_yt_video, video_link): video_link for video_link in video_links
+                }
+
+                for future in tqdm(
+                    concurrent.futures.as_completed(future_to_video), total=len(video_links), desc="Processing videos"
+                ):
+                    video = future_to_video[future]
+                    try:
+                        results = future.result()
+                        if results:
+                            data.extend(results)
+                            data_urls.extend([result.get("meta_data").get("url") for result in results])
+                    except Exception as e:
+                        logging.error(f"Failed to process youtube video {video}: {e}")
+
+        _add_youtube_channel()
+        doc_id = hashlib.sha256((youtube_url + ", ".join(data_urls)).encode()).hexdigest()
+        return {
+            "doc_id": doc_id,
+            "data": data,
+        }

embedchain/loaders/youtube_video.py

@@ -6,7 +6,7 @@ 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.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils import clean_string
 
@@ -19,7 +19,7 @@ class YoutubeVideoLoader(BaseLoader):
         doc = loader.load()
         output = []
         if not len(doc):
-            raise ValueError("No data found")
+            raise ValueError(f"No data found for url: {url}")
         content = doc[0].page_content
         content = clean_string(content)
         meta_data = doc[0].metadata

embedchain/memory/message.py

@@ -1,7 +1,7 @@
 import logging
 from typing import Any, Dict, Optional
 
-from embedchain.helper.json_serializable import JSONSerializable
+from embedchain.helpers.json_serializable import JSONSerializable
 
 
 class BaseMessage(JSONSerializable):

embedchain/models/data_type.py

@@ -32,6 +32,10 @@ class IndirectDataType(Enum):
     POSTGRES = "postgres"
     MYSQL = "mysql"
     SLACK = "slack"
+    DISCOURSE = "discourse"
+    SUBSTACK = "substack"
+    GITHUB = "github"
+    YOUTUBE_CHANNEL = "youtube_channel"
 
 
 class SpecialDataType(Enum):
@@ -63,3 +67,7 @@ class DataType(Enum):
     POSTGRES = IndirectDataType.POSTGRES.value
     MYSQL = IndirectDataType.MYSQL.value
     SLACK = IndirectDataType.SLACK.value
+    DISCOURSE = IndirectDataType.DISCOURSE.value
+    SUBSTACK = IndirectDataType.SUBSTACK.value
+    GITHUB = IndirectDataType.GITHUB.value
+    YOUTUBE_CHANNEL = IndirectDataType.YOUTUBE_CHANNEL.value

embedchain/pipeline.py

@@ -15,7 +15,7 @@ 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.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 from embedchain.llm.openai import OpenAILlm
 from embedchain.telemetry.posthog import AnonymousTelemetry
@@ -24,6 +24,10 @@ from embedchain.vectordb.base import BaseVectorDB
 from embedchain.vectordb.chroma import ChromaDB
 
 
+# Setup the user directory if doesn't exist already
+Client.setup_dir()
+
+
 @register_deserializable
 class Pipeline(EmbedChain):
     """
@@ -64,9 +68,6 @@ class Pipeline(EmbedChain):
         :type auto_deploy: bool, optional
         :raises Exception: If an error occurs while creating the pipeline
         """
-        # Setup user directory if it doesn't exist already
-        Client.setup_dir()
-
         if id and yaml_path:
             raise Exception("Cannot provide both id and config. Please provide only one of them.")
 
@@ -357,9 +358,6 @@ class Pipeline(EmbedChain):
         :return: An instance of the Pipeline class.
         :rtype: Pipeline
         """
-        # Setup user directory if it doesn't exist already
-        Client.setup_dir()
-
         with open(yaml_path, "r") as file:
             config_data = yaml.safe_load(file)
 

embedchain/store/assistants.py

@@ -10,7 +10,7 @@ from typing import cast
 from openai import OpenAI
 from openai.types.beta.threads import MessageContentText, ThreadMessage
 
-from embedchain import Pipeline
+from embedchain import Client, Pipeline
 from embedchain.config import AddConfig
 from embedchain.data_formatter import DataFormatter
 from embedchain.models.data_type import DataType
@@ -19,6 +19,9 @@ from embedchain.utils import detect_datatype
 
 logging.basicConfig(level=logging.WARN)
 
+# Setup the user directory if doesn't exist already
+Client.setup_dir()
+
 
 class OpenAIAssistant:
     def __init__(

embedchain/utils.py

@@ -10,6 +10,62 @@ from schema import Optional, Or, Schema
 from embedchain.models.data_type import DataType
 
 
+def parse_content(content, type):
+    implemented = ["html.parser", "lxml", "lxml-xml", "xml", "html5lib"]
+    if type not in implemented:
+        raise ValueError(f"Parser type {type} not implemented. Please choose one of {implemented}")
+
+    from bs4 import BeautifulSoup
+
+    soup = BeautifulSoup(content, type)
+    original_size = len(str(soup.get_text()))
+
+    tags_to_exclude = [
+        "nav",
+        "aside",
+        "form",
+        "header",
+        "noscript",
+        "svg",
+        "canvas",
+        "footer",
+        "script",
+        "style",
+    ]
+    for tag in soup(tags_to_exclude):
+        tag.decompose()
+
+    ids_to_exclude = ["sidebar", "main-navigation", "menu-main-menu"]
+    for id in ids_to_exclude:
+        tags = soup.find_all(id=id)
+        for tag in tags:
+            tag.decompose()
+
+    classes_to_exclude = [
+        "elementor-location-header",
+        "navbar-header",
+        "nav",
+        "header-sidebar-wrapper",
+        "blog-sidebar-wrapper",
+        "related-posts",
+    ]
+    for class_name in classes_to_exclude:
+        tags = soup.find_all(class_=class_name)
+        for tag in tags:
+            tag.decompose()
+
+    content = soup.get_text()
+    content = clean_string(content)
+
+    cleaned_size = len(content)
+    if original_size != 0:
+        logging.info(
+            f"Cleaned page size: {cleaned_size} characters, down from {original_size} (shrunk: {original_size-cleaned_size} chars, {round((1-(cleaned_size/original_size)) * 100, 2)}%)"  # noqa:E501
+        )
+
+    return content
+
+
 def clean_string(text):
     """
     This function takes in a string and performs a series of text cleaning operations.
@@ -161,6 +217,10 @@ def detect_datatype(source: Any) -> DataType:
             logging.debug(f"Source of `{formatted_source}` detected as `csv`.")
             return DataType.CSV
 
+        if url.path.endswith(".mdx") or url.path.endswith(".md"):
+            logging.debug(f"Source of `{formatted_source}` detected as `mdx`.")
+            return DataType.MDX
+
         if url.path.endswith(".docx"):
             logging.debug(f"Source of `{formatted_source}` detected as `docx`.")
             return DataType.DOCX
@@ -200,6 +260,10 @@ def detect_datatype(source: Any) -> DataType:
             logging.debug(f"Source of `{formatted_source}` detected as `docs_site`.")
             return DataType.DOCS_SITE
 
+        if "github.com" in url.netloc:
+            logging.debug(f"Source of `{formatted_source}` detected as `github`.")
+            return DataType.GITHUB
+
         # If none of the above conditions are met, it's a general web page
         logging.debug(f"Source of `{formatted_source}` detected as `web_page`.")
         return DataType.WEB_PAGE
@@ -233,6 +297,10 @@ def detect_datatype(source: Any) -> DataType:
             logging.debug(f"Source of `{formatted_source}` detected as `xml`.")
             return DataType.XML
 
+        if source.endswith(".mdx") or source.endswith(".md"):
+            logging.debug(f"Source of `{formatted_source}` detected as `mdx`.")
+            return DataType.MDX
+
         if source.endswith(".yaml"):
             with open(source, "r") as file:
                 yaml_content = yaml.safe_load(file)

embedchain/vectordb/base.py

@@ -1,6 +1,6 @@
 from embedchain.config.vectordb.base import BaseVectorDbConfig
 from embedchain.embedder.base import BaseEmbedder
-from embedchain.helper.json_serializable import JSONSerializable
+from embedchain.helpers.json_serializable import JSONSerializable
 
 
 class BaseVectorDB(JSONSerializable):

embedchain/vectordb/chroma.py

@@ -3,9 +3,10 @@ from typing import Any, Dict, List, Optional, Tuple, Union
 
 from chromadb import Collection, QueryResult
 from langchain.docstore.document import Document
+from tqdm import tqdm
 
 from embedchain.config import ChromaDbConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.vectordb.base import BaseVectorDB
 
 try:
@@ -157,12 +158,7 @@ class ChromaDB(BaseVectorDB):
                 " Ids size: {}".format(len(documents), len(metadatas), len(ids))
             )
 
-        for i in range(0, len(documents), self.BATCH_SIZE):
+        for i in tqdm(range(0, len(documents), self.BATCH_SIZE), desc="Inserting batches in chromadb"):
-            print(
-                "Inserting batches from {} to {} in vector database.".format(
-                    i, min(len(documents), i + self.BATCH_SIZE)
-                )
-            )
             if skip_embedding:
                 self.collection.add(
                     embeddings=embeddings[i : i + self.BATCH_SIZE],

embedchain/vectordb/elasticsearch.py

@@ -10,7 +10,7 @@ except ImportError:
     ) from None
 
 from embedchain.config import ElasticsearchDBConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.vectordb.base import BaseVectorDB
 
 

embedchain/vectordb/opensearch.py

@@ -1,6 +1,9 @@
 import logging
+import time
 from typing import Dict, List, Optional, Set, Tuple, Union
 
+from tqdm import tqdm
+
 try:
     from opensearchpy import OpenSearch
     from opensearchpy.helpers import bulk
@@ -13,7 +16,7 @@ from langchain.embeddings.openai import OpenAIEmbeddings
 from langchain.vectorstores import OpenSearchVectorSearch
 
 from embedchain.config import OpenSearchDBConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.vectordb.base import BaseVectorDB
 
 
@@ -23,6 +26,8 @@ class OpenSearchDB(BaseVectorDB):
     OpenSearch as vector database
     """
 
+    BATCH_SIZE = 100
+
     def __init__(self, config: OpenSearchDBConfig):
         """OpenSearch as vector database.
 
@@ -131,19 +136,28 @@ class OpenSearchDB(BaseVectorDB):
         :type skip_embedding: bool
         """
 
-        docs = []
+        for i in tqdm(range(0, len(documents), self.BATCH_SIZE), desc="Inserting batches in opensearch"):
-        if not skip_embedding:
+            if not skip_embedding:
-            embeddings = self.embedder.embedding_fn(documents)
+                embeddings = self.embedder.embedding_fn(documents[i : i + self.BATCH_SIZE])
-        for id, text, metadata, embeddings in zip(ids, documents, metadatas, embeddings):
+
-            docs.append(
+            docs = []
-                {
+            for id, text, metadata, embeddings in zip(
-                    "_index": self._get_index(),
+                ids[i : i + self.BATCH_SIZE],
-                    "_id": id,
+                documents[i : i + self.BATCH_SIZE],
-                    "_source": {"text": text, "metadata": metadata, "embeddings": embeddings},
+                metadatas[i : i + self.BATCH_SIZE],
-                }
+                embeddings[i : i + self.BATCH_SIZE],
-            )
+            ):
-        bulk(self.client, docs)
+                docs.append(
-        self.client.indices.refresh(index=self._get_index())
+                    {
+                        "_index": self._get_index(),
+                        "_id": id,
+                        "_source": {"text": text, "metadata": metadata, "embeddings": embeddings},
+                    }
+                )
+            bulk(self.client, docs)
+            self.client.indices.refresh(index=self._get_index())
+            # Sleep for 0.1 seconds to avoid rate limiting
+            time.sleep(0.1)
 
     def query(
         self,

embedchain/vectordb/pinecone.py

@@ -9,7 +9,7 @@ except ImportError:
     ) from None
 
 from embedchain.config.vectordb.pinecone import PineconeDBConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.vectordb.base import BaseVectorDB
 
 

embedchain/vectordb/weaviate.py

@@ -10,7 +10,7 @@ except ImportError:
     ) from None
 
 from embedchain.config.vectordb.weaviate import WeaviateDBConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.vectordb.base import BaseVectorDB
 
 

embedchain/vectordb/zilliz.py

@@ -2,7 +2,7 @@ import logging
 from typing import Dict, List, Optional, Tuple, Union
 
 from embedchain.config import ZillizDBConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.vectordb.base import BaseVectorDB
 
 try:

poetry.lock

@@ -337,26 +337,6 @@ description = "The uncompromising code formatter."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "black-23.9.1-cp310-cp310-macosx_10_16_arm64.whl", hash = "sha256:d6bc09188020c9ac2555a498949401ab35bb6bf76d4e0f8ee251694664df6301"},
-    {file = "black-23.9.1-cp310-cp310-macosx_10_16_universal2.whl", hash = "sha256:13ef033794029b85dfea8032c9d3b92b42b526f1ff4bf13b2182ce4e917f5100"},
-    {file = "black-23.9.1-cp310-cp310-macosx_10_16_x86_64.whl", hash = "sha256:75a2dc41b183d4872d3a500d2b9c9016e67ed95738a3624f4751a0cb4818fe71"},
-    {file = "black-23.9.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:13a2e4a93bb8ca74a749b6974925c27219bb3df4d42fc45e948a5d9feb5122b7"},
-    {file = "black-23.9.1-cp310-cp310-win_amd64.whl", hash = "sha256:adc3e4442eef57f99b5590b245a328aad19c99552e0bdc7f0b04db6656debd80"},
-    {file = "black-23.9.1-cp311-cp311-macosx_10_16_arm64.whl", hash = "sha256:8431445bf62d2a914b541da7ab3e2b4f3bc052d2ccbf157ebad18ea126efb91f"},
-    {file = "black-23.9.1-cp311-cp311-macosx_10_16_universal2.whl", hash = "sha256:8fc1ddcf83f996247505db6b715294eba56ea9372e107fd54963c7553f2b6dfe"},
-    {file = "black-23.9.1-cp311-cp311-macosx_10_16_x86_64.whl", hash = "sha256:7d30ec46de88091e4316b17ae58bbbfc12b2de05e069030f6b747dfc649ad186"},
-    {file = "black-23.9.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:031e8c69f3d3b09e1aa471a926a1eeb0b9071f80b17689a655f7885ac9325a6f"},
-    {file = "black-23.9.1-cp311-cp311-win_amd64.whl", hash = "sha256:538efb451cd50f43aba394e9ec7ad55a37598faae3348d723b59ea8e91616300"},
-    {file = "black-23.9.1-cp38-cp38-macosx_10_16_arm64.whl", hash = "sha256:638619a559280de0c2aa4d76f504891c9860bb8fa214267358f0a20f27c12948"},
-    {file = "black-23.9.1-cp38-cp38-macosx_10_16_universal2.whl", hash = "sha256:a732b82747235e0542c03bf352c126052c0fbc458d8a239a94701175b17d4855"},
-    {file = "black-23.9.1-cp38-cp38-macosx_10_16_x86_64.whl", hash = "sha256:cf3a4d00e4cdb6734b64bf23cd4341421e8953615cba6b3670453737a72ec204"},
-    {file = "black-23.9.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cf99f3de8b3273a8317681d8194ea222f10e0133a24a7548c73ce44ea1679377"},
-    {file = "black-23.9.1-cp38-cp38-win_amd64.whl", hash = "sha256:14f04c990259576acd093871e7e9b14918eb28f1866f91968ff5524293f9c573"},
-    {file = "black-23.9.1-cp39-cp39-macosx_10_16_arm64.whl", hash = "sha256:c619f063c2d68f19b2d7270f4cf3192cb81c9ec5bc5ba02df91471d0b88c4c5c"},
-    {file = "black-23.9.1-cp39-cp39-macosx_10_16_universal2.whl", hash = "sha256:6a3b50e4b93f43b34a9d3ef00d9b6728b4a722c997c99ab09102fd5efdb88325"},
-    {file = "black-23.9.1-cp39-cp39-macosx_10_16_x86_64.whl", hash = "sha256:c46767e8df1b7beefb0899c4a95fb43058fa8500b6db144f4ff3ca38eb2f6393"},
-    {file = "black-23.9.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:50254ebfa56aa46a9fdd5d651f9637485068a1adf42270148cd101cdf56e0ad9"},
-    {file = "black-23.9.1-cp39-cp39-win_amd64.whl", hash = "sha256:403397c033adbc45c2bd41747da1f7fc7eaa44efbee256b53842470d4ac5a70f"},
     {file = "black-23.9.1-py3-none-any.whl", hash = "sha256:6ccd59584cc834b6d127628713e4b6b968e5f79572da66284532525a042549f9"},
     {file = "black-23.9.1.tar.gz", hash = "sha256:24b6b3ff5c6d9ea08a8888f6977eae858e1f340d7260cf56d70a49823236b62d"},
 ]
@@ -764,13 +744,13 @@ numpy = "*"
 
 [[package]]
 name = "chromadb"
-version = "0.4.16"
+version = "0.4.17"
 description = "Chroma."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "chromadb-0.4.16-py3-none-any.whl", hash = "sha256:a2e79d80cf25adc5658af568c66949628a8991779d832044a0fabed983b79fc3"},
+    {file = "chromadb-0.4.17-py3-none-any.whl", hash = "sha256:8cb88162bc6124441ba5a4b93819463a10e9aaafbe05a3286e876cbdc7a7e11d"},
-    {file = "chromadb-0.4.16.tar.gz", hash = "sha256:d5fb113ea02f87b969887279aec625e1a2a68bf6acedf1609f95d27670a78dc0"},
+    {file = "chromadb-0.4.17.tar.gz", hash = "sha256:120f9d364719b664d5314500f8e6097f0e0b24496bb97a429bc324f8d11f1b52"},
 ]
 
 [package.dependencies]
@@ -1691,6 +1671,37 @@ files = [
 [package.dependencies]
 wcwidth = ">=0.2.5"
 
+[[package]]
+name = "gitdb"
+version = "4.0.11"
+description = "Git Object Database"
+optional = true
+python-versions = ">=3.7"
+files = [
+    {file = "gitdb-4.0.11-py3-none-any.whl", hash = "sha256:81a3407ddd2ee8df444cbacea00e2d038e40150acfa3001696fe0dcf1d3adfa4"},
+    {file = "gitdb-4.0.11.tar.gz", hash = "sha256:bf5421126136d6d0af55bc1e7c1af1c397a34f5b7bd79e776cd3e89785c2b04b"},
+]
+
+[package.dependencies]
+smmap = ">=3.0.1,<6"
+
+[[package]]
+name = "gitpython"
+version = "3.1.40"
+description = "GitPython is a Python library used to interact with Git repositories"
+optional = true
+python-versions = ">=3.7"
+files = [
+    {file = "GitPython-3.1.40-py3-none-any.whl", hash = "sha256:cf14627d5a8049ffbf49915732e5eddbe8134c3bdb9d476e6182b676fc573f8a"},
+    {file = "GitPython-3.1.40.tar.gz", hash = "sha256:22b126e9ffb671fdd0c129796343a02bf67bf2994b35449ffc9321aa755e18a4"},
+]
+
+[package.dependencies]
+gitdb = ">=4.0.1,<5"
+
+[package.extras]
+test = ["black", "coverage[toml]", "ddt (>=1.1.1,!=1.4.3)", "mock", "mypy", "pre-commit", "pytest", "pytest-cov", "pytest-instafail", "pytest-subtests", "pytest-sugar"]
+
 [[package]]
 name = "google-api-core"
 version = "2.12.0"
@@ -2039,7 +2050,7 @@ files = [
     {file = "greenlet-3.0.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:0b72b802496cccbd9b31acea72b6f87e7771ccfd7f7927437d592e5c92ed703c"},
     {file = "greenlet-3.0.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:527cd90ba3d8d7ae7dceb06fda619895768a46a1b4e423bdb24c1969823b8362"},
     {file = "greenlet-3.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:37f60b3a42d8b5499be910d1267b24355c495064f271cfe74bf28b17b099133c"},
-    {file = "greenlet-3.0.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:1482fba7fbed96ea7842b5a7fc11d61727e8be75a077e603e8ab49d24e234383"},
+    {file = "greenlet-3.0.0-cp311-universal2-macosx_10_9_universal2.whl", hash = "sha256:c3692ecf3fe754c8c0f2c95ff19626584459eab110eaab66413b1e7425cd84e9"},
     {file = "greenlet-3.0.0-cp312-cp312-macosx_13_0_arm64.whl", hash = "sha256:be557119bf467d37a8099d91fbf11b2de5eb1fd5fc5b91598407574848dc910f"},
     {file = "greenlet-3.0.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:73b2f1922a39d5d59cc0e597987300df3396b148a9bd10b76a058a2f2772fc04"},
     {file = "greenlet-3.0.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d1e22c22f7826096ad503e9bb681b05b8c1f5a8138469b255eb91f26a76634f2"},
@@ -2049,6 +2060,7 @@ files = [
     {file = "greenlet-3.0.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:952256c2bc5b4ee8df8dfc54fc4de330970bf5d79253c863fb5e6761f00dda35"},
     {file = "greenlet-3.0.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:269d06fa0f9624455ce08ae0179430eea61085e3cf6457f05982b37fd2cefe17"},
     {file = "greenlet-3.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:9adbd8ecf097e34ada8efde9b6fec4dd2a903b1e98037adf72d12993a1c80b51"},
+    {file = "greenlet-3.0.0-cp312-universal2-macosx_10_9_universal2.whl", hash = "sha256:553d6fb2324e7f4f0899e5ad2c427a4579ed4873f42124beba763f16032959af"},
     {file = "greenlet-3.0.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c6b5ce7f40f0e2f8b88c28e6691ca6806814157ff05e794cdd161be928550f4c"},
     {file = "greenlet-3.0.0-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ecf94aa539e97a8411b5ea52fc6ccd8371be9550c4041011a091eb8b3ca1d810"},
     {file = "greenlet-3.0.0-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:80dcd3c938cbcac986c5c92779db8e8ce51a89a849c135172c88ecbdc8c056b7"},
@@ -2761,13 +2773,13 @@ adal = ["adal (>=1.0.2)"]
 
 [[package]]
 name = "langchain"
-version = "0.0.332"
+version = "0.0.336"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = ">=3.8.1,<4.0"
 files = [
-    {file = "langchain-0.0.332-py3-none-any.whl", hash = "sha256:4cbf183b8a385483907192efea2f55d34c0f0c441b0a02f41af1eeec4526677c"},
+    {file = "langchain-0.0.336-py3-none-any.whl", hash = "sha256:cbc72c170c5eb67509bf44fb833412a3d4ccf4476136447abd4f10468ef7d4c4"},
-    {file = "langchain-0.0.332.tar.gz", hash = "sha256:8356b6c0073680d66d5ee2d9e54c23c90198ee74ab2431a0256934a69a511c1f"},
+    {file = "langchain-0.0.336.tar.gz", hash = "sha256:2cbb992b0a6975948d35616386d088c2920b66023cb94eb4f4b25e097fa1374d"},
 ]
 
 [package.dependencies]
@@ -2776,7 +2788,7 @@ anyio = "<4.0"
 async-timeout = {version = ">=4.0.0,<5.0.0", markers = "python_version < \"3.11\""}
 dataclasses-json = ">=0.5.7,<0.7"
 jsonpatch = ">=1.33,<2.0"
-langsmith = ">=0.0.52,<0.1.0"
+langsmith = ">=0.0.63,<0.1.0"
 numpy = ">=1,<2"
 pydantic = ">=1,<3"
 PyYAML = ">=5.3"
@@ -2785,17 +2797,17 @@ SQLAlchemy = ">=1.4,<3"
 tenacity = ">=8.1.0,<9.0.0"
 
 [package.extras]
-all = ["O365 (>=2.0.26,<3.0.0)", "aleph-alpha-client (>=2.15.0,<3.0.0)", "amadeus (>=8.1.0)", "arxiv (>=1.4,<2.0)", "atlassian-python-api (>=3.36.0,<4.0.0)", "awadb (>=0.3.9,<0.4.0)", "azure-ai-formrecognizer (>=3.2.1,<4.0.0)", "azure-ai-vision (>=0.11.1b1,<0.12.0)", "azure-cognitiveservices-speech (>=1.28.0,<2.0.0)", "azure-cosmos (>=4.4.0b1,<5.0.0)", "azure-identity (>=1.12.0,<2.0.0)", "beautifulsoup4 (>=4,<5)", "clarifai (>=9.1.0)", "clickhouse-connect (>=0.5.14,<0.6.0)", "cohere (>=4,<5)", "deeplake (>=3.8.3,<4.0.0)", "docarray[hnswlib] (>=0.32.0,<0.33.0)", "duckduckgo-search (>=3.8.3,<4.0.0)", "elasticsearch (>=8,<9)", "esprima (>=4.0.1,<5.0.0)", "faiss-cpu (>=1,<2)", "google-api-python-client (==2.70.0)", "google-auth (>=2.18.1,<3.0.0)", "google-search-results (>=2,<3)", "gptcache (>=0.1.7)", "html2text (>=2020.1.16,<2021.0.0)", "huggingface_hub (>=0,<1)", "jinja2 (>=3,<4)", "jq (>=1.4.1,<2.0.0)", "lancedb (>=0.1,<0.2)", "langkit (>=0.0.6,<0.1.0)", "lark (>=1.1.5,<2.0.0)", "librosa (>=0.10.0.post2,<0.11.0)", "lxml (>=4.9.2,<5.0.0)", "manifest-ml (>=0.0.1,<0.0.2)", "marqo (>=1.2.4,<2.0.0)", "momento (>=1.10.1,<2.0.0)", "nebula3-python (>=3.4.0,<4.0.0)", "neo4j (>=5.8.1,<6.0.0)", "networkx (>=2.6.3,<4)", "nlpcloud (>=1,<2)", "nltk (>=3,<4)", "nomic (>=1.0.43,<2.0.0)", "openai (>=0,<1)", "openlm (>=0.0.5,<0.0.6)", "opensearch-py (>=2.0.0,<3.0.0)", "pdfminer-six (>=20221105,<20221106)", "pexpect (>=4.8.0,<5.0.0)", "pgvector (>=0.1.6,<0.2.0)", "pinecone-client (>=2,<3)", "pinecone-text (>=0.4.2,<0.5.0)", "psycopg2-binary (>=2.9.5,<3.0.0)", "pymongo (>=4.3.3,<5.0.0)", "pyowm (>=3.3.0,<4.0.0)", "pypdf (>=3.4.0,<4.0.0)", "pytesseract (>=0.3.10,<0.4.0)", "python-arango (>=7.5.9,<8.0.0)", "pyvespa (>=0.33.0,<0.34.0)", "qdrant-client (>=1.3.1,<2.0.0)", "rdflib (>=6.3.2,<7.0.0)", "redis (>=4,<5)", "requests-toolbelt (>=1.0.0,<2.0.0)", "sentence-transformers (>=2,<3)", "singlestoredb (>=0.7.1,<0.8.0)", "tensorflow-text (>=2.11.0,<3.0.0)", "tigrisdb (>=1.0.0b6,<2.0.0)", "tiktoken (>=0.3.2,<0.6.0)", "torch (>=1,<3)", "transformers (>=4,<5)", "weaviate-client (>=3,<4)", "wikipedia (>=1,<2)", "wolframalpha (==5.0.0)"]
+all = ["O365 (>=2.0.26,<3.0.0)", "aleph-alpha-client (>=2.15.0,<3.0.0)", "amadeus (>=8.1.0)", "arxiv (>=1.4,<2.0)", "atlassian-python-api (>=3.36.0,<4.0.0)", "awadb (>=0.3.9,<0.4.0)", "azure-ai-formrecognizer (>=3.2.1,<4.0.0)", "azure-ai-vision (>=0.11.1b1,<0.12.0)", "azure-cognitiveservices-speech (>=1.28.0,<2.0.0)", "azure-cosmos (>=4.4.0b1,<5.0.0)", "azure-identity (>=1.12.0,<2.0.0)", "beautifulsoup4 (>=4,<5)", "clarifai (>=9.1.0)", "clickhouse-connect (>=0.5.14,<0.6.0)", "cohere (>=4,<5)", "deeplake (>=3.8.3,<4.0.0)", "docarray[hnswlib] (>=0.32.0,<0.33.0)", "duckduckgo-search (>=3.8.3,<4.0.0)", "elasticsearch (>=8,<9)", "esprima (>=4.0.1,<5.0.0)", "faiss-cpu (>=1,<2)", "google-api-python-client (==2.70.0)", "google-auth (>=2.18.1,<3.0.0)", "google-search-results (>=2,<3)", "gptcache (>=0.1.7)", "html2text (>=2020.1.16,<2021.0.0)", "huggingface_hub (>=0,<1)", "jinja2 (>=3,<4)", "jq (>=1.4.1,<2.0.0)", "lancedb (>=0.1,<0.2)", "langkit (>=0.0.6,<0.1.0)", "lark (>=1.1.5,<2.0.0)", "librosa (>=0.10.0.post2,<0.11.0)", "lxml (>=4.9.2,<5.0.0)", "manifest-ml (>=0.0.1,<0.0.2)", "marqo (>=1.2.4,<2.0.0)", "momento (>=1.13.0,<2.0.0)", "nebula3-python (>=3.4.0,<4.0.0)", "neo4j (>=5.8.1,<6.0.0)", "networkx (>=2.6.3,<4)", "nlpcloud (>=1,<2)", "nltk (>=3,<4)", "nomic (>=1.0.43,<2.0.0)", "openai (<2)", "openlm (>=0.0.5,<0.0.6)", "opensearch-py (>=2.0.0,<3.0.0)", "pdfminer-six (>=20221105,<20221106)", "pexpect (>=4.8.0,<5.0.0)", "pgvector (>=0.1.6,<0.2.0)", "pinecone-client (>=2,<3)", "pinecone-text (>=0.4.2,<0.5.0)", "psycopg2-binary (>=2.9.5,<3.0.0)", "pymongo (>=4.3.3,<5.0.0)", "pyowm (>=3.3.0,<4.0.0)", "pypdf (>=3.4.0,<4.0.0)", "pytesseract (>=0.3.10,<0.4.0)", "python-arango (>=7.5.9,<8.0.0)", "pyvespa (>=0.33.0,<0.34.0)", "qdrant-client (>=1.3.1,<2.0.0)", "rdflib (>=6.3.2,<7.0.0)", "redis (>=4,<5)", "requests-toolbelt (>=1.0.0,<2.0.0)", "sentence-transformers (>=2,<3)", "singlestoredb (>=0.7.1,<0.8.0)", "tensorflow-text (>=2.11.0,<3.0.0)", "tigrisdb (>=1.0.0b6,<2.0.0)", "tiktoken (>=0.3.2,<0.6.0)", "torch (>=1,<3)", "transformers (>=4,<5)", "weaviate-client (>=3,<4)", "wikipedia (>=1,<2)", "wolframalpha (==5.0.0)"]
-azure = ["azure-ai-formrecognizer (>=3.2.1,<4.0.0)", "azure-ai-vision (>=0.11.1b1,<0.12.0)", "azure-cognitiveservices-speech (>=1.28.0,<2.0.0)", "azure-core (>=1.26.4,<2.0.0)", "azure-cosmos (>=4.4.0b1,<5.0.0)", "azure-identity (>=1.12.0,<2.0.0)", "azure-search-documents (==11.4.0b8)", "openai (>=0,<1)"]
+azure = ["azure-ai-formrecognizer (>=3.2.1,<4.0.0)", "azure-ai-vision (>=0.11.1b1,<0.12.0)", "azure-cognitiveservices-speech (>=1.28.0,<2.0.0)", "azure-core (>=1.26.4,<2.0.0)", "azure-cosmos (>=4.4.0b1,<5.0.0)", "azure-identity (>=1.12.0,<2.0.0)", "azure-search-documents (==11.4.0b8)", "openai (<2)"]
 clarifai = ["clarifai (>=9.1.0)"]
 cli = ["typer (>=0.9.0,<0.10.0)"]
 cohere = ["cohere (>=4,<5)"]
 docarray = ["docarray[hnswlib] (>=0.32.0,<0.33.0)"]
 embeddings = ["sentence-transformers (>=2,<3)"]
-extended-testing = ["aiosqlite (>=0.19.0,<0.20.0)", "aleph-alpha-client (>=2.15.0,<3.0.0)", "anthropic (>=0.3.11,<0.4.0)", "arxiv (>=1.4,<2.0)", "assemblyai (>=0.17.0,<0.18.0)", "atlassian-python-api (>=3.36.0,<4.0.0)", "beautifulsoup4 (>=4,<5)", "bibtexparser (>=1.4.0,<2.0.0)", "cassio (>=0.1.0,<0.2.0)", "chardet (>=5.1.0,<6.0.0)", "dashvector (>=1.0.1,<2.0.0)", "esprima (>=4.0.1,<5.0.0)", "faiss-cpu (>=1,<2)", "feedparser (>=6.0.10,<7.0.0)", "fireworks-ai (>=0.6.0,<0.7.0)", "geopandas (>=0.13.1,<0.14.0)", "gitpython (>=3.1.32,<4.0.0)", "google-cloud-documentai (>=2.20.1,<3.0.0)", "gql (>=3.4.1,<4.0.0)", "html2text (>=2020.1.16,<2021.0.0)", "jinja2 (>=3,<4)", "jq (>=1.4.1,<2.0.0)", "jsonschema (>1)", "lxml (>=4.9.2,<5.0.0)", "markdownify (>=0.11.6,<0.12.0)", "motor (>=3.3.1,<4.0.0)", "mwparserfromhell (>=0.6.4,<0.7.0)", "mwxml (>=0.3.3,<0.4.0)", "newspaper3k (>=0.2.8,<0.3.0)", "numexpr (>=2.8.6,<3.0.0)", "openai (>=0,<1)", "openapi-pydantic (>=0.3.2,<0.4.0)", "pandas (>=2.0.1,<3.0.0)", "pdfminer-six (>=20221105,<20221106)", "pgvector (>=0.1.6,<0.2.0)", "psychicapi (>=0.8.0,<0.9.0)", "py-trello (>=0.19.0,<0.20.0)", "pymupdf (>=1.22.3,<2.0.0)", "pypdf (>=3.4.0,<4.0.0)", "pypdfium2 (>=4.10.0,<5.0.0)", "pyspark (>=3.4.0,<4.0.0)", "rank-bm25 (>=0.2.2,<0.3.0)", "rapidfuzz (>=3.1.1,<4.0.0)", "rapidocr-onnxruntime (>=1.3.2,<2.0.0)", "requests-toolbelt (>=1.0.0,<2.0.0)", "rspace_client (>=2.5.0,<3.0.0)", "scikit-learn (>=1.2.2,<2.0.0)", "sqlite-vss (>=0.1.2,<0.2.0)", "streamlit (>=1.18.0,<2.0.0)", "sympy (>=1.12,<2.0)", "telethon (>=1.28.5,<2.0.0)", "timescale-vector (>=0.0.1,<0.0.2)", "tqdm (>=4.48.0)", "upstash-redis (>=0.15.0,<0.16.0)", "xata (>=1.0.0a7,<2.0.0)", "xmltodict (>=0.13.0,<0.14.0)"]
+extended-testing = ["aiosqlite (>=0.19.0,<0.20.0)", "aleph-alpha-client (>=2.15.0,<3.0.0)", "anthropic (>=0.3.11,<0.4.0)", "arxiv (>=1.4,<2.0)", "assemblyai (>=0.17.0,<0.18.0)", "atlassian-python-api (>=3.36.0,<4.0.0)", "beautifulsoup4 (>=4,<5)", "bibtexparser (>=1.4.0,<2.0.0)", "cassio (>=0.1.0,<0.2.0)", "chardet (>=5.1.0,<6.0.0)", "dashvector (>=1.0.1,<2.0.0)", "esprima (>=4.0.1,<5.0.0)", "faiss-cpu (>=1,<2)", "feedparser (>=6.0.10,<7.0.0)", "fireworks-ai (>=0.6.0,<0.7.0)", "geopandas (>=0.13.1,<0.14.0)", "gitpython (>=3.1.32,<4.0.0)", "google-cloud-documentai (>=2.20.1,<3.0.0)", "gql (>=3.4.1,<4.0.0)", "html2text (>=2020.1.16,<2021.0.0)", "javelin-sdk (>=0.1.8,<0.2.0)", "jinja2 (>=3,<4)", "jq (>=1.4.1,<2.0.0)", "jsonschema (>1)", "lxml (>=4.9.2,<5.0.0)", "markdownify (>=0.11.6,<0.12.0)", "motor (>=3.3.1,<4.0.0)", "mwparserfromhell (>=0.6.4,<0.7.0)", "mwxml (>=0.3.3,<0.4.0)", "newspaper3k (>=0.2.8,<0.3.0)", "numexpr (>=2.8.6,<3.0.0)", "openai (<2)", "openapi-pydantic (>=0.3.2,<0.4.0)", "pandas (>=2.0.1,<3.0.0)", "pdfminer-six (>=20221105,<20221106)", "pgvector (>=0.1.6,<0.2.0)", "psychicapi (>=0.8.0,<0.9.0)", "py-trello (>=0.19.0,<0.20.0)", "pymupdf (>=1.22.3,<2.0.0)", "pypdf (>=3.4.0,<4.0.0)", "pypdfium2 (>=4.10.0,<5.0.0)", "pyspark (>=3.4.0,<4.0.0)", "rank-bm25 (>=0.2.2,<0.3.0)", "rapidfuzz (>=3.1.1,<4.0.0)", "rapidocr-onnxruntime (>=1.3.2,<2.0.0)", "requests-toolbelt (>=1.0.0,<2.0.0)", "rspace_client (>=2.5.0,<3.0.0)", "scikit-learn (>=1.2.2,<2.0.0)", "sqlite-vss (>=0.1.2,<0.2.0)", "streamlit (>=1.18.0,<2.0.0)", "sympy (>=1.12,<2.0)", "telethon (>=1.28.5,<2.0.0)", "timescale-vector (>=0.0.1,<0.0.2)", "tqdm (>=4.48.0)", "upstash-redis (>=0.15.0,<0.16.0)", "xata (>=1.0.0a7,<2.0.0)", "xmltodict (>=0.13.0,<0.14.0)"]
 javascript = ["esprima (>=4.0.1,<5.0.0)"]
-llms = ["clarifai (>=9.1.0)", "cohere (>=4,<5)", "huggingface_hub (>=0,<1)", "manifest-ml (>=0.0.1,<0.0.2)", "nlpcloud (>=1,<2)", "openai (>=0,<1)", "openlm (>=0.0.5,<0.0.6)", "torch (>=1,<3)", "transformers (>=4,<5)"]
+llms = ["clarifai (>=9.1.0)", "cohere (>=4,<5)", "huggingface_hub (>=0,<1)", "manifest-ml (>=0.0.1,<0.0.2)", "nlpcloud (>=1,<2)", "openai (<2)", "openlm (>=0.0.5,<0.0.6)", "torch (>=1,<3)", "transformers (>=4,<5)"]
-openai = ["openai (>=0,<1)", "tiktoken (>=0.3.2,<0.6.0)"]
+openai = ["openai (<2)", "tiktoken (>=0.3.2,<0.6.0)"]
 qdrant = ["qdrant-client (>=1.3.1,<2.0.0)"]
 text-helpers = ["chardet (>=5.1.0,<6.0.0)"]
 
@@ -2815,18 +2827,17 @@ six = "*"
 
 [[package]]
 name = "langsmith"
-version = "0.0.62"
+version = "0.0.65"
 description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform."
 optional = false
 python-versions = ">=3.8.1,<4.0"
 files = [
-    {file = "langsmith-0.0.62-py3-none-any.whl", hash = "sha256:d50fe00eee06001ac5f705d4ff09c6b4a2f20688d57de5fbd6974a510da672fa"},
+    {file = "langsmith-0.0.65-py3-none-any.whl", hash = "sha256:92450957d1c6b6be814f9b726f3bc751deca684535fb404508ccad7aec1bb049"},
-    {file = "langsmith-0.0.62.tar.gz", hash = "sha256:196b16bea6856a83c8d95f3f709beebc6c72ea82c113021d3f62ac7cbde51bfe"},
+    {file = "langsmith-0.0.65.tar.gz", hash = "sha256:ef20e2e32392fb1a0fc5d171e8de595d868b4153a10cc119d7bf8418192c06b6"},
 ]
 
 [package.dependencies]
 pydantic = ">=1,<3"
-pytest-subtests = ">=0.11.0,<0.12.0"
 requests = ">=2,<3"
 
 [[package]]
@@ -3095,16 +3106,6 @@ files = [
     {file = "MarkupSafe-2.1.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:5bbe06f8eeafd38e5d0a4894ffec89378b6c6a625ff57e3028921f8ff59318ac"},
     {file = "MarkupSafe-2.1.3-cp311-cp311-win32.whl", hash = "sha256:dd15ff04ffd7e05ffcb7fe79f1b98041b8ea30ae9234aed2a9168b5797c3effb"},
     {file = "MarkupSafe-2.1.3-cp311-cp311-win_amd64.whl", hash = "sha256:134da1eca9ec0ae528110ccc9e48041e0828d79f24121a1a146161103c76e686"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:f698de3fd0c4e6972b92290a45bd9b1536bffe8c6759c62471efaa8acb4c37bc"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:aa57bd9cf8ae831a362185ee444e15a93ecb2e344c8e52e4d721ea3ab6ef1823"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ffcc3f7c66b5f5b7931a5aa68fc9cecc51e685ef90282f4a82f0f5e9b704ad11"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:47d4f1c5f80fc62fdd7777d0d40a2e9dda0a05883ab11374334f6c4de38adffd"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1f67c7038d560d92149c060157d623c542173016c4babc0c1913cca0564b9939"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:9aad3c1755095ce347e26488214ef77e0485a3c34a50c5a5e2471dff60b9dd9c"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:14ff806850827afd6b07a5f32bd917fb7f45b046ba40c57abdb636674a8b559c"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8f9293864fe09b8149f0cc42ce56e3f0e54de883a9de90cd427f191c346eb2e1"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-win32.whl", hash = "sha256:715d3562f79d540f251b99ebd6d8baa547118974341db04f5ad06d5ea3eb8007"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-win_amd64.whl", hash = "sha256:1b8dd8c3fd14349433c79fa8abeb573a55fc0fdd769133baac1f5e07abf54aeb"},
     {file = "MarkupSafe-2.1.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:8e254ae696c88d98da6555f5ace2279cf7cd5b3f52be2b5cf97feafe883b58d2"},
     {file = "MarkupSafe-2.1.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cb0932dc158471523c9637e807d9bfb93e06a95cbf010f1a38b98623b929ef2b"},
     {file = "MarkupSafe-2.1.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9402b03f1a1b4dc4c19845e5c749e3ab82d5078d16a2a4c2cd2df62d57bb0707"},
@@ -3380,6 +3381,17 @@ files = [
     {file = "multidict-6.0.4.tar.gz", hash = "sha256:3666906492efb76453c0e7b97f2cf459b0682e7402c0489a95484965dbc1da49"},
 ]
 
+[[package]]
+name = "mutagen"
+version = "1.47.0"
+description = "read and write audio tags for many formats"
+optional = true
+python-versions = ">=3.7"
+files = [
+    {file = "mutagen-1.47.0-py3-none-any.whl", hash = "sha256:edd96f50c5907a9539d8e5bba7245f62c9f520aef333d13392a79a4f70aca719"},
+    {file = "mutagen-1.47.0.tar.gz", hash = "sha256:719fadef0a978c31b4cf3c956261b3c58b6948b32023078a2117b1de09f0fc99"},
+]
+
 [[package]]
 name = "mypy-extensions"
 version = "1.0.0"
@@ -4639,6 +4651,47 @@ files = [
     {file = "pycparser-2.21.tar.gz", hash = "sha256:e644fdec12f7872f86c58ff790da456218b10f863970249516d60a5eaca77206"},
 ]
 
+[[package]]
+name = "pycryptodomex"
+version = "3.19.0"
+description = "Cryptographic library for Python"
+optional = true
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
+files = [
+    {file = "pycryptodomex-3.19.0-cp27-cp27m-macosx_10_9_x86_64.whl", hash = "sha256:ff64fd720def623bf64d8776f8d0deada1cc1bf1ec3c1f9d6f5bb5bd098d034f"},
+    {file = "pycryptodomex-3.19.0-cp27-cp27m-manylinux2010_i686.whl", hash = "sha256:61056a1fd3254f6f863de94c233b30dd33bc02f8c935b2000269705f1eeeffa4"},
+    {file = "pycryptodomex-3.19.0-cp27-cp27m-manylinux2010_x86_64.whl", hash = "sha256:258c4233a3fe5a6341780306a36c6fb072ef38ce676a6d41eec3e591347919e8"},
+    {file = "pycryptodomex-3.19.0-cp27-cp27m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6e45bb4635b3c4e0a00ca9df75ef6295838c85c2ac44ad882410cb631ed1eeaa"},
+    {file = "pycryptodomex-3.19.0-cp27-cp27m-musllinux_1_1_aarch64.whl", hash = "sha256:a12144d785518f6491ad334c75ccdc6ad52ea49230b4237f319dbb7cef26f464"},
+    {file = "pycryptodomex-3.19.0-cp27-cp27m-win32.whl", hash = "sha256:1789d89f61f70a4cd5483d4dfa8df7032efab1118f8b9894faae03c967707865"},
+    {file = "pycryptodomex-3.19.0-cp27-cp27m-win_amd64.whl", hash = "sha256:eb2fc0ec241bf5e5ef56c8fbec4a2634d631e4c4f616a59b567947a0f35ad83c"},
+    {file = "pycryptodomex-3.19.0-cp27-cp27mu-manylinux2010_i686.whl", hash = "sha256:c9a68a2f7bd091ccea54ad3be3e9d65eded813e6d79fdf4cc3604e26cdd6384f"},
+    {file = "pycryptodomex-3.19.0-cp27-cp27mu-manylinux2010_x86_64.whl", hash = "sha256:8df69e41f7e7015a90b94d1096ec3d8e0182e73449487306709ec27379fff761"},
+    {file = "pycryptodomex-3.19.0-cp27-cp27mu-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:917033016ecc23c8933205585a0ab73e20020fdf671b7cd1be788a5c4039840b"},
+    {file = "pycryptodomex-3.19.0-cp27-cp27mu-musllinux_1_1_aarch64.whl", hash = "sha256:e8e5ecbd4da4157889fce8ba49da74764dd86c891410bfd6b24969fa46edda51"},
+    {file = "pycryptodomex-3.19.0-cp35-abi3-macosx_10_9_universal2.whl", hash = "sha256:a77b79852175064c822b047fee7cf5a1f434f06ad075cc9986aa1c19a0c53eb0"},
+    {file = "pycryptodomex-3.19.0-cp35-abi3-macosx_10_9_x86_64.whl", hash = "sha256:5b883e1439ab63af976656446fb4839d566bb096f15fc3c06b5a99cde4927188"},
+    {file = "pycryptodomex-3.19.0-cp35-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a3866d68e2fc345162b1b9b83ef80686acfe5cec0d134337f3b03950a0a8bf56"},
+    {file = "pycryptodomex-3.19.0-cp35-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c74eb1f73f788facece7979ce91594dc177e1a9b5d5e3e64697dd58299e5cb4d"},
+    {file = "pycryptodomex-3.19.0-cp35-abi3-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7cb51096a6a8d400724104db8a7e4f2206041a1f23e58924aa3d8d96bcb48338"},
+    {file = "pycryptodomex-3.19.0-cp35-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:a588a1cb7781da9d5e1c84affd98c32aff9c89771eac8eaa659d2760666f7139"},
+    {file = "pycryptodomex-3.19.0-cp35-abi3-musllinux_1_1_i686.whl", hash = "sha256:d4dd3b381ff5a5907a3eb98f5f6d32c64d319a840278ceea1dcfcc65063856f3"},
+    {file = "pycryptodomex-3.19.0-cp35-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:263de9a96d2fcbc9f5bd3a279f14ea0d5f072adb68ebd324987576ec25da084d"},
+    {file = "pycryptodomex-3.19.0-cp35-abi3-win32.whl", hash = "sha256:67c8eb79ab33d0fbcb56842992298ddb56eb6505a72369c20f60bc1d2b6fb002"},
+    {file = "pycryptodomex-3.19.0-cp35-abi3-win_amd64.whl", hash = "sha256:09c9401dc06fb3d94cb1ec23b4ea067a25d1f4c6b7b118ff5631d0b5daaab3cc"},
+    {file = "pycryptodomex-3.19.0-pp27-pypy_73-manylinux2010_x86_64.whl", hash = "sha256:edbe083c299835de7e02c8aa0885cb904a75087d35e7bab75ebe5ed336e8c3e2"},
+    {file = "pycryptodomex-3.19.0-pp27-pypy_73-win32.whl", hash = "sha256:136b284e9246b4ccf4f752d435c80f2c44fc2321c198505de1d43a95a3453b3c"},
+    {file = "pycryptodomex-3.19.0-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:5d73e9fa3fe830e7b6b42afc49d8329b07a049a47d12e0ef9225f2fd220f19b2"},
+    {file = "pycryptodomex-3.19.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0b2f1982c5bc311f0aab8c293524b861b485d76f7c9ab2c3ac9a25b6f7655975"},
+    {file = "pycryptodomex-3.19.0-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bfb040b5dda1dff1e197d2ef71927bd6b8bfcb9793bc4dfe0bb6df1e691eaacb"},
+    {file = "pycryptodomex-3.19.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:800a2b05cfb83654df80266692f7092eeefe2a314fa7901dcefab255934faeec"},
+    {file = "pycryptodomex-3.19.0-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:c01678aee8ac0c1a461cbc38ad496f953f9efcb1fa19f5637cbeba7544792a53"},
+    {file = "pycryptodomex-3.19.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2126bc54beccbede6eade00e647106b4f4c21e5201d2b0a73e9e816a01c50905"},
+    {file = "pycryptodomex-3.19.0-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b801216c48c0886742abf286a9a6b117e248ca144d8ceec1f931ce2dd0c9cb40"},
+    {file = "pycryptodomex-3.19.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:50cb18d4dd87571006fd2447ccec85e6cec0136632a550aa29226ba075c80644"},
+    {file = "pycryptodomex-3.19.0.tar.gz", hash = "sha256:af83a554b3f077564229865c45af0791be008ac6469ef0098152139e6bd4b5b6"},
+]
+
 [[package]]
 name = "pydantic"
 version = "2.4.2"
@@ -5008,21 +5061,6 @@ pytest = ">=5.0"
 [package.extras]
 dev = ["pre-commit", "pytest-asyncio", "tox"]
 
-[[package]]
-name = "pytest-subtests"
-version = "0.11.0"
-description = "unittest subTest() support and subtests fixture"
-optional = false
-python-versions = ">=3.7"
-files = [
-    {file = "pytest-subtests-0.11.0.tar.gz", hash = "sha256:51865c88457545f51fb72011942f0a3c6901ee9e24cbfb6d1b9dc1348bafbe37"},
-    {file = "pytest_subtests-0.11.0-py3-none-any.whl", hash = "sha256:453389984952eec85ab0ce0c4f026337153df79587048271c7fd0f49119c07e4"},
-]
-
-[package.dependencies]
-attrs = ">=19.2.0"
-pytest = ">=7.0"
-
 [[package]]
 name = "python-dateutil"
 version = "2.8.2"
@@ -5177,7 +5215,6 @@ files = [
     {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:69b023b2b4daa7548bcfbd4aa3da05b3a74b772db9e23b982788168117739938"},
     {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:81e0b275a9ecc9c0c0c07b4b90ba548307583c125f54d5b6946cfee6360c733d"},
     {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba336e390cd8e4d1739f42dfe9bb83a3cc2e80f567d8805e11b46f4a943f5515"},
-    {file = "PyYAML-6.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:326c013efe8048858a6d312ddd31d56e468118ad4cdeda36c719bf5bb6192290"},
     {file = "PyYAML-6.0.1-cp310-cp310-win32.whl", hash = "sha256:bd4af7373a854424dabd882decdc5579653d7868b8fb26dc7d0e99f823aa5924"},
     {file = "PyYAML-6.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:fd1592b3fdf65fff2ad0004b5e363300ef59ced41c2e6b3a99d4089fa8c5435d"},
     {file = "PyYAML-6.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6965a7bc3cf88e5a1c3bd2e0b5c22f8d677dc88a455344035f03399034eb3007"},
@@ -5185,15 +5222,8 @@ files = [
     {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42f8152b8dbc4fe7d96729ec2b99c7097d656dc1213a3229ca5383f973a5ed6d"},
     {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:062582fca9fabdd2c8b54a3ef1c978d786e0f6b3a1510e0ac93ef59e0ddae2bc"},
     {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2b04aac4d386b172d5b9692e2d2da8de7bfb6c387fa4f801fbf6fb2e6ba4673"},
-    {file = "PyYAML-6.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e7d73685e87afe9f3b36c799222440d6cf362062f78be1013661b00c5c6f678b"},
     {file = "PyYAML-6.0.1-cp311-cp311-win32.whl", hash = "sha256:1635fd110e8d85d55237ab316b5b011de701ea0f29d07611174a1b42f1444741"},
     {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
-    {file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"},
-    {file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"},
-    {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"},
-    {file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"},
-    {file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"},
-    {file = "PyYAML-6.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:0d3304d8c0adc42be59c5f8a4d9e3d7379e6955ad754aa9d6ab7a398b59dd1df"},
     {file = "PyYAML-6.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:50550eb667afee136e9a77d6dc71ae76a44df8b3e51e41b77f6de2932bfe0f47"},
     {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1fe35611261b29bd1de0070f0b2f47cb6ff71fa6595c077e42bd0c419fa27b98"},
     {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:704219a11b772aea0d8ecd7058d0082713c3562b4e271b849ad7dc4a5c90c13c"},
@@ -5210,7 +5240,6 @@ files = [
     {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0cd17c15d3bb3fa06978b4e8958dcdc6e0174ccea823003a106c7d4d7899ac5"},
     {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28c119d996beec18c05208a8bd78cbe4007878c6dd15091efb73a30e90539696"},
     {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7e07cbde391ba96ab58e532ff4803f79c4129397514e1413a7dc761ccd755735"},
-    {file = "PyYAML-6.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:49a183be227561de579b4a36efbb21b3eab9651dd81b1858589f796549873dd6"},
     {file = "PyYAML-6.0.1-cp38-cp38-win32.whl", hash = "sha256:184c5108a2aca3c5b3d3bf9395d50893a7ab82a38004c8f61c258d4428e80206"},
     {file = "PyYAML-6.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:1e2722cc9fbb45d9b87631ac70924c11d3a401b2d7f410cc0e3bbf249f2dca62"},
     {file = "PyYAML-6.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9eb6caa9a297fc2c2fb8862bc5370d0303ddba53ba97e71f08023b6cd73d16a8"},
@@ -5218,7 +5247,6 @@ files = [
     {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5773183b6446b2c99bb77e77595dd486303b4faab2b086e7b17bc6bef28865f6"},
     {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b786eecbdf8499b9ca1d697215862083bd6d2a99965554781d0d8d1ad31e13a0"},
     {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc1bf2925a1ecd43da378f4db9e4f799775d6367bdb94671027b73b393a7c42c"},
-    {file = "PyYAML-6.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:04ac92ad1925b2cff1db0cfebffb6ffc43457495c9b3c39d3fcae417d7125dc5"},
     {file = "PyYAML-6.0.1-cp39-cp39-win32.whl", hash = "sha256:faca3bdcf85b2fc05d06ff3fbc1f83e1391b3e724afa3feba7d13eeab355484c"},
     {file = "PyYAML-6.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:510c9deebc5c0225e8c96813043e62b680ba2f9c50a08d3724c7f28a747d1486"},
     {file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"},
@@ -5746,11 +5774,6 @@ files = [
     {file = "scikit_learn-1.3.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f66eddfda9d45dd6cadcd706b65669ce1df84b8549875691b1f403730bdef217"},
     {file = "scikit_learn-1.3.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c6448c37741145b241eeac617028ba6ec2119e1339b1385c9720dae31367f2be"},
     {file = "scikit_learn-1.3.1-cp311-cp311-win_amd64.whl", hash = "sha256:c413c2c850241998168bbb3bd1bb59ff03b1195a53864f0b80ab092071af6028"},
-    {file = "scikit_learn-1.3.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:ef540e09873e31569bc8b02c8a9f745ee04d8e1263255a15c9969f6f5caa627f"},
-    {file = "scikit_learn-1.3.1-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:9147a3a4df4d401e618713880be023e36109c85d8569b3bf5377e6cd3fecdeac"},
-    {file = "scikit_learn-1.3.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d2cd3634695ad192bf71645702b3df498bd1e246fc2d529effdb45a06ab028b4"},
-    {file = "scikit_learn-1.3.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0c275a06c5190c5ce00af0acbb61c06374087949f643ef32d355ece12c4db043"},
-    {file = "scikit_learn-1.3.1-cp312-cp312-win_amd64.whl", hash = "sha256:0e1aa8f206d0de814b81b41d60c1ce31f7f2c7354597af38fae46d9c47c45122"},
     {file = "scikit_learn-1.3.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:52b77cc08bd555969ec5150788ed50276f5ef83abb72e6f469c5b91a0009bbca"},
     {file = "scikit_learn-1.3.1-cp38-cp38-macosx_12_0_arm64.whl", hash = "sha256:a683394bc3f80b7c312c27f9b14ebea7766b1f0a34faf1a2e9158d80e860ec26"},
     {file = "scikit_learn-1.3.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a15d964d9eb181c79c190d3dbc2fff7338786bf017e9039571418a1d53dab236"},
@@ -6014,6 +6037,17 @@ files = [
 optional = ["SQLAlchemy (>=1.4,<3)", "aiodns (>1.0)", "aiohttp (>=3.7.3,<4)", "boto3 (<=2)", "websocket-client (>=1,<2)", "websockets (>=10,<11)"]
 testing = ["Flask (>=1,<2)", "Flask-Sockets (>=0.2,<1)", "Jinja2 (==3.0.3)", "Werkzeug (<2)", "black (==22.8.0)", "boto3 (<=2)", "click (==8.0.4)", "databases (>=0.5)", "flake8 (>=5,<6)", "itsdangerous (==1.1.0)", "moto (>=3,<4)", "psutil (>=5,<6)", "pytest (>=6.2.5,<7)", "pytest-asyncio (<1)", "pytest-cov (>=2,<3)"]
 
+[[package]]
+name = "smmap"
+version = "5.0.1"
+description = "A pure Python implementation of a sliding window memory map manager"
+optional = true
+python-versions = ">=3.7"
+files = [
+    {file = "smmap-5.0.1-py3-none-any.whl", hash = "sha256:e6d8668fa5f93e706934a62d7b4db19c8d9eb8cf2adbb75ef1b675aa332b69da"},
+    {file = "smmap-5.0.1.tar.gz", hash = "sha256:dceeb6c0028fdb6734471eb07c0cd2aae706ccaecab45965ee83f11c8d3b1f62"},
+]
+
 [[package]]
 name = "sniffio"
 version = "1.3.0"
@@ -6054,54 +6088,13 @@ description = "Database Abstraction Library"
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "SQLAlchemy-2.0.22-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:f146c61ae128ab43ea3a0955de1af7e1633942c2b2b4985ac51cc292daf33222"},
-    {file = "SQLAlchemy-2.0.22-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:875de9414393e778b655a3d97d60465eb3fae7c919e88b70cc10b40b9f56042d"},
-    {file = "SQLAlchemy-2.0.22-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:13790cb42f917c45c9c850b39b9941539ca8ee7917dacf099cc0b569f3d40da7"},
-    {file = "SQLAlchemy-2.0.22-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e04ab55cf49daf1aeb8c622c54d23fa4bec91cb051a43cc24351ba97e1dd09f5"},
-    {file = "SQLAlchemy-2.0.22-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:a42c9fa3abcda0dcfad053e49c4f752eef71ecd8c155221e18b99d4224621176"},
-    {file = "SQLAlchemy-2.0.22-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:14cd3bcbb853379fef2cd01e7c64a5d6f1d005406d877ed9509afb7a05ff40a5"},
-    {file = "SQLAlchemy-2.0.22-cp310-cp310-win32.whl", hash = "sha256:d143c5a9dada696bcfdb96ba2de4a47d5a89168e71d05a076e88a01386872f97"},
-    {file = "SQLAlchemy-2.0.22-cp310-cp310-win_amd64.whl", hash = "sha256:ccd87c25e4c8559e1b918d46b4fa90b37f459c9b4566f1dfbce0eb8122571547"},
     {file = "SQLAlchemy-2.0.22-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:4f6ff392b27a743c1ad346d215655503cec64405d3b694228b3454878bf21590"},
     {file = "SQLAlchemy-2.0.22-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f776c2c30f0e5f4db45c3ee11a5f2a8d9de68e81eb73ec4237de1e32e04ae81c"},
-    {file = "SQLAlchemy-2.0.22-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c8f1792d20d2f4e875ce7a113f43c3561ad12b34ff796b84002a256f37ce9437"},
-    {file = "SQLAlchemy-2.0.22-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d80eeb5189d7d4b1af519fc3f148fe7521b9dfce8f4d6a0820e8f5769b005051"},
-    {file = "SQLAlchemy-2.0.22-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:69fd9e41cf9368afa034e1c81f3570afb96f30fcd2eb1ef29cb4d9371c6eece2"},
-    {file = "SQLAlchemy-2.0.22-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:54bcceaf4eebef07dadfde424f5c26b491e4a64e61761dea9459103ecd6ccc95"},
-    {file = "SQLAlchemy-2.0.22-cp311-cp311-win32.whl", hash = "sha256:7ee7ccf47aa503033b6afd57efbac6b9e05180f492aeed9fcf70752556f95624"},
-    {file = "SQLAlchemy-2.0.22-cp311-cp311-win_amd64.whl", hash = "sha256:b560f075c151900587ade06706b0c51d04b3277c111151997ea0813455378ae0"},
     {file = "SQLAlchemy-2.0.22-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:2c9bac865ee06d27a1533471405ad240a6f5d83195eca481f9fc4a71d8b87df8"},
     {file = "SQLAlchemy-2.0.22-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:625b72d77ac8ac23da3b1622e2da88c4aedaee14df47c8432bf8f6495e655de2"},
-    {file = "SQLAlchemy-2.0.22-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b39a6e21110204a8c08d40ff56a73ba542ec60bab701c36ce721e7990df49fb9"},
-    {file = "SQLAlchemy-2.0.22-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:53a766cb0b468223cafdf63e2d37f14a4757476157927b09300c8c5832d88560"},
-    {file = "SQLAlchemy-2.0.22-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:0e1ce8ebd2e040357dde01a3fb7d30d9b5736b3e54a94002641dfd0aa12ae6ce"},
-    {file = "SQLAlchemy-2.0.22-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:505f503763a767556fa4deae5194b2be056b64ecca72ac65224381a0acab7ebe"},
-    {file = "SQLAlchemy-2.0.22-cp312-cp312-win32.whl", hash = "sha256:154a32f3c7b00de3d090bc60ec8006a78149e221f1182e3edcf0376016be9396"},
-    {file = "SQLAlchemy-2.0.22-cp312-cp312-win_amd64.whl", hash = "sha256:129415f89744b05741c6f0b04a84525f37fbabe5dc3774f7edf100e7458c48cd"},
     {file = "SQLAlchemy-2.0.22-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:3940677d341f2b685a999bffe7078697b5848a40b5f6952794ffcf3af150c301"},
-    {file = "SQLAlchemy-2.0.22-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:55914d45a631b81a8a2cb1a54f03eea265cf1783241ac55396ec6d735be14883"},
-    {file = "SQLAlchemy-2.0.22-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2096d6b018d242a2bcc9e451618166f860bb0304f590d205173d317b69986c95"},
-    {file = "SQLAlchemy-2.0.22-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:19c6986cf2fb4bc8e0e846f97f4135a8e753b57d2aaaa87c50f9acbe606bd1db"},
-    {file = "SQLAlchemy-2.0.22-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:6ac28bd6888fe3c81fbe97584eb0b96804bd7032d6100b9701255d9441373ec1"},
-    {file = "SQLAlchemy-2.0.22-cp37-cp37m-win32.whl", hash = "sha256:cb9a758ad973e795267da334a92dd82bb7555cb36a0960dcabcf724d26299db8"},
-    {file = "SQLAlchemy-2.0.22-cp37-cp37m-win_amd64.whl", hash = "sha256:40b1206a0d923e73aa54f0a6bd61419a96b914f1cd19900b6c8226899d9742ad"},
     {file = "SQLAlchemy-2.0.22-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:3aa1472bf44f61dd27987cd051f1c893b7d3b17238bff8c23fceaef4f1133868"},
     {file = "SQLAlchemy-2.0.22-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:56a7e2bb639df9263bf6418231bc2a92a773f57886d371ddb7a869a24919face"},
-    {file = "SQLAlchemy-2.0.22-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ccca778c0737a773a1ad86b68bda52a71ad5950b25e120b6eb1330f0df54c3d0"},
-    {file = "SQLAlchemy-2.0.22-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7c6c3e9350f9fb16de5b5e5fbf17b578811a52d71bb784cc5ff71acb7de2a7f9"},
-    {file = "SQLAlchemy-2.0.22-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:564e9f9e4e6466273dbfab0e0a2e5fe819eec480c57b53a2cdee8e4fdae3ad5f"},
-    {file = "SQLAlchemy-2.0.22-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:af66001d7b76a3fab0d5e4c1ec9339ac45748bc4a399cbc2baa48c1980d3c1f4"},
-    {file = "SQLAlchemy-2.0.22-cp38-cp38-win32.whl", hash = "sha256:9e55dff5ec115316dd7a083cdc1a52de63693695aecf72bc53a8e1468ce429e5"},
-    {file = "SQLAlchemy-2.0.22-cp38-cp38-win_amd64.whl", hash = "sha256:4e869a8ff7ee7a833b74868a0887e8462445ec462432d8cbeff5e85f475186da"},
-    {file = "SQLAlchemy-2.0.22-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9886a72c8e6371280cb247c5d32c9c8fa141dc560124348762db8a8b236f8692"},
-    {file = "SQLAlchemy-2.0.22-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:a571bc8ac092a3175a1d994794a8e7a1f2f651e7c744de24a19b4f740fe95034"},
-    {file = "SQLAlchemy-2.0.22-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8db5ba8b7da759b727faebc4289a9e6a51edadc7fc32207a30f7c6203a181592"},
-    {file = "SQLAlchemy-2.0.22-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0b0b3f2686c3f162123adba3cb8b626ed7e9b8433ab528e36ed270b4f70d1cdb"},
-    {file = "SQLAlchemy-2.0.22-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:0c1fea8c0abcb070ffe15311853abfda4e55bf7dc1d4889497b3403629f3bf00"},
-    {file = "SQLAlchemy-2.0.22-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:4bb062784f37b2d75fd9b074c8ec360ad5df71f933f927e9e95c50eb8e05323c"},
-    {file = "SQLAlchemy-2.0.22-cp39-cp39-win32.whl", hash = "sha256:58a3aba1bfb32ae7af68da3f277ed91d9f57620cf7ce651db96636790a78b736"},
-    {file = "SQLAlchemy-2.0.22-cp39-cp39-win_amd64.whl", hash = "sha256:92e512a6af769e4725fa5b25981ba790335d42c5977e94ded07db7d641490a85"},
-    {file = "SQLAlchemy-2.0.22-py3-none-any.whl", hash = "sha256:3076740335e4aaadd7deb3fe6dcb96b3015f1613bd190a4e1634e1b99b02ec86"},
     {file = "SQLAlchemy-2.0.22.tar.gz", hash = "sha256:5434cc601aa17570d79e5377f5fd45ff92f9379e2abed0be5e8c2fba8d353d2b"},
 ]
 
@@ -6798,30 +6791,30 @@ backoff = "*"
 beautifulsoup4 = "*"
 chardet = "*"
 dataclasses-json = "*"
-ebooklib = {version = "*", optional = true, markers = "extra == \"local-inference\""}
+ebooklib = {version = "*", optional = true, markers = "extra == \"all-docs\" or extra == \"local-inference\""}
 emoji = "*"
 filetype = "*"
 langdetect = "*"
 lxml = "*"
-markdown = {version = "*", optional = true, markers = "extra == \"local-inference\""}
+markdown = {version = "*", optional = true, markers = "extra == \"all-docs\" or extra == \"local-inference\""}
-msg-parser = {version = "*", optional = true, markers = "extra == \"local-inference\""}
+msg-parser = {version = "*", optional = true, markers = "extra == \"all-docs\" or extra == \"local-inference\""}
 nltk = "*"
 numpy = "*"
-openpyxl = {version = "*", optional = true, markers = "extra == \"local-inference\""}
+openpyxl = {version = "*", optional = true, markers = "extra == \"all-docs\" or extra == \"local-inference\""}
-pandas = {version = "*", optional = true, markers = "extra == \"local-inference\""}
+pandas = {version = "*", optional = true, markers = "extra == \"all-docs\" or extra == \"local-inference\""}
-pdf2image = {version = "*", optional = true, markers = "extra == \"local-inference\""}
+pdf2image = {version = "*", optional = true, markers = "extra == \"all-docs\" or extra == \"local-inference\""}
-"pdfminer.six" = {version = "*", optional = true, markers = "extra == \"local-inference\""}
+"pdfminer.six" = {version = "*", optional = true, markers = "extra == \"all-docs\" or extra == \"local-inference\""}
-pypandoc = {version = "*", optional = true, markers = "extra == \"local-inference\""}
+pypandoc = {version = "*", optional = true, markers = "extra == \"all-docs\" or extra == \"local-inference\""}
-python-docx = {version = ">=1.0.1", optional = true, markers = "extra == \"local-inference\""}
+python-docx = {version = ">=1.0.1", optional = true, markers = "extra == \"all-docs\" or extra == \"local-inference\""}
 python-iso639 = "*"
 python-magic = "*"
-python-pptx = {version = "<=0.6.21", optional = true, markers = "extra == \"local-inference\""}
+python-pptx = {version = "<=0.6.21", optional = true, markers = "extra == \"all-docs\" or extra == \"local-inference\""}
 rapidfuzz = "*"
 requests = "*"
 tabulate = "*"
-unstructured-inference = {version = "0.7.3", optional = true, markers = "extra == \"local-inference\""}
+unstructured-inference = {version = "0.7.3", optional = true, markers = "extra == \"all-docs\" or extra == \"local-inference\""}
-"unstructured.pytesseract" = {version = ">=0.3.12", optional = true, markers = "extra == \"local-inference\""}
+"unstructured.pytesseract" = {version = ">=0.3.12", optional = true, markers = "extra == \"all-docs\" or extra == \"local-inference\""}
-xlrd = {version = "*", optional = true, markers = "extra == \"local-inference\""}
+xlrd = {version = "*", optional = true, markers = "extra == \"all-docs\" or extra == \"local-inference\""}
 
 [package.extras]
 airtable = ["pyairtable"]
@@ -7508,6 +7501,27 @@ files = [
 [package.dependencies]
 requests = "*"
 
+[[package]]
+name = "yt-dlp"
+version = "2023.11.16"
+description = "A youtube-dl fork with additional features and patches"
+optional = true
+python-versions = ">=3.7"
+files = [
+    {file = "yt-dlp-2023.11.16.tar.gz", hash = "sha256:f0ccdaf12e08b15902601a4671c7ab12906d7b11de3ae75fa6506811c24ec5da"},
+    {file = "yt_dlp-2023.11.16-py2.py3-none-any.whl", hash = "sha256:0322ba85aa4afdb75f8641ed550e5958964daff034aeb477abb15031fd9a51ed"},
+]
+
+[package.dependencies]
+brotli = {version = "*", markers = "implementation_name == \"cpython\""}
+brotlicffi = {version = "*", markers = "implementation_name != \"cpython\""}
+certifi = "*"
+mutagen = "*"
+pycryptodomex = "*"
+requests = ">=2.31.0,<3"
+urllib3 = ">=1.26.17,<3"
+websockets = "*"
+
 [[package]]
 name = "zipp"
 version = "3.17.0"
@@ -7526,9 +7540,10 @@ testing = ["big-O", "jaraco.functools", "jaraco.itertools", "more-itertools", "p
 [extras]
 cohere = ["cohere"]
 community = ["llama-hub"]
-dataloaders = ["beautifulsoup4", "docx2txt", "duckduckgo-search", "pypdf", "pytube", "sentence-transformers", "unstructured"]
+dataloaders = ["beautifulsoup4", "docx2txt", "duckduckgo-search", "pypdf", "pytube", "sentence-transformers", "unstructured", "youtube-transcript-api"]
 discord = ["discord"]
 elasticsearch = ["elasticsearch"]
+git = ["gitpython"]
 gmail = ["llama-hub", "requests"]
 huggingface-hub = ["huggingface_hub"]
 images = ["ftfy", "pillow", "regex", "torch", "torchvision"]
@@ -7547,8 +7562,9 @@ streamlit = []
 vertexai = ["google-cloud-aiplatform"]
 weaviate = ["weaviate-client"]
 whatsapp = ["flask", "twilio"]
+youtube = ["youtube-transcript-api", "yt_dlp"]
 
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.9,<3.12"
-content-hash = "fe9ebe5f637303885981d10ace60b955635c7ca7586605546837e59206bfefd7"
+content-hash = "ea063cadfefd23d4c9b2a25c9096efe6bcedc367136d819ccb1fd2f510a91206"

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "embedchain"
-version = "0.1.10"
+version = "0.1.21"
 description = "Data platform for LLMs - Load, index, retrieve and sync any unstructured data"
 authors = [
     "Taranjeet Singh <taranjeet@embedchain.ai>",
@@ -90,10 +90,10 @@ color = true
 [tool.poetry.dependencies]
 python = ">=3.9,<3.12"
 python-dotenv = "^1.0.0"
-langchain = "^0.0.332"
+langchain = "^0.0.336"
 requests = "^2.31.0"
 openai = ">=1.1.1"
-chromadb = "^0.4.16"
+chromadb = "^0.4.17"
 posthog = "^3.0.2"
 tiktoken = { version = "^0.4.0", optional = true }
 youtube-transcript-api = { version = "^0.6.1", optional = true }
@@ -120,7 +120,7 @@ weaviate-client = { version = "^3.24.1", optional = true }
 docx2txt = { version = "^0.8", optional = true }
 pinecone-client = { version = "^2.2.4", optional = true }
 qdrant-client = { version = "1.6.3", optional = true }
-unstructured = {extras = ["local-inference"], version = "^0.10.18", optional = true}
+unstructured = {extras = ["local-inference", "all-docs"], version = "^0.10.18", optional = true}
 pillow = { version = "10.0.1", optional = true }
 torchvision = { version = ">=0.15.1, !=0.15.2", optional = true }
 ftfy = { version = "6.1.1", optional = true }
@@ -134,6 +134,8 @@ psycopg = { version = "^3.1.12", optional = true }
 psycopg-binary = { version = "^3.1.12", optional = true }
 psycopg-pool = { version = "^3.1.8", optional = true }
 mysql-connector-python = { version = "^8.1.0", optional = true }
+gitpython = { version = "^3.1.38", optional = true }
+yt_dlp = { version = "^2023.11.14", optional = true }
 
 [tool.poetry.group.dev.dependencies]
 black = "^23.3.0"
@@ -167,7 +169,7 @@ huggingface_hub=["huggingface_hub"]
 cohere = ["cohere"]
 milvus = ["pymilvus"]
 dataloaders=[
-    "youtube-transcripts-api",
+    "youtube-transcript-api",
     "beautifulsoup4",
     "docx2txt",
     "duckduckgo-search",
@@ -190,6 +192,11 @@ gmail = [
 json = ["llama-hub"]
 postgres = ["psycopg", "psycopg-binary", "psycopg-pool"]
 mysql = ["mysql-connector-python"]
+git = ["gitpython"]
+youtube = [
+    "yt_dlp",
+    "youtube-transcript-api",
+]
 
 [tool.poetry.group.docs.dependencies]