[Feature] Improve github and youtube channel loader (#966)

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

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/llms.mdx

@@ -237,7 +237,7 @@ llm:
 Install related dependencies using the following command:
 
 ```bash
-pip install --upgrade 'embedchain[huggingface_hub]'
+pip install --upgrade 'embedchain[huggingface-hub]'
 ```
 
 First, set `HUGGINGFACE_ACCESS_TOKEN` in environment variable which you can obtain from [their platform](https://huggingface.co/settings/tokens).

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/mysql.mdx

@@ -0,0 +1,48 @@
+---
+title: '🐬 MySQL'
+---
+
+1. Setup the MySQL loader by configuring the SQL db.
+```Python
+from embedchain.loaders.mysql import MySQLLoader
+
+config = {
+    "host": "host",
+    "port": "port",
+    "database": "database",
+    "user": "username",
+    "password": "password",
+}
+
+mysql_loader = MySQLLoader(config=config)
+```
+
+For more details on how to setup with valid config, check MySQL [documentation](https://dev.mysql.com/doc/connector-python/en/connector-python-connectargs.html).
+
+2. Once you setup the loader, you can create an app and load data using the above MySQL loader
+```Python
+import os
+from embedchain.pipeline import Pipeline as App
+
+app = App()
+
+app.add("SELECT * FROM table_name;", data_type='mysql', loader=mysql_loader)
+# Adds `(1, 'What is your net worth, Elon Musk?', "As of October 2023, Elon Musk's net worth is $255.2 billion.")`
+
+response = app.query(question)
+# Answer: As of October 2023, Elon Musk's net worth is $255.2 billion.
+```
+
+NOTE: The `add` function of the app will accept any executable query to load data. DO NOT pass the `CREATE`, `INSERT` queries in `add` function.
+
+3. We automatically create a chunker to chunk your SQL data, however if you wish to provide your own chunker class. Here is how you can do that:
+``Python
+
+from embedchain.chunkers.mysql import MySQLChunker
+from embedchain.config.add_config import ChunkerConfig
+
+mysql_chunker_config = ChunkerConfig(chunk_size=1000, chunk_overlap=0, length_function=len)
+mysql_chunker = MySQLChunker(config=mysql_chunker_config)
+
+app.add("SELECT * FROM table_name;", data_type='mysql', loader=mysql_loader, chunker=mysql_chunker)
+```

docs/data-sources/overview.mdx

@@ -18,9 +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/slack.mdx

@@ -0,0 +1,54 @@
+---
+title: '🤖 Slack'
+---
+
+## Pre-requisite
+- Download required packages by running `pip install --upgrade "embedchain[slack]"`.
+- Configure your slack bot token as environment variable `SLACK_USER_TOKEN`.
+    - Find your user token on your [Slack Account](https://api.slack.com/authentication/token-types)
+    - Make sure your slack user token includes [search](https://api.slack.com/scopes/search:read) scope.
+
+## Example
+1. Setup the Slack loader by configuring the Slack Webclient.
+```Python
+from embedchain.loaders.slack import SlackLoader
+
+os.environ["SLACK_USER_TOKEN"] = "xoxp-*"
+
+loader = SlackLoader()
+
+"""
+config = {
+    'base_url': slack_app_url,
+    'headers': web_headers,
+    'team_id': slack_team_id,
+}
+
+loader = SlackLoader(config)
+"""
+```
+
+NOTE: you can also pass the `config` with `base_url`, `headers`, `team_id` to setup your SlackLoader.
+
+2. Once you setup the loader, you can create an app and load data using the above slack loader
+```Python
+import os
+from embedchain.pipeline import Pipeline as App
+
+app = App()
+
+app.add("in:random", data_type="slack", loader=loader)
+question = "Which bots are available in the slack workspace's random channel?"
+# Answer: The available bot in the slack workspace's random channel is the Embedchain bot.
+```
+
+3. We automatically create a chunker to chunk your slack data, however if you wish to provide your own chunker class. Here is how you can do that:
+```Python
+from embedchain.chunkers.slack import SlackChunker
+from embedchain.config.add_config import ChunkerConfig
+
+slack_chunker_config = ChunkerConfig(chunk_size=1000, chunk_overlap=0, length_function=len)
+slack_chunker = SlackChunker(config=slack_chunker_config)
+
+app.add(slack_chunker, data_type="slack", loader=loader, chunker=slack_chunker)
+```

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/examples/slack_bot.mdx

@@ -15,8 +15,21 @@ channels:read
 chat:write
 ```
 5. Now select the option `Install to Workspace` and after it's done, copy the `Bot User OAuth Token` and set it in your secrets as `SLACK_BOT_TOKEN`.
-6. Run your bot now with `python3 -m embedchain.bots.slack`
+6. Run your bot now,
-7. Expose your bot to the internet. Default port is `5000`, which can be changed by adding `port --8080` to the startup command. You can use your machine's public IP or DNS. Otherwise, employ a proxy server like [ngrok](https://ngrok.com/) to make your local bot accessible.
+<Tabs>
+    <Tab title="docker">
+        ```bash
+        docker run --name slack-bot -e OPENAI_API_KEY=sk-xxx -e SLACK_BOT_TOKEN=xxx -p 8000:8000 embedchain/slack-bot
+        ```
+    </Tab>
+    <Tab title="python">
+        ```bash
+        pip install --upgrade "embedchain[slack]"
+        python3 -m embedchain.bots.slack --port 8000
+        ```
+</Tab>
+</Tabs>
+7. Expose your bot to the internet. You can use your machine's public IP or DNS. Otherwise, employ a proxy server like [ngrok](https://ngrok.com/) to make your local bot accessible.
 8. On the Slack API website go to `Event Subscriptions` on the left Sidebar and turn on `Enable Events`.
 9. In `Request URL`, enter your server or ngrok address.
 10. After it gets verified, click on `Subscribe to bot events`, add `message.channels` Bot User Event and click on `Save Changes`.

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/apps/app.py

@@ -134,6 +134,9 @@ 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/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.helper.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.helper.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/mysql.py

@@ -0,0 +1,22 @@
+from typing import Optional
+
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+from embedchain.chunkers.base_chunker import BaseChunker
+from embedchain.config.add_config import ChunkerConfig
+from embedchain.helper.json_serializable import register_deserializable
+
+
+@register_deserializable
+class MySQLChunker(BaseChunker):
+    """Chunker for json."""
+
+    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/slack.py

@@ -0,0 +1,22 @@
+from typing import Optional
+
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+from embedchain.chunkers.base_chunker import BaseChunker
+from embedchain.config.add_config import ChunkerConfig
+from embedchain.helper.json_serializable import register_deserializable
+
+
+@register_deserializable
+class SlackChunker(BaseChunker):
+    """Chunker for postgres."""
+
+    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/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.helper.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/data_formatter/data_formatter.py

@@ -63,11 +63,17 @@ 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(
             [
                 DataType.POSTGRES,
+                DataType.MYSQL,
+                DataType.SLACK,
+                DataType.DISCOURSE,
             ]
         )
 
@@ -106,6 +112,12 @@ class DataFormatter(JSONSerializable):
             DataType.GMAIL: "embedchain.chunkers.gmail.GmailChunker",
             DataType.NOTION: "embedchain.chunkers.notion.NotionChunker",
             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

@@ -203,7 +203,7 @@ class EmbedChain(JSONSerializable):
         self.user_asks.append([source, data_type.value, metadata])
 
         data_formatter = DataFormatter(data_type, config, kwargs)
-        documents, metadatas, _ids, new_chunks = self.load_and_embed(
+        documents, metadatas, _ids, new_chunks = self._load_and_embed(
             data_formatter.loader, data_formatter.chunker, source, metadata, source_hash, dry_run
         )
         if data_type in {DataType.DOCS_SITE}:
@@ -340,7 +340,7 @@ class EmbedChain(JSONSerializable):
                 "When it should be  DirectDataType, IndirectDataType or SpecialDataType."
             )
 
-    def load_and_embed(
+    def _load_and_embed(
         self,
         loader: BaseLoader,
         chunker: BaseChunker,
@@ -457,7 +457,7 @@ class EmbedChain(JSONSerializable):
             )
         ]
 
-    def retrieve_from_database(
+    def _retrieve_from_database(
         self, input_query: str, config: Optional[BaseLlmConfig] = None, where=None, citations: bool = False
     ) -> Union[List[Tuple[str, str, str]], List[str]]:
         """
@@ -482,7 +482,7 @@ class EmbedChain(JSONSerializable):
             where = {}
             if query_config is not None and query_config.where is not None:
                 where = query_config.where
-            
+
             if self.config.id is not None:
                 where.update({"app_id": self.config.id})
 
@@ -537,7 +537,9 @@ class EmbedChain(JSONSerializable):
         :rtype: str, if citations is False, otherwise Tuple[str,List[Tuple[str,str,str]]]
         """
         citations = kwargs.get("citations", False)
-        contexts = self.retrieve_from_database(input_query=input_query, config=config, where=where, citations=citations)
+        contexts = self._retrieve_from_database(
+            input_query=input_query, config=config, where=where, citations=citations
+        )
         if citations and len(contexts) > 0 and isinstance(contexts[0], tuple):
             contexts_data_for_llm_query = list(map(lambda x: x[0], contexts))
         else:
@@ -588,7 +590,9 @@ class EmbedChain(JSONSerializable):
         :rtype: str, if citations is False, otherwise Tuple[str,List[Tuple[str,str,str]]]
         """
         citations = kwargs.get("citations", False)
-        contexts = self.retrieve_from_database(input_query=input_query, config=config, where=where, citations=citations)
+        contexts = self._retrieve_from_database(
+            input_query=input_query, config=config, where=where, citations=citations
+        )
         if citations and len(contexts) > 0 and isinstance(contexts[0], tuple):
             contexts_data_for_llm_query = list(map(lambda x: x[0], contexts))
         else:

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

@@ -1,18 +1,18 @@
 import os
 from typing import Optional
 
+from chromadb.utils.embedding_functions import OpenAIEmbeddingFunction
 from langchain.embeddings import OpenAIEmbeddings
 
 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"
 

embedchain/helper/json_serializable.py

@@ -33,7 +33,7 @@ def register_deserializable(cls: Type[T]) -> Type[T]:
     Returns:
         Type: The same class, after registration.
     """
-    JSONSerializable.register_class_as_deserializable(cls)
+    JSONSerializable._register_class_as_deserializable(cls)
     return cls
 
 
@@ -183,7 +183,7 @@ class JSONSerializable:
             return cls.deserialize(json_str)
 
     @classmethod
-    def register_class_as_deserializable(cls, target_class: Type[T]) -> None:
+    def _register_class_as_deserializable(cls, target_class: Type[T]) -> None:
         """
         Register a class as deserializable. This is a classmethod and globally shared.
 

embedchain/llm/huggingface.py

@@ -20,7 +20,7 @@ class HuggingFaceLlm(BaseLlm):
         except ModuleNotFoundError:
             raise ModuleNotFoundError(
                 "The required dependencies for HuggingFaceHub are not installed."
-                'Please install with `pip install --upgrade "embedchain[huggingface_hub]"`'
+                'Please install with `pip install --upgrade "embedchain[huggingface-hub]"`'
             ) from None
 
         super().__init__(config=config)

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/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/mysql.py

@@ -0,0 +1,64 @@
+import hashlib
+import logging
+from typing import Any, Dict, Optional
+
+from embedchain.loaders.base_loader import BaseLoader
+from embedchain.utils import clean_string
+
+
+class MySQLLoader(BaseLoader):
+    def __init__(self, config: Optional[Dict[str, Any]]):
+        super().__init__()
+        if not config:
+            raise ValueError(
+                f"Invalid sql config: {config}.",
+                "Provide the correct config, refer `https://docs.embedchain.ai/data-sources/mysql`.",
+            )
+
+        self.config = config
+        self.connection = None
+        self.cursor = None
+        self._setup_loader(config=config)
+
+    def _setup_loader(self, config: Dict[str, Any]):
+        try:
+            import mysql.connector as sqlconnector
+        except ImportError as e:
+            raise ImportError(
+                "Unable to import required packages for MySQL loader. Run `pip install --upgrade 'embedchain[mysql]'`."  # noqa: E501
+            ) from e
+
+        try:
+            self.connection = sqlconnector.connection.MySQLConnection(**config)
+            self.cursor = self.connection.cursor()
+        except (sqlconnector.Error, IOError) as err:
+            logging.info(f"Connection failed: {err}")
+            raise ValueError(
+                f"Unable to connect with the given config: {config}.",
+                "Please provide the correct configuration to load data from you MySQL DB. \
+                    Refer `https://docs.embedchain.ai/data-sources/mysql`.",
+            )
+
+    def _check_query(self, query):
+        if not isinstance(query, str):
+            raise ValueError(
+                f"Invalid mysql query: {query}",
+                "Provide the valid query to add from mysql, \
+                    make sure you are following `https://docs.embedchain.ai/data-sources/mysql`",
+            )
+
+    def load_data(self, query):
+        self._check_query(query=query)
+        data = []
+        data_content = []
+        self.cursor.execute(query)
+        rows = self.cursor.fetchall()
+        for row in rows:
+            doc_content = clean_string(str(row))
+            data.append({"content": doc_content, "meta_data": {"url": query}})
+            data_content.append(doc_content)
+        doc_id = hashlib.sha256((query + ", ".join(data_content)).encode()).hexdigest()
+        return {
+            "doc_id": doc_id,
+            "data": data,
+        }

embedchain/loaders/postgres.py

@@ -40,9 +40,7 @@ class PostgresLoader(BaseLoader):
     def _check_query(self, query):
         if not isinstance(query, str):
             raise ValueError(
-                f"Invalid postgres query: {query}",
+                f"Invalid postgres query: {query}. Provide the valid source to add from postgres, make sure you are following `https://docs.embedchain.ai/data-sources/postgres`",  # noqa:E501
-                "Provide the valid source to add from postgres, \
-                    make sure you are following `https://docs.embedchain.ai/data-sources/postgres`",
             )
 
     def load_data(self, query):
@@ -54,7 +52,7 @@ class PostgresLoader(BaseLoader):
             results = self.cursor.fetchall()
             for result in results:
                 doc_content = str(result)
-                data.append({"content": doc_content, "meta_data": {"url": f"postgres_query-({query})"}})
+                data.append({"content": doc_content, "meta_data": {"url": query}})
                 data_content.append(doc_content)
             doc_id = hashlib.sha256((query + ", ".join(data_content)).encode()).hexdigest()
             return {

embedchain/loaders/sitemap.py

@@ -1,7 +1,9 @@
+import concurrent.futures
 import hashlib
 import logging
 
 import requests
+from tqdm import tqdm
 
 try:
     from bs4 import BeautifulSoup
@@ -19,33 +21,45 @@ from embedchain.utils import is_readable
 
 @register_deserializable
 class SitemapLoader(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, sitemap_url):
-        """
-        This method takes a sitemap URL as input and retrieves
-        all the URLs to use the WebPageLoader to load content
-        of each page.
-        """
         output = []
         web_page_loader = WebPageLoader()
         response = requests.get(sitemap_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"]
         if len(links) == 0:
-            # Get all <loc> tags as a fallback. This might include images.
             links = [link.text for link in soup.find_all("loc")]
 
         doc_id = hashlib.sha256((" ".join(links) + sitemap_url).encode()).hexdigest()
 
-        for link in links:
+        def load_link(link):
             try:
                 each_load_data = web_page_loader.load_data(link)
                 if is_readable(each_load_data.get("data")[0].get("content")):
-                    output.append(each_load_data.get("data"))
+                    return each_load_data.get("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 {"doc_id": doc_id, "data": [data[0] for data in output]}
+            return None
+
+        with concurrent.futures.ThreadPoolExecutor() as executor:
+            future_to_link = {executor.submit(load_link, link): link for link in links}
+            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.extend(data)
+                except Exception as e:
+                    logging.error(f"Error loading page {link}: {e}")
+
+        return {"doc_id": doc_id, "data": output}

embedchain/loaders/slack.py

@@ -0,0 +1,108 @@
+import hashlib
+import logging
+import os
+import ssl
+from typing import Any, Dict, Optional
+
+import certifi
+
+from embedchain.loaders.base_loader import BaseLoader
+from embedchain.utils import clean_string
+
+SLACK_API_BASE_URL = "https://www.slack.com/api/"
+
+
+class SlackLoader(BaseLoader):
+    def __init__(self, config: Optional[Dict[str, Any]] = None):
+        super().__init__()
+
+        if config is not None:
+            self.config = config
+        else:
+            self.config = {"base_url": SLACK_API_BASE_URL}
+
+        self.client = None
+        self._setup_loader(self.config)
+
+    def _setup_loader(self, config: Dict[str, Any]):
+        try:
+            from slack_sdk import WebClient
+        except ImportError as e:
+            raise ImportError(
+                "Slack loader requires extra dependencies. \
+                Install with `pip install --upgrade embedchain[slack]`"
+            ) from e
+
+        if os.getenv("SLACK_USER_TOKEN") is None:
+            raise ValueError(
+                "SLACK_USER_TOKEN environment variables not provided. Check `https://docs.embedchain.ai/data-sources/slack` to learn more."  # noqa:E501
+            )
+
+        logging.info(f"Creating Slack Loader with config: {config}")
+        # get slack client config params
+        slack_bot_token = os.getenv("SLACK_USER_TOKEN")
+        ssl_cert = ssl.create_default_context(cafile=certifi.where())
+        base_url = config.get("base_url", SLACK_API_BASE_URL)
+        headers = config.get("headers")
+        # for Org-Wide App
+        team_id = config.get("team_id")
+
+        self.client = WebClient(
+            token=slack_bot_token,
+            base_url=base_url,
+            ssl=ssl_cert,
+            headers=headers,
+            team_id=team_id,
+        )
+        logging.info("Slack Loader setup successful!")
+
+    def _check_query(self, query):
+        if not isinstance(query, str):
+            raise ValueError(
+                f"Invalid query passed to Slack loader, found: {query}. Check `https://docs.embedchain.ai/data-sources/slack` to learn more."  # noqa:E501
+            )
+
+    def load_data(self, query):
+        self._check_query(query)
+        try:
+            data = []
+            data_content = []
+
+            logging.info(f"Searching slack conversations for query: {query}")
+            results = self.client.search_messages(
+                query=query,
+                sort="timestamp",
+                sort_dir="desc",
+                count=1000,
+            )
+
+            messages = results.get("messages")
+            num_message = results.get("total")
+            logging.info(f"Found {num_message} messages for query: {query}")
+
+            matches = messages.get("matches", [])
+            for message in matches:
+                url = message.get("permalink")
+                text = message.get("text")
+                content = clean_string(text)
+
+                message_meta_data_keys = ["channel", "iid", "team", "ts", "type", "user", "username"]
+                meta_data = message.fromkeys(message_meta_data_keys, "")
+                meta_data.update({"url": url})
+                data.append(
+                    {
+                        "content": content,
+                        "meta_data": meta_data,
+                    }
+                )
+                data_content.append(content)
+            doc_id = hashlib.md5((query + ", ".join(data_content)).encode()).hexdigest()
+            return {
+                "doc_id": doc_id,
+                "data": data,
+            }
+        except Exception as e:
+            logging.warning(f"Error in loading slack data: {e}")
+            raise ValueError(
+                f"Error in loading slack data: {e}. Check `https://docs.embedchain.ai/data-sources/slack` to learn more."  # noqa:E501
+            ) from e

embedchain/loaders/substack.py

@@ -0,0 +1,86 @@
+import hashlib
+import logging
+import time
+
+import requests
+
+from embedchain.helper.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

@@ -1,11 +1,5 @@
 import hashlib
 
-try:
-    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

@@ -17,15 +17,17 @@ 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/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

@@ -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/models/data_type.py

@@ -30,6 +30,12 @@ class IndirectDataType(Enum):
     OPENAPI = "openapi"
     GMAIL = "gmail"
     POSTGRES = "postgres"
+    MYSQL = "mysql"
+    SLACK = "slack"
+    DISCOURSE = "discourse"
+    SUBSTACK = "substack"
+    GITHUB = "github"
+    YOUTUBE_CHANNEL = "youtube_channel"
 
 
 class SpecialDataType(Enum):
@@ -59,3 +65,9 @@ class DataType(Enum):
     OPENAPI = IndirectDataType.OPENAPI.value
     GMAIL = IndirectDataType.GMAIL.value
     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

@@ -357,6 +357,9 @@ 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

@@ -3,12 +3,14 @@ import os
 import re
 import tempfile
 import time
+import uuid
 from pathlib import Path
 from typing import cast
 
 from openai import OpenAI
 from openai.types.beta.threads import MessageContentText, ThreadMessage
 
+from embedchain import Pipeline
 from embedchain.config import AddConfig
 from embedchain.data_formatter import DataFormatter
 from embedchain.models.data_type import DataType
@@ -138,3 +140,65 @@ class OpenAIAssistant:
         with open(file_path, "wb") as file:
             file.write(data)
         return file_path
+
+
+class AIAssistant:
+    def __init__(
+        self,
+        name=None,
+        instructions=None,
+        yaml_path=None,
+        assistant_id=None,
+        thread_id=None,
+        data_sources=None,
+        log_level=logging.WARN,
+        collect_metrics=True,
+    ):
+        logging.basicConfig(level=log_level)
+
+        self.name = name or "AI Assistant"
+        self.data_sources = data_sources or []
+        self.log_level = log_level
+        self.instructions = instructions
+        self.assistant_id = assistant_id or str(uuid.uuid4())
+        self.thread_id = thread_id or str(uuid.uuid4())
+        self.pipeline = Pipeline.from_config(yaml_path=yaml_path) if yaml_path else Pipeline()
+        self.pipeline.local_id = self.pipeline.config.id = self.thread_id
+
+        if self.instructions:
+            self.pipeline.system_prompt = self.instructions
+
+        print(
+            f"🎉 Created AI Assistant with name: {self.name}, assistant_id: {self.assistant_id}, thread_id: {self.thread_id}"  # noqa: E501
+        )
+
+        # telemetry related properties
+        self._telemetry_props = {"class": self.__class__.__name__}
+        self.telemetry = AnonymousTelemetry(enabled=collect_metrics)
+        self.telemetry.capture(event_name="init", properties=self._telemetry_props)
+
+        if self.data_sources:
+            for data_source in self.data_sources:
+                metadata = {"assistant_id": self.assistant_id, "thread_id": "global_knowledge"}
+                self.pipeline.add(data_source["source"], data_source.get("data_type"), metadata=metadata)
+
+    def add(self, source, data_type=None):
+        metadata = {"assistant_id": self.assistant_id, "thread_id": self.thread_id}
+        self.pipeline.add(source, data_type=data_type, metadata=metadata)
+        event_props = {
+            **self._telemetry_props,
+            "data_type": data_type or detect_datatype(source),
+        }
+        self.telemetry.capture(event_name="add", properties=event_props)
+
+    def chat(self, query):
+        where = {
+            "$and": [
+                {"assistant_id": {"$eq": self.assistant_id}},
+                {"thread_id": {"$in": [self.thread_id, "global_knowledge"]}},
+            ]
+        }
+        return self.pipeline.chat(query, where=where)
+
+    def delete(self):
+        self.pipeline.reset()

embedchain/telemetry/posthog.py

@@ -20,7 +20,7 @@ class AnonymousTelemetry:
         self.project_api_key = "phc_PHQDA5KwztijnSojsxJ2c1DuJd52QCzJzT2xnSGvjN2"
         self.host = host
         self.posthog = Posthog(project_api_key=self.project_api_key, host=self.host)
-        self.user_id = self.get_user_id()
+        self.user_id = self._get_user_id()
         self.enabled = enabled
 
         # Check if telemetry tracking is disabled via environment variable
@@ -38,7 +38,7 @@ class AnonymousTelemetry:
         posthog_logger = logging.getLogger("posthog")
         posthog_logger.disabled = True
 
-    def get_user_id(self):
+    def _get_user_id(self):
         if not os.path.exists(CONFIG_DIR):
             os.makedirs(CONFIG_DIR)
 

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/chroma.py

@@ -3,6 +3,7 @@ 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
@@ -157,8 +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 chromadb".format(i, min(len(documents), i + self.BATCH_SIZE)))
             if skip_embedding:
                 self.collection.add(
                     embeddings=embeddings[i : i + self.BATCH_SIZE],

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
@@ -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,

examples/rest-api/main.py

@@ -83,7 +83,7 @@ async def create_app_using_default_config(app_id: str, config: UploadFile = None
 
         return DefaultResponse(response=f"App created successfully. App ID: {app_id}")
     except Exception as e:
-        logging.warn(str(e))
+        logging.warning(str(e))
         raise HTTPException(detail=f"Error creating app: {str(e)}", status_code=400)
 
 
@@ -113,13 +113,13 @@ async def get_datasources_associated_with_app_id(app_id: str, db: Session = Depe
         response = app.get_data_sources()
         return {"results": response}
     except ValueError as ve:
-        logging.warn(str(ve))
+        logging.warning(str(ve))
         raise HTTPException(
             detail=generate_error_message_for_api_keys(ve),
             status_code=400,
         )
     except Exception as e:
-        logging.warn(str(e))
+        logging.warning(str(e))
         raise HTTPException(detail=f"Error occurred: {str(e)}", status_code=400)
 
 
@@ -152,13 +152,13 @@ async def add_datasource_to_an_app(body: SourceApp, app_id: str, db: Session = D
         response = app.add(source=body.source, data_type=body.data_type)
         return DefaultResponse(response=response)
     except ValueError as ve:
-        logging.warn(str(ve))
+        logging.warning(str(ve))
         raise HTTPException(
             detail=generate_error_message_for_api_keys(ve),
             status_code=400,
         )
     except Exception as e:
-        logging.warn(str(e))
+        logging.warning(str(e))
         raise HTTPException(detail=f"Error occurred: {str(e)}", status_code=400)
 
 
@@ -190,13 +190,13 @@ async def query_an_app(body: QueryApp, app_id: str, db: Session = Depends(get_db
         response = app.query(body.query)
         return DefaultResponse(response=response)
     except ValueError as ve:
-        logging.warn(str(ve))
+        logging.warning(str(ve))
         raise HTTPException(
             detail=generate_error_message_for_api_keys(ve),
             status_code=400,
         )
     except Exception as e:
-        logging.warn(str(e))
+        logging.warning(str(e))
         raise HTTPException(detail=f"Error occurred: {str(e)}", status_code=400)
 
 
@@ -273,13 +273,13 @@ async def deploy_app(body: DeployAppRequest, app_id: str, db: Session = Depends(
         app.deploy()
         return DefaultResponse(response="App deployed successfully.")
     except ValueError as ve:
-        logging.warn(str(ve))
+        logging.warning(str(ve))
         raise HTTPException(
             detail=generate_error_message_for_api_keys(ve),
             status_code=400,
         )
     except Exception as e:
-        logging.warn(str(e))
+        logging.warning(str(e))
         raise HTTPException(detail=f"Error occurred: {str(e)}", status_code=400)
 
 

examples/slack_bot/Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.11-slim
+
+WORKDIR /usr/src/
+COPY requirements.txt .
+RUN pip install -r requirements.txt
+
+COPY . .
+
+EXPOSE 8000
+
+CMD ["python", "-m", "embedchain.bots.slack", "--port", "8000"]

examples/slack_bot/requirements.txt

@@ -0,0 +1 @@
+embedchain[slack, poe]==0.1.7

poetry.lock

@@ -744,13 +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]
@@ -1671,6 +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"
@@ -2742,13 +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]
@@ -2757,7 +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"
@@ -2766,17 +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)"]
 
@@ -2796,18 +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]]
@@ -3351,6 +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"
@@ -3362,6 +3403,50 @@ files = [
     {file = "mypy_extensions-1.0.0.tar.gz", hash = "sha256:75dbf8955dc00442a438fc4d0666508a9a97b6bd41aa2f0ffe9d2f2725af0782"},
 ]
 
+[[package]]
+name = "mysql-connector-python"
+version = "8.2.0"
+description = "MySQL driver written in Python"
+optional = true
+python-versions = ">=3.8"
+files = [
+    {file = "mysql-connector-python-8.2.0.tar.gz", hash = "sha256:884eba07b4c97edf552a03f5fdca145e0ab4afc3d8677cca20276effca1bea54"},
+    {file = "mysql_connector_python-8.2.0-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:37ca26d7b10580b836f038d42f21ba9e6c88542868d50f55defdbd2dc8e0c0e6"},
+    {file = "mysql_connector_python-8.2.0-cp310-cp310-macosx_12_0_x86_64.whl", hash = "sha256:9d598cc854d1b61eabad7cbf003cfe59970aae80384f5ff18a5cc3fba7becdcc"},
+    {file = "mysql_connector_python-8.2.0-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:4828a08b738174cacb0985df01120e0a2f0ba534c9d2f67d6613b0930a0fe3cd"},
+    {file = "mysql_connector_python-8.2.0-cp310-cp310-manylinux_2_17_x86_64.whl", hash = "sha256:4b2de9dd56de4874c30364023b59991399222cf73ec744da590cf9eef2623c26"},
+    {file = "mysql_connector_python-8.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:858490bb450b6ae45f415d2205d65a12e84e3445c7b9736e1d1552b685bf237a"},
+    {file = "mysql_connector_python-8.2.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:5d1e1399a9feb45fc8caca6168ff35d31a8124693f24391153764bccc61d15ad"},
+    {file = "mysql_connector_python-8.2.0-cp311-cp311-macosx_12_0_x86_64.whl", hash = "sha256:a0308455462d4078baf516255662a46611eb12fc8d83d40dea38df3032d2566d"},
+    {file = "mysql_connector_python-8.2.0-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:539300944c36566e91d131e106dbf0a90cde697ba88247a820f5af9caea2e5c2"},
+    {file = "mysql_connector_python-8.2.0-cp311-cp311-manylinux_2_17_x86_64.whl", hash = "sha256:66d755b94f547d6fcdee9f2256805a4534103363e35d185d3800bfc5274e1f4f"},
+    {file = "mysql_connector_python-8.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:877076f2d71d268fb1b334c85a20ef1d42096ceb6580b25229be4510ebf5a0c5"},
+    {file = "mysql_connector_python-8.2.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:b3f64b1fd2de2e8ed5c9ddd388efce8c6804a8633e18dbb45563a6ae61fbc45b"},
+    {file = "mysql_connector_python-8.2.0-cp312-cp312-macosx_12_0_x86_64.whl", hash = "sha256:e9eacdc3fa5f61276c1549ca7c471a6fde576692881a70dcbac8258314015347"},
+    {file = "mysql_connector_python-8.2.0-cp312-cp312-manylinux_2_17_aarch64.whl", hash = "sha256:230a34df2f3c4f36acf426361914b8552f129538a5e2256d489dca2b39f2f031"},
+    {file = "mysql_connector_python-8.2.0-cp312-cp312-manylinux_2_17_x86_64.whl", hash = "sha256:26e19a4469276870ccc0a04db30c534519f0f774a5949370ff0dc03e7cfc071c"},
+    {file = "mysql_connector_python-8.2.0-cp312-cp312-win_amd64.whl", hash = "sha256:e0b8af0d8c56619875dee4168b1bf77e17a4c1c5e1df935623d264729df70227"},
+    {file = "mysql_connector_python-8.2.0-cp38-cp38-macosx_12_0_x86_64.whl", hash = "sha256:81ac2e409b604bcf2ae6e18bc477f8f6e509ea5004c8dba291afe3d2591f0a3f"},
+    {file = "mysql_connector_python-8.2.0-cp38-cp38-manylinux_2_17_aarch64.whl", hash = "sha256:98606e893bc2343ccc9254f248e4bd5bae18cb03bf4931f3b1657900cd647718"},
+    {file = "mysql_connector_python-8.2.0-cp38-cp38-manylinux_2_17_x86_64.whl", hash = "sha256:e33677bcf6c2bdee7f25f3b38da7a204ab761e3b6763cbb2a413a5300c151059"},
+    {file = "mysql_connector_python-8.2.0-cp38-cp38-win_amd64.whl", hash = "sha256:55a58e57824b03f31befdd460b1dd173a05605bfac25278cd9845f3927c94399"},
+    {file = "mysql_connector_python-8.2.0-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:86e30370b6c38a9aaeae042eade5eea95000f6eb93b3802a8a215750a29a48c1"},
+    {file = "mysql_connector_python-8.2.0-cp39-cp39-macosx_12_0_x86_64.whl", hash = "sha256:6ac2c0d9c0248df8a62a736ae9024e1934acdbdf9ce3b2ab57b2a99c1da5f028"},
+    {file = "mysql_connector_python-8.2.0-cp39-cp39-manylinux_2_17_aarch64.whl", hash = "sha256:8c3ed071e19981e8e4ae64c1e3ded050571637a8d519669c03be5e1029c04ef7"},
+    {file = "mysql_connector_python-8.2.0-cp39-cp39-manylinux_2_17_x86_64.whl", hash = "sha256:717472cab0c4d5000cf60797be4d453b60d9ec98ec446c1e3c399fdd43941cb9"},
+    {file = "mysql_connector_python-8.2.0-cp39-cp39-win_amd64.whl", hash = "sha256:df033ca9c76f3a7c3500baea109127bc872c79431e9de691ffce4c2878af2828"},
+    {file = "mysql_connector_python-8.2.0-py2.py3-none-any.whl", hash = "sha256:59d4ea8253edbca7cbd1ac25ed524fcf5d8e34ee7ef5fb1be9e3026852b88126"},
+]
+
+[package.dependencies]
+protobuf = ">=4.21.1,<=4.21.12"
+
+[package.extras]
+compression = ["lz4 (>=2.1.6,<=4.3.2)", "zstandard (>=0.12.0,<=0.19.0)"]
+dns-srv = ["dnspython (>=1.16.0,<=2.3.0)"]
+gssapi = ["gssapi (>=1.6.9,<=1.8.2)"]
+opentelemetry = ["Deprecated (>=1.2.6)", "typing-extensions (>=3.7.4)", "zipp (>=0.5)"]
+
 [[package]]
 name = "nest-asyncio"
 version = "1.5.8"
@@ -4292,24 +4377,25 @@ testing = ["google-api-core[grpc] (>=1.31.5)"]
 
 [[package]]
 name = "protobuf"
-version = "4.24.4"
+version = "4.21.12"
 description = ""
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "protobuf-4.24.4-cp310-abi3-win32.whl", hash = "sha256:ec9912d5cb6714a5710e28e592ee1093d68c5ebfeda61983b3f40331da0b1ebb"},
+    {file = "protobuf-4.21.12-cp310-abi3-win32.whl", hash = "sha256:b135410244ebe777db80298297a97fbb4c862c881b4403b71bac9d4107d61fd1"},
-    {file = "protobuf-4.24.4-cp310-abi3-win_amd64.whl", hash = "sha256:1badab72aa8a3a2b812eacfede5020472e16c6b2212d737cefd685884c191085"},
+    {file = "protobuf-4.21.12-cp310-abi3-win_amd64.whl", hash = "sha256:89f9149e4a0169cddfc44c74f230d7743002e3aa0b9472d8c28f0388102fc4c2"},
-    {file = "protobuf-4.24.4-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:8e61a27f362369c2f33248a0ff6896c20dcd47b5d48239cb9720134bef6082e4"},
+    {file = "protobuf-4.21.12-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:299ea899484ee6f44604deb71f424234f654606b983cb496ea2a53e3c63ab791"},
-    {file = "protobuf-4.24.4-cp37-abi3-manylinux2014_aarch64.whl", hash = "sha256:bffa46ad9612e6779d0e51ae586fde768339b791a50610d85eb162daeb23661e"},
+    {file = "protobuf-4.21.12-cp37-abi3-manylinux2014_aarch64.whl", hash = "sha256:d1736130bce8cf131ac7957fa26880ca19227d4ad68b4888b3be0dea1f95df97"},
-    {file = "protobuf-4.24.4-cp37-abi3-manylinux2014_x86_64.whl", hash = "sha256:b493cb590960ff863743b9ff1452c413c2ee12b782f48beca77c8da3e2ffe9d9"},
+    {file = "protobuf-4.21.12-cp37-abi3-manylinux2014_x86_64.whl", hash = "sha256:78a28c9fa223998472886c77042e9b9afb6fe4242bd2a2a5aced88e3f4422aa7"},
-    {file = "protobuf-4.24.4-cp37-cp37m-win32.whl", hash = "sha256:dbbed8a56e56cee8d9d522ce844a1379a72a70f453bde6243e3c86c30c2a3d46"},
+    {file = "protobuf-4.21.12-cp37-cp37m-win32.whl", hash = "sha256:3d164928ff0727d97022957c2b849250ca0e64777ee31efd7d6de2e07c494717"},
-    {file = "protobuf-4.24.4-cp37-cp37m-win_amd64.whl", hash = "sha256:6b7d2e1c753715dcfe9d284a25a52d67818dd43c4932574307daf836f0071e37"},
+    {file = "protobuf-4.21.12-cp37-cp37m-win_amd64.whl", hash = "sha256:f45460f9ee70a0ec1b6694c6e4e348ad2019275680bd68a1d9314b8c7e01e574"},
-    {file = "protobuf-4.24.4-cp38-cp38-win32.whl", hash = "sha256:02212557a76cd99574775a81fefeba8738d0f668d6abd0c6b1d3adcc75503dbe"},
+    {file = "protobuf-4.21.12-cp38-cp38-win32.whl", hash = "sha256:6ab80df09e3208f742c98443b6166bcb70d65f52cfeb67357d52032ea1ae9bec"},
-    {file = "protobuf-4.24.4-cp38-cp38-win_amd64.whl", hash = "sha256:2fa3886dfaae6b4c5ed2730d3bf47c7a38a72b3a1f0acb4d4caf68e6874b947b"},
+    {file = "protobuf-4.21.12-cp38-cp38-win_amd64.whl", hash = "sha256:1f22ac0ca65bb70a876060d96d914dae09ac98d114294f77584b0d2644fa9c30"},
-    {file = "protobuf-4.24.4-cp39-cp39-win32.whl", hash = "sha256:b77272f3e28bb416e2071186cb39efd4abbf696d682cbb5dc731308ad37fa6dd"},
+    {file = "protobuf-4.21.12-cp39-cp39-win32.whl", hash = "sha256:27f4d15021da6d2b706ddc3860fac0a5ddaba34ab679dc182b60a8bb4e1121cc"},
-    {file = "protobuf-4.24.4-cp39-cp39-win_amd64.whl", hash = "sha256:9fee5e8aa20ef1b84123bb9232b3f4a5114d9897ed89b4b8142d81924e05d79b"},
+    {file = "protobuf-4.21.12-cp39-cp39-win_amd64.whl", hash = "sha256:237216c3326d46808a9f7c26fd1bd4b20015fb6867dc5d263a493ef9a539293b"},
-    {file = "protobuf-4.24.4-py3-none-any.whl", hash = "sha256:80797ce7424f8c8d2f2547e2d42bfbb6c08230ce5832d6c099a37335c9c90a92"},
+    {file = "protobuf-4.21.12-py2.py3-none-any.whl", hash = "sha256:a53fd3f03e578553623272dc46ac2f189de23862e68565e83dde203d41b76fc5"},
-    {file = "protobuf-4.24.4.tar.gz", hash = "sha256:5a70731910cd9104762161719c3d883c960151eea077134458503723b60e3667"},
+    {file = "protobuf-4.21.12-py3-none-any.whl", hash = "sha256:b98d0148f84e3a3c569e19f52103ca1feacdac0d2df8d6533cf983d1fda28462"},
+    {file = "protobuf-4.21.12.tar.gz", hash = "sha256:7cd532c4566d0e6feafecc1059d04c7915aec8e182d1cf7adee8b24ef1e2e6ab"},
 ]
 
 [[package]]
@@ -4565,6 +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"
@@ -4934,21 +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"
@@ -5925,6 +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"
@@ -6668,30 +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"]
@@ -7378,6 +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"
@@ -7396,15 +7540,17 @@ 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"]
 json = ["llama-hub"]
 llama2 = ["replicate"]
 milvus = ["pymilvus"]
+mysql = ["mysql-connector-python"]
 opensearch = ["opensearch-py"]
 opensource = ["gpt4all", "sentence-transformers", "torch"]
 pinecone = ["pinecone-client"]
@@ -7416,8 +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 = "fa041b870ce060414e7c2d2bc21c2c4909aff117b40a161f2eaafafe44136597"
+content-hash = "ea063cadfefd23d4c9b2a25c9096efe6bcedc367136d819ccb1fd2f510a91206"

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "embedchain"
-version = "0.1.6"
+version = "0.1.17"
 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 }
@@ -133,6 +133,9 @@ schema = "^0.7.5"
 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"
@@ -166,7 +169,7 @@ huggingface_hub=["huggingface_hub"]
 cohere = ["cohere"]
 milvus = ["pymilvus"]
 dataloaders=[
-    "youtube-transcripts-api",
+    "youtube-transcript-api",
     "beautifulsoup4",
     "docx2txt",
     "duckduckgo-search",
@@ -188,6 +191,12 @@ 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]
 

tests/chunkers/test_chunkers.py

@@ -1,3 +1,5 @@
+from embedchain.chunkers.common_chunker import CommonChunker
+from embedchain.chunkers.discourse import DiscourseChunker
 from embedchain.chunkers.docs_site import DocsSiteChunker
 from embedchain.chunkers.docx_file import DocxFileChunker
 from embedchain.chunkers.gmail import GmailChunker
@@ -9,6 +11,7 @@ from embedchain.chunkers.pdf_file import PdfFileChunker
 from embedchain.chunkers.postgres import PostgresChunker
 from embedchain.chunkers.qna_pair import QnaPairChunker
 from embedchain.chunkers.sitemap import SitemapChunker
+from embedchain.chunkers.slack import SlackChunker
 from embedchain.chunkers.table import TableChunker
 from embedchain.chunkers.text import TextChunker
 from embedchain.chunkers.web_page import WebPageChunker
@@ -35,6 +38,9 @@ chunker_common_config = {
     OpenAPIChunker: {"chunk_size": 1000, "chunk_overlap": 0, "length_function": len},
     GmailChunker: {"chunk_size": 1000, "chunk_overlap": 0, "length_function": len},
     PostgresChunker: {"chunk_size": 1000, "chunk_overlap": 0, "length_function": len},
+    SlackChunker: {"chunk_size": 1000, "chunk_overlap": 0, "length_function": len},
+    DiscourseChunker: {"chunk_size": 1000, "chunk_overlap": 0, "length_function": len},
+    CommonChunker: {"chunk_size": 1000, "chunk_overlap": 0, "length_function": len},
 }
 
 

tests/embedchain/test_embedchain.py

@@ -22,7 +22,7 @@ def test_whole_app(app_instance, mocker):
     knowledge = "lorem ipsum dolor sit amet, consectetur adipiscing"
 
     mocker.patch.object(EmbedChain, "add")
-    mocker.patch.object(EmbedChain, "retrieve_from_database")
+    mocker.patch.object(EmbedChain, "_retrieve_from_database")
     mocker.patch.object(BaseLlm, "get_answer_from_llm", return_value=knowledge)
     mocker.patch.object(BaseLlm, "get_llm_model_answer", return_value=knowledge)
     mocker.patch.object(BaseLlm, "generate_prompt")

tests/helper_classes/test_json_serializable.py

@@ -53,7 +53,7 @@ class TestJsonSerializable(unittest.TestCase):
         app: SecondTestClass = SecondTestClass().deserialize(serial)
         self.assertTrue(app.default)
         # If we register and try again with the same serial, it should work
-        SecondTestClass.register_class_as_deserializable(SecondTestClass)
+        SecondTestClass._register_class_as_deserializable(SecondTestClass)
         app: SecondTestClass = SecondTestClass().deserialize(serial)
         self.assertFalse(app.default)
 

tests/llm/test_chat.py

@@ -14,7 +14,7 @@ class TestApp(unittest.TestCase):
         os.environ["OPENAI_API_KEY"] = "test_key"
         self.app = App(config=AppConfig(collect_metrics=False))
 
-    @patch.object(App, "retrieve_from_database", return_value=["Test context"])
+    @patch.object(App, "_retrieve_from_database", return_value=["Test context"])
     @patch.object(BaseLlm, "get_answer_from_llm", return_value="Test answer")
     def test_chat_with_memory(self, mock_get_answer, mock_retrieve):
         """
@@ -28,7 +28,7 @@ class TestApp(unittest.TestCase):
         - After the first call, 'memory.chat_memory.add_user_message' and 'memory.chat_memory.add_ai_message' are
         - During the second call, the 'chat' method uses the chat history from the first call.
 
-        The test isolates the 'chat' method behavior by mocking out 'retrieve_from_database', 'get_answer_from_llm' and
+        The test isolates the 'chat' method behavior by mocking out '_retrieve_from_database', 'get_answer_from_llm' and
         'memory' methods.
         """
         config = AppConfig(collect_metrics=False)
@@ -42,7 +42,7 @@ class TestApp(unittest.TestCase):
             self.assertEqual(second_answer, "Test answer")
             mock_history.assert_called_with(app.config.id, "Test query 2", "Test answer")
 
-    @patch.object(App, "retrieve_from_database", return_value=["Test context"])
+    @patch.object(App, "_retrieve_from_database", return_value=["Test context"])
     @patch.object(BaseLlm, "get_answer_from_llm", return_value="Test answer")
     def test_template_replacement(self, mock_get_answer, mock_retrieve):
         """
@@ -73,7 +73,7 @@ class TestApp(unittest.TestCase):
         """
         Test where filter
         """
-        with patch.object(self.app, "retrieve_from_database") as mock_retrieve:
+        with patch.object(self.app, "_retrieve_from_database") as mock_retrieve:
             mock_retrieve.return_value = ["Test context"]
             with patch.object(self.app.llm, "get_llm_model_answer") as mock_answer:
                 mock_answer.return_value = "Test answer"
@@ -89,19 +89,19 @@ class TestApp(unittest.TestCase):
     def test_chat_with_where_in_chat_config(self):
         """
         This test checks the functionality of the 'chat' method in the App class.
-        It simulates a scenario where the 'retrieve_from_database' method returns a context list based on
+        It simulates a scenario where the '_retrieve_from_database' method returns a context list based on
         a where filter and 'get_llm_model_answer' returns an expected answer string.
 
-        The 'chat' method is expected to call 'retrieve_from_database' with the where filter specified
+        The 'chat' method is expected to call '_retrieve_from_database' with the where filter specified
         in the BaseLlmConfig and 'get_llm_model_answer' methods appropriately and return the right answer.
 
         Key assumptions tested:
-        - 'retrieve_from_database' method is called exactly once with arguments: "Test query" and an instance of
+        - '_retrieve_from_database' method is called exactly once with arguments: "Test query" and an instance of
             BaseLlmConfig.
         - 'get_llm_model_answer' is called exactly once. The specific arguments are not checked in this test.
         - 'chat' method returns the value it received from 'get_llm_model_answer'.
 
-        The test isolates the 'chat' method behavior by mocking out 'retrieve_from_database' and
+        The test isolates the 'chat' method behavior by mocking out '_retrieve_from_database' and
         'get_llm_model_answer' methods.
         """
         with patch.object(self.app.llm, "get_llm_model_answer") as mock_answer:

tests/llm/test_query.py

@@ -16,7 +16,7 @@ def app():
 
 @patch("chromadb.api.models.Collection.Collection.add", MagicMock)
 def test_query(app):
-    with patch.object(app, "retrieve_from_database") as mock_retrieve:
+    with patch.object(app, "_retrieve_from_database") as mock_retrieve:
         mock_retrieve.return_value = ["Test context"]
         with patch.object(app.llm, "get_llm_model_answer") as mock_answer:
             mock_answer.return_value = "Test answer"
@@ -58,7 +58,7 @@ def test_app_passing(mock_get_answer):
 
 @patch("chromadb.api.models.Collection.Collection.add", MagicMock)
 def test_query_with_where_in_params(app):
-    with patch.object(app, "retrieve_from_database") as mock_retrieve:
+    with patch.object(app, "_retrieve_from_database") as mock_retrieve:
         mock_retrieve.return_value = ["Test context"]
         with patch.object(app.llm, "get_llm_model_answer") as mock_answer:
             mock_answer.return_value = "Test answer"

tests/loaders/test_discourse.py

@@ -0,0 +1,119 @@
+import pytest
+import requests
+
+from embedchain.loaders.discourse import DiscourseLoader
+
+
+@pytest.fixture
+def discourse_loader_config():
+    return {
+        "domain": "https://example.com/",
+    }
+
+
+@pytest.fixture
+def discourse_loader(discourse_loader_config):
+    return DiscourseLoader(config=discourse_loader_config)
+
+
+def test_discourse_loader_init_with_valid_config():
+    config = {"domain": "https://example.com/"}
+    loader = DiscourseLoader(config=config)
+    assert loader.domain == "https://example.com/"
+
+
+def test_discourse_loader_init_with_missing_config():
+    with pytest.raises(ValueError, match="DiscourseLoader requires a config"):
+        DiscourseLoader()
+
+
+def test_discourse_loader_init_with_missing_domain():
+    config = {"another_key": "value"}
+    with pytest.raises(ValueError, match="DiscourseLoader requires a domain"):
+        DiscourseLoader(config=config)
+
+
+def test_discourse_loader_check_query_with_valid_query(discourse_loader):
+    discourse_loader._check_query("sample query")
+
+
+def test_discourse_loader_check_query_with_empty_query(discourse_loader):
+    with pytest.raises(ValueError, match="DiscourseLoader requires a query"):
+        discourse_loader._check_query("")
+
+
+def test_discourse_loader_check_query_with_invalid_query_type(discourse_loader):
+    with pytest.raises(ValueError, match="DiscourseLoader requires a query"):
+        discourse_loader._check_query(123)
+
+
+def test_discourse_loader_load_post_with_valid_post_id(discourse_loader, monkeypatch):
+    def mock_get(*args, **kwargs):
+        class MockResponse:
+            def json(self):
+                return {"raw": "Sample post content"}
+
+            def raise_for_status(self):
+                pass
+
+        return MockResponse()
+
+    monkeypatch.setattr(requests, "get", mock_get)
+
+    post_data = discourse_loader._load_post(123)
+
+    assert post_data["content"] == "Sample post content"
+    assert "meta_data" in post_data
+
+
+def test_discourse_loader_load_post_with_invalid_post_id(discourse_loader, monkeypatch, caplog):
+    def mock_get(*args, **kwargs):
+        class MockResponse:
+            def raise_for_status(self):
+                raise requests.exceptions.RequestException("Test error")
+
+        return MockResponse()
+
+    monkeypatch.setattr(requests, "get", mock_get)
+
+    discourse_loader._load_post(123)
+
+    assert "Failed to load post" in caplog.text
+
+
+def test_discourse_loader_load_data_with_valid_query(discourse_loader, monkeypatch):
+    def mock_get(*args, **kwargs):
+        class MockResponse:
+            def json(self):
+                return {"grouped_search_result": {"post_ids": [123, 456, 789]}}
+
+            def raise_for_status(self):
+                pass
+
+        return MockResponse()
+
+    monkeypatch.setattr(requests, "get", mock_get)
+
+    def mock_load_post(*args, **kwargs):
+        return {
+            "content": "Sample post content",
+            "meta_data": {
+                "url": "https://example.com/posts/123.json",
+                "created_at": "2021-01-01",
+                "username": "test_user",
+                "topic_slug": "test_topic",
+                "score": 10,
+            },
+        }
+
+    monkeypatch.setattr(discourse_loader, "_load_post", mock_load_post)
+
+    data = discourse_loader.load_data("sample query")
+
+    assert len(data["data"]) == 3
+    assert data["data"][0]["content"] == "Sample post content"
+    assert data["data"][0]["meta_data"]["url"] == "https://example.com/posts/123.json"
+    assert data["data"][0]["meta_data"]["created_at"] == "2021-01-01"
+    assert data["data"][0]["meta_data"]["username"] == "test_user"
+    assert data["data"][0]["meta_data"]["topic_slug"] == "test_topic"
+    assert data["data"][0]["meta_data"]["score"] == 10

tests/loaders/test_mysql.py

@@ -0,0 +1,77 @@
+import hashlib
+from unittest.mock import MagicMock
+
+import pytest
+
+from embedchain.loaders.mysql import MySQLLoader
+
+
+@pytest.fixture
+def mysql_loader(mocker):
+    with mocker.patch("mysql.connector.connection.MySQLConnection"):
+        config = {
+            "host": "localhost",
+            "port": "3306",
+            "user": "your_username",
+            "password": "your_password",
+            "database": "your_database",
+        }
+        loader = MySQLLoader(config=config)
+        yield loader
+
+
+def test_mysql_loader_initialization(mysql_loader):
+    assert mysql_loader.config is not None
+    assert mysql_loader.connection is not None
+    assert mysql_loader.cursor is not None
+
+
+def test_mysql_loader_invalid_config():
+    with pytest.raises(ValueError, match="Invalid sql config: None"):
+        MySQLLoader(config=None)
+
+
+def test_mysql_loader_setup_loader_successful(mysql_loader):
+    assert mysql_loader.connection is not None
+    assert mysql_loader.cursor is not None
+
+
+def test_mysql_loader_setup_loader_connection_error(mysql_loader, mocker):
+    mocker.patch("mysql.connector.connection.MySQLConnection", side_effect=IOError("Mocked connection error"))
+    with pytest.raises(ValueError, match="Unable to connect with the given config:"):
+        mysql_loader._setup_loader(config={})
+
+
+def test_mysql_loader_check_query_successful(mysql_loader):
+    query = "SELECT * FROM table"
+    mysql_loader._check_query(query=query)
+
+
+def test_mysql_loader_check_query_invalid(mysql_loader):
+    with pytest.raises(ValueError, match="Invalid mysql query: 123"):
+        mysql_loader._check_query(query=123)
+
+
+def test_mysql_loader_load_data_successful(mysql_loader, mocker):
+    mock_cursor = MagicMock()
+    mocker.patch.object(mysql_loader, "cursor", mock_cursor)
+    mock_cursor.fetchall.return_value = [(1, "data1"), (2, "data2")]
+
+    query = "SELECT * FROM table"
+    result = mysql_loader.load_data(query)
+
+    assert "doc_id" in result
+    assert "data" in result
+    assert len(result["data"]) == 2
+    assert result["data"][0]["meta_data"]["url"] == query
+    assert result["data"][1]["meta_data"]["url"] == query
+
+    doc_id = hashlib.sha256((query + ", ".join([d["content"] for d in result["data"]])).encode()).hexdigest()
+
+    assert result["doc_id"] == doc_id
+    assert mock_cursor.execute.called_with(query)
+
+
+def test_mysql_loader_load_data_invalid_query(mysql_loader):
+    with pytest.raises(ValueError, match="Invalid mysql query: 123"):
+        mysql_loader.load_data(query=123)

tests/loaders/test_postgres.py

@@ -36,8 +36,8 @@ def test_load_data(postgres_loader, monkeypatch):
     assert "doc_id" in result
     assert "data" in result
     assert len(result["data"]) == 2
-    assert result["data"][0]["meta_data"]["url"] == f"postgres_query-({query})"
+    assert result["data"][0]["meta_data"]["url"] == query
-    assert result["data"][1]["meta_data"]["url"] == f"postgres_query-({query})"
+    assert result["data"][1]["meta_data"]["url"] == query
     assert mock_cursor.execute.called_with(query)
 
 

tests/loaders/test_slack.py

@@ -0,0 +1,47 @@
+import pytest
+
+from embedchain.loaders.slack import SlackLoader
+
+
+@pytest.fixture
+def slack_loader(mocker, monkeypatch):
+    # Mocking necessary dependencies
+    mocker.patch("slack_sdk.WebClient")
+    mocker.patch("ssl.create_default_context")
+    mocker.patch("certifi.where")
+
+    monkeypatch.setenv("SLACK_USER_TOKEN", "slack_user_token")
+
+    return SlackLoader()
+
+
+def test_slack_loader_initialization(slack_loader):
+    assert slack_loader.client is not None
+    assert slack_loader.config == {"base_url": "https://www.slack.com/api/"}
+
+
+def test_slack_loader_setup_loader(slack_loader):
+    slack_loader._setup_loader({"base_url": "https://custom.slack.api/"})
+
+    assert slack_loader.client is not None
+
+
+def test_slack_loader_check_query(slack_loader):
+    valid_json_query = "test_query"
+    invalid_query = 123
+
+    slack_loader._check_query(valid_json_query)
+
+    with pytest.raises(ValueError):
+        slack_loader._check_query(invalid_query)
+
+
+def test_slack_loader_load_data(slack_loader, mocker):
+    valid_json_query = "in:random"
+
+    mocker.patch.object(slack_loader.client, "search_messages", return_value={"messages": {}})
+
+    result = slack_loader.load_data(valid_json_query)
+
+    assert "doc_id" in result
+    assert "data" in result

tests/loaders/test_web_page.py

@@ -27,7 +27,7 @@ def test_load_data(web_page_loader):
             </body>
         </html>
     """
-    with patch("embedchain.loaders.web_page.requests.get", return_value=mock_response):
+    with patch("embedchain.loaders.web_page.WebPageLoader._session.get", return_value=mock_response):
         result = web_page_loader.load_data(page_url)
 
     content = web_page_loader._get_clean_content(mock_response.content, page_url)

tests/telemetry/test_posthog.py

@@ -29,7 +29,7 @@ class TestAnonymousTelemetry:
         mocker.patch("embedchain.telemetry.posthog.CONFIG_FILE", str(config_file))
         telemetry = AnonymousTelemetry()
 
-        user_id = telemetry.get_user_id()
+        user_id = telemetry._get_user_id()
         assert user_id == "unique_user_id"
         assert config_file.read() == '{"user_id": "unique_user_id"}'
 

tests/test_utils.py

@@ -9,6 +9,7 @@ CONFIG_YAMLS = [
     "configs/chunker.yaml",
     "configs/cohere.yaml",
     "configs/full-stack.yaml",
+    "configs/gpt4.yaml",
     "configs/gpt4all.yaml",
     "configs/huggingface.yaml",
     "configs/jina.yaml",
@@ -21,16 +22,15 @@ CONFIG_YAMLS = [
 ]
 
 
-class TestAllConfigYamls:
+def test_all_config_yamls():
-    def test_all_config_yamls(self):
+    """Test that all config yamls are valid."""
-        """Test that all config yamls are valid."""
+    for config_yaml in CONFIG_YAMLS:
-        for config_yaml in CONFIG_YAMLS:
+        with open(config_yaml, "r") as f:
-            with open(config_yaml, "r") as f:
+            config = yaml.safe_load(f)
-                config = yaml.safe_load(f)
+        assert config is not None
-            assert config is not None
 
-            try:
+        try:
-                validate_yaml_config(config)
+            validate_yaml_config(config)
-            except Exception as e:
+        except Exception as e:
-                print(f"Error in {config_yaml}: {e}")
+            print(f"Error in {config_yaml}: {e}")
-                raise e
+            raise e