[Feature] OpenAI Function Calling (#1224)

docs/components/llms.mdx

@@ -68,125 +68,75 @@ llm:
 </CodeGroup>
 
 ### Function Calling
-To enable [function calling](https://platform.openai.com/docs/guides/function-calling) in your application using embedchain and OpenAI, you need to pass functions into `OpenAILlm` class as an array of functions. Here are several ways in which you can achieve that:
+Embedchain supports OpenAI [Function calling](https://platform.openai.com/docs/guides/function-calling) with a single function. It accepts inputs in accordance with the [Langchain interface](https://python.langchain.com/docs/modules/model_io/chat/function_calling#legacy-args-functions-and-function_call).
 
-Examples:
-<Accordion title="Using Pydantic Models">
+<Accordion title="Pydantic Model">
   ```python
-import os
-from embedchain import App
-from embedchain.llm.openai import OpenAILlm
-import requests
-from pydantic import BaseModel, Field, ValidationError, field_validator
+  from pydantic import BaseModel
 
-os.environ["OPENAI_API_KEY"] = "sk-xxx"
+  class multiply(BaseModel):
+      """Multiply two integers together."""
 
-class QA(BaseModel):
-    """
-    A question and answer pair.
-    """
-
-    question: str = Field(
-        ..., description="The question.", example="What is a mountain?"
-    )
-    answer: str = Field(
-        ..., description="The answer.", example="A mountain is a hill."
-    )
-    person_who_is_asking: str = Field(
-        ..., description="The person who is asking the question.", example="John"
-    )
-
-    @field_validator("question")
-    def question_must_end_with_a_question_mark(cls, v):
-        """
-        Validate that the question ends with a question mark.
-        """
-        if not v.endswith("?"):
-            raise ValueError("question must end with a question mark")
-        return v
-
-    @field_validator("answer")
-    def answer_must_end_with_a_period(cls, v):
-        """
-        Validate that the answer ends with a period.
-        """
-        if not v.endswith("."):
-            raise ValueError("answer must end with a period")
-        return v
-
-llm = OpenAILlm(config=None,functions=[QA])
-app = App(llm=llm)
-
-result = app.query("Hey I am Sid. What is a mountain? A mountain is a hill.")
-
-print(result)
+      a: int = Field(..., description="First integer")
+      b: int = Field(..., description="Second integer")
   ```
-  </Accordion>
+</Accordion>
   
-  <Accordion title="Using OpenAI JSON schema">
+<Accordion title="Python function">
+  ```python
+  def multiply(a: int, b: int) -> int:
+      """Multiply two integers together.
+
+      Args:
+          a: First integer
+          b: Second integer
+      """
+      return a * b
+  ```
+</Accordion>
+<Accordion title="OpenAI tool dictionary">
+  ```python
+  multiply = {
+    "type": "function",
+    "function": {
+      "name": "multiply",
+      "description": "Multiply two integers together.",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "a": {
+            "description": "First integer",
+            "type": "integer"
+          },
+          "b": {
+            "description": "Second integer",
+            "type": "integer"
+          }
+        },
+        "required": [
+          "a",
+          "b"
+        ]
+      }
+    }
+  }
+  ```
+</Accordion>
+
+With any of the previous inputs, the OpenAI LLM can be queried to provide the appropriate arguments for the function.
+
 ```python
 import os
 from embedchain import App
 from embedchain.llm.openai import OpenAILlm
-import requests
-from pydantic import BaseModel, Field, ValidationError, field_validator
 
 os.environ["OPENAI_API_KEY"] = "sk-xxx"
 
-json_schema = {
-    "name": "get_qa",
-    "description": "A question and answer pair and the user who is asking the question.",
-    "parameters": {
-        "type": "object",
-        "properties": {
-            "question": {"type": "string", "description": "The question."},
-            "answer": {"type": "string", "description": "The answer."},
-            "person_who_is_asking": {
-                "type": "string",
-                "description": "The person who is asking the question.",
-            }
-        },
-        "required": ["question", "answer", "person_who_is_asking"],
-    },
-}
-
-llm = OpenAILlm(config=None,functions=[json_schema])
+llm = OpenAILlm(tools=multiply)
 app = App(llm=llm)
 
-result = app.query("Hey I am Sid. What is a mountain? A mountain is a hill.")
-
-print(result)
-  ```
-  </Accordion>
-  <Accordion title="Using actual python functions">
-  ```python
-import os
-from embedchain import App
-from embedchain.llm.openai import OpenAILlm
-import requests
-from pydantic import BaseModel, Field, ValidationError, field_validator
-
-os.environ["OPENAI_API_KEY"] = "sk-xxx"
-
-def find_info_of_pokemon(pokemon: str):
-    """
-    Find the information of the given pokemon.
-    Args:
-        pokemon: The pokemon.
-    """
-    req = requests.get(f"https://pokeapi.co/api/v2/pokemon/{pokemon}")
-    if req.status_code == 404:
-        raise ValueError("pokemon not found")
-    return req.json()
-
-llm = OpenAILlm(config=None,functions=[find_info_of_pokemon])
-app = App(llm=llm)
-
-result = app.query("Tell me more about the pokemon pikachu.")
-
-print(result)
+result = app.query("What is the result of 125 multiplied by fifteen?")
 ```
-</Accordion>
 
 ## Google AI
 

embedchain/embedder/huggingface.py

@@ -1,6 +1,6 @@
 from typing import Optional
 
-from langchain.embeddings import HuggingFaceEmbeddings
+from langchain_community.embeddings import HuggingFaceEmbeddings
 
 from embedchain.config import BaseEmbedderConfig
 from embedchain.embedder.base import BaseEmbedder

embedchain/embedder/openai.py

@@ -2,7 +2,7 @@ import os
 from typing import Optional
 
 from chromadb.utils.embedding_functions import OpenAIEmbeddingFunction
-from langchain.embeddings import AzureOpenAIEmbeddings
+from langchain_community.embeddings import AzureOpenAIEmbeddings
 
 from embedchain.config import BaseEmbedderConfig
 from embedchain.embedder.base import BaseEmbedder

embedchain/embedder/vertexai.py

@@ -1,6 +1,6 @@
 from typing import Optional
 
-from langchain.embeddings import VertexAIEmbeddings
+from langchain_community.embeddings import VertexAIEmbeddings
 
 from embedchain.config import BaseEmbedderConfig
 from embedchain.embedder.base import BaseEmbedder

embedchain/llm/anthropic.py

@@ -19,7 +19,7 @@ class AnthropicLlm(BaseLlm):
 
     @staticmethod
     def _get_answer(prompt: str, config: BaseLlmConfig) -> str:
-        from langchain.chat_models import ChatAnthropic
+        from langchain_community.chat_models import ChatAnthropic
 
         chat = ChatAnthropic(
             anthropic_api_key=os.environ["ANTHROPIC_API_KEY"], temperature=config.temperature, model=config.model

embedchain/llm/aws_bedrock.py

@@ -1,7 +1,7 @@
 import os
 from typing import Optional
 
-from langchain.llms import Bedrock
+from langchain_community.llms import Bedrock
 
 from embedchain.config import BaseLlmConfig
 from embedchain.helpers.json_serializable import register_deserializable

embedchain/llm/azure_openai.py

@@ -16,7 +16,7 @@ class AzureOpenAILlm(BaseLlm):
 
     @staticmethod
     def _get_answer(prompt: str, config: BaseLlmConfig) -> str:
-        from langchain.chat_models import AzureChatOpenAI
+        from langchain_community.chat_models import AzureChatOpenAI
 
         if not config.deployment_name:
             raise ValueError("Deployment name must be provided for Azure OpenAI")

embedchain/llm/cohere.py

@@ -2,7 +2,7 @@ import importlib
 import os
 from typing import Optional
 
-from langchain.llms.cohere import Cohere
+from langchain_community.llms.cohere import Cohere
 
 from embedchain.config import BaseLlmConfig
 from embedchain.helpers.json_serializable import register_deserializable

embedchain/llm/gpt4all.py

@@ -26,7 +26,8 @@ class GPT4ALLLlm(BaseLlm):
     @staticmethod
     def _get_instance(model):
         try:
-            from langchain.llms.gpt4all import GPT4All as LangchainGPT4All
+            from langchain_community.llms.gpt4all import \
+                GPT4All as LangchainGPT4All
         except ModuleNotFoundError:
             raise ModuleNotFoundError(
                 "The GPT4All python package is not installed. Please install it with `pip install --upgrade embedchain[opensource]`"  # noqa E501

embedchain/llm/huggingface.py

@@ -3,8 +3,8 @@ import logging
 import os
 from typing import Optional
 
-from langchain.llms.huggingface_endpoint import HuggingFaceEndpoint
-from langchain.llms.huggingface_hub import HuggingFaceHub
+from langchain_community.llms.huggingface_endpoint import HuggingFaceEndpoint
+from langchain_community.llms.huggingface_hub import HuggingFaceHub
 
 from embedchain.config import BaseLlmConfig
 from embedchain.helpers.json_serializable import register_deserializable

embedchain/llm/jina.py

@@ -1,8 +1,8 @@
 import os
 from typing import Optional
 
-from langchain.chat_models import JinaChat
 from langchain.schema import HumanMessage, SystemMessage
+from langchain_community.chat_models import JinaChat
 
 from embedchain.config import BaseLlmConfig
 from embedchain.helpers.json_serializable import register_deserializable

embedchain/llm/llama2.py

@@ -2,7 +2,7 @@ import importlib
 import os
 from typing import Optional
 
-from langchain.llms.replicate import Replicate
+from langchain_community.llms.replicate import Replicate
 
 from embedchain.config import BaseLlmConfig
 from embedchain.helpers.json_serializable import register_deserializable

embedchain/llm/ollama.py

@@ -4,7 +4,7 @@ from typing import Optional, Union
 from langchain.callbacks.manager import CallbackManager
 from langchain.callbacks.stdout import StdOutCallbackHandler
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
-from langchain.llms.ollama import Ollama
+from langchain_community.llms.ollama import Ollama
 
 from embedchain.config import BaseLlmConfig
 from embedchain.helpers.json_serializable import register_deserializable

embedchain/llm/openai.py

@@ -1,9 +1,11 @@
 import json
 import os
-from typing import Any, Optional
+from typing import Any, Callable, Dict, Optional, Type, Union
 
-from langchain.chat_models import ChatOpenAI
-from langchain.schema import AIMessage, HumanMessage, SystemMessage
+from langchain.schema import BaseMessage, HumanMessage, SystemMessage
+from langchain_core.tools import BaseTool
+from langchain_openai import ChatOpenAI
+from pydantic import BaseModel
 
 from embedchain.config import BaseLlmConfig
 from embedchain.helpers.json_serializable import register_deserializable
@@ -12,8 +14,12 @@ from embedchain.llm.base import BaseLlm
 
 @register_deserializable
 class OpenAILlm(BaseLlm):
-    def __init__(self, config: Optional[BaseLlmConfig] = None, functions: Optional[dict[str, Any]] = None):
-        self.functions = functions
+    def __init__(
+        self,
+        config: Optional[BaseLlmConfig] = None,
+        tools: Optional[Union[Dict[str, Any], Type[BaseModel], Callable[..., Any], BaseTool]] = None,
+    ):
+        self.tools = tools
         super().__init__(config=config)
 
     def get_llm_model_answer(self, prompt) -> str:
@@ -38,21 +44,27 @@ class OpenAILlm(BaseLlm):
             from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 
             callbacks = config.callbacks if config.callbacks else [StreamingStdOutCallbackHandler()]
-            llm = ChatOpenAI(**kwargs, streaming=config.stream, callbacks=callbacks, api_key=api_key)
+            chat = ChatOpenAI(**kwargs, streaming=config.stream, callbacks=callbacks, api_key=api_key)
         else:
-            llm = ChatOpenAI(**kwargs, api_key=api_key)
+            chat = ChatOpenAI(**kwargs, api_key=api_key)
+        if self.tools:
+            return self._query_function_call(chat, self.tools, messages)
 
-        if self.functions is not None:
-            from langchain.chains.openai_functions import create_openai_fn_runnable
-            from langchain.prompts import ChatPromptTemplate
+        return chat.invoke(messages).content
 
-            structured_prompt = ChatPromptTemplate.from_messages(messages)
-            runnable = create_openai_fn_runnable(functions=self.functions, prompt=structured_prompt, llm=llm)
-            fn_res = runnable.invoke(
-                {
-                    "input": prompt,
-                }
-            )
-            messages.append(AIMessage(content=json.dumps(fn_res)))
+    def _query_function_call(
+        self,
+        chat: ChatOpenAI,
+        tools: Optional[Union[Dict[str, Any], Type[BaseModel], Callable[..., Any], BaseTool]],
+        messages: list[BaseMessage],
+    ) -> str:
+        from langchain.output_parsers.openai_tools import JsonOutputToolsParser
+        from langchain_core.utils.function_calling import \
+            convert_to_openai_tool
 
-        return llm(messages).content
+        openai_tools = [convert_to_openai_tool(tools)]
+        chat = chat.bind(tools=openai_tools).pipe(JsonOutputToolsParser())
+        try:
+            return json.dumps(chat.invoke(messages)[0])
+        except IndexError:
+            return "Input could not be mapped to the function!"

embedchain/llm/together.py

@@ -2,7 +2,7 @@ import importlib
 import os
 from typing import Optional
 
-from langchain.llms import Together
+from langchain_community.llms import Together
 
 from embedchain.config import BaseLlmConfig
 from embedchain.helpers.json_serializable import register_deserializable

embedchain/llm/vertex_ai.py

@@ -24,7 +24,7 @@ class VertexAILlm(BaseLlm):
 
     @staticmethod
     def _get_answer(prompt: str, config: BaseLlmConfig) -> str:
-        from langchain.chat_models import ChatVertexAI
+        from langchain_community.chat_models import ChatVertexAI
 
         chat = ChatVertexAI(temperature=config.temperature, model=config.model)
 

embedchain/loaders/docx_file.py

@@ -1,7 +1,7 @@
 import hashlib
 
 try:
-    from langchain.document_loaders import Docx2txtLoader
+    from langchain_community.document_loaders import Docx2txtLoader
 except ImportError:
     raise ImportError(
         'Docx file requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'

embedchain/loaders/google_drive.py

@@ -8,8 +8,8 @@ except ImportError:
         "Google Drive requires extra dependencies. Install with `pip install embedchain[googledrive]`"
     ) from None
 
-from langchain.document_loaders import GoogleDriveLoader as Loader
-from langchain.document_loaders import UnstructuredFileIOLoader
+from langchain_community.document_loaders import GoogleDriveLoader as Loader
+from langchain_community.document_loaders import UnstructuredFileIOLoader
 
 from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader

embedchain/loaders/pdf_file.py

@@ -1,7 +1,7 @@
 import hashlib
 
 try:
-    from langchain.document_loaders import PyPDFLoader
+    from langchain_community.document_loaders import PyPDFLoader
 except ImportError:
     raise ImportError(
         'PDF File requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'

embedchain/loaders/rss_feed.py

@@ -28,7 +28,7 @@ class RSSFeedLoader(BaseLoader):
     @staticmethod
     def get_rss_content(url: str):
         try:
-            from langchain.document_loaders import \
+            from langchain_community.document_loaders import \
                 RSSFeedLoader as LangchainRSSFeedLoader
         except ImportError:
             raise ImportError(

embedchain/loaders/unstructured_file.py

@@ -10,7 +10,8 @@ class UnstructuredLoader(BaseLoader):
     def load_data(self, url):
         """Load data from an Unstructured file."""
         try:
-            from langchain.document_loaders import UnstructuredFileLoader
+            from langchain_community.document_loaders import \
+                UnstructuredFileLoader
         except ImportError:
             raise ImportError(
                 'Unstructured file requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'  # noqa: E501

embedchain/loaders/xml.py

@@ -1,7 +1,7 @@
 import hashlib
 
 try:
-    from langchain.document_loaders import UnstructuredXMLLoader
+    from langchain_community.document_loaders import UnstructuredXMLLoader
 except ImportError:
     raise ImportError(
         'XML file requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'

embedchain/loaders/youtube_video.py

@@ -1,7 +1,7 @@
 import hashlib
 
 try:
-    from langchain.document_loaders import YoutubeLoader
+    from langchain_community.document_loaders import YoutubeLoader
 except ImportError:
     raise ImportError(
         'YouTube video requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'

embedchain/vectordb/opensearch.py

@@ -12,8 +12,8 @@ except ImportError:
         "OpenSearch requires extra dependencies. Install with `pip install --upgrade embedchain[opensearch]`"
     ) from None
 
-from langchain.embeddings.openai import OpenAIEmbeddings
-from langchain.vectorstores import OpenSearchVectorSearch
+from langchain_community.embeddings.openai import OpenAIEmbeddings
+from langchain_community.vectorstores import OpenSearchVectorSearch
 
 from embedchain.config import OpenSearchDBConfig
 from embedchain.helpers.json_serializable import register_deserializable

poetry.lock

@@ -3020,22 +3020,23 @@ adal = ["adal (>=1.0.2)"]
 
 [[package]]
 name = "langchain"
-version = "0.0.336"
+version = "0.1.4"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = ">=3.8.1,<4.0"
 files = [
-    {file = "langchain-0.0.336-py3-none-any.whl", hash = "sha256:cbc72c170c5eb67509bf44fb833412a3d4ccf4476136447abd4f10468ef7d4c4"},
-    {file = "langchain-0.0.336.tar.gz", hash = "sha256:2cbb992b0a6975948d35616386d088c2920b66023cb94eb4f4b25e097fa1374d"},
+    {file = "langchain-0.1.4-py3-none-any.whl", hash = "sha256:6befdd6221f5f326092e31a3c19efdc7ce3d7d1f2e2cab065141071451730ed7"},
+    {file = "langchain-0.1.4.tar.gz", hash = "sha256:8767a9461e2b717ce9a35b1fa20659de89ea86ba9c2a4ff516e05d47ab2d195d"},
 ]
 
 [package.dependencies]
 aiohttp = ">=3.8.3,<4.0.0"
-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 = ">=0.0.63,<0.1.0"
+langchain-community = ">=0.0.14,<0.1"
+langchain-core = ">=0.1.16,<0.2"
+langsmith = ">=0.0.83,<0.1"
 numpy = ">=1,<2"
 pydantic = ">=1,<3"
 PyYAML = ">=5.3"
@@ -3044,14 +3045,13 @@ 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 (>=1.13.0,<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 (<2)"]
+azure = ["azure-ai-formrecognizer (>=3.2.1,<4.0.0)", "azure-ai-textanalytics (>=5.3.0,<6.0.0)", "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)", "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)"]
+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)", "cohere (>=4,<5)", "couchbase (>=4.1.9,<5.0.0)", "dashvector (>=1.0.1,<2.0.0)", "databricks-vectorsearch (>=0.21,<0.22)", "datasets (>=2.15.0,<3.0.0)", "dgml-utils (>=0.3.0,<0.4.0)", "esprima (>=4.0.1,<5.0.0)", "faiss-cpu (>=1,<2)", "feedparser (>=6.0.10,<7.0.0)", "fireworks-ai (>=0.9.0,<0.10.0)", "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)", "hologres-vector (>=0.0.6,<0.0.7)", "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)", "langchain-openai (>=0.0.2,<0.1)", "lxml (>=4.9.2,<5.0.0)", "markdownify (>=0.11.6,<0.12.0)", "motor (>=3.3.1,<4.0.0)", "msal (>=1.25.0,<2.0.0)", "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)", "praw (>=7.7.1,<8.0.0)", "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 (<2)", "openlm (>=0.0.5,<0.0.6)", "torch (>=1,<3)", "transformers (>=4,<5)"]
 openai = ["openai (<2)", "tiktoken (>=0.3.2,<0.6.0)"]
@@ -3059,20 +3059,46 @@ qdrant = ["qdrant-client (>=1.3.1,<2.0.0)"]
 text-helpers = ["chardet (>=5.1.0,<6.0.0)"]
 
 [[package]]
-name = "langchain-core"
-version = "0.1.12"
-description = "Building applications with LLMs through composability"
-optional = true
+name = "langchain-community"
+version = "0.0.16"
+description = "Community contributed LangChain integrations."
+optional = false
 python-versions = ">=3.8.1,<4.0"
 files = [
-    {file = "langchain_core-0.1.12-py3-none-any.whl", hash = "sha256:d11c6262f7a9deff7de8fdf14498b8a951020dfed3a80f2358ab731ad04abef0"},
-    {file = "langchain_core-0.1.12.tar.gz", hash = "sha256:f18e9300e9a07589b3e280e51befbc5a4513f535949406e55eb7a2dc40c3ce66"},
+    {file = "langchain_community-0.0.16-py3-none-any.whl", hash = "sha256:0f1dfc1a6205ce8d39931d3515974a208a9f69c16157c649f83490a7cc830b73"},
+    {file = "langchain_community-0.0.16.tar.gz", hash = "sha256:c06512a93013a06fba7679cd5a1254ff8b927cddd2d1fbe0cc444bf7bbdf0b8c"},
+]
+
+[package.dependencies]
+aiohttp = ">=3.8.3,<4.0.0"
+dataclasses-json = ">=0.5.7,<0.7"
+langchain-core = ">=0.1.16,<0.2"
+langsmith = ">=0.0.83,<0.1"
+numpy = ">=1,<2"
+PyYAML = ">=5.3"
+requests = ">=2,<3"
+SQLAlchemy = ">=1.4,<3"
+tenacity = ">=8.1.0,<9.0.0"
+
+[package.extras]
+cli = ["typer (>=0.9.0,<0.10.0)"]
+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)", "azure-ai-documentintelligence (>=1.0.0b1,<2.0.0)", "beautifulsoup4 (>=4,<5)", "bibtexparser (>=1.4.0,<2.0.0)", "cassio (>=0.1.0,<0.2.0)", "chardet (>=5.1.0,<6.0.0)", "cohere (>=4,<5)", "dashvector (>=1.0.1,<2.0.0)", "databricks-vectorsearch (>=0.21,<0.22)", "datasets (>=2.15.0,<3.0.0)", "dgml-utils (>=0.3.0,<0.4.0)", "elasticsearch (>=8.12.0,<9.0.0)", "esprima (>=4.0.1,<5.0.0)", "faiss-cpu (>=1,<2)", "feedparser (>=6.0.10,<7.0.0)", "fireworks-ai (>=0.9.0,<0.10.0)", "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)", "gradientai (>=1.4.0,<2.0.0)", "hdbcli (>=2.19.21,<3.0.0)", "hologres-vector (>=0.0.6,<0.0.7)", "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)", "msal (>=1.25.0,<2.0.0)", "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)", "oci (>=2.119.1,<3.0.0)", "openai (<2)", "openapi-pydantic (>=0.3.2,<0.4.0)", "oracle-ads (>=2.9.1,<3.0.0)", "pandas (>=2.0.1,<3.0.0)", "pdfminer-six (>=20221105,<20221106)", "pgvector (>=0.1.6,<0.2.0)", "praw (>=7.7.1,<8.0.0)", "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)", "zhipuai (>=1.0.7,<2.0.0)"]
+
+[[package]]
+name = "langchain-core"
+version = "0.1.16"
+description = "Building applications with LLMs through composability"
+optional = false
+python-versions = ">=3.8.1,<4.0"
+files = [
+    {file = "langchain_core-0.1.16-py3-none-any.whl", hash = "sha256:c1b2e7363771d64a72cb45032ed5a46facf67de005017fb5e74595cbf433f834"},
+    {file = "langchain_core-0.1.16.tar.gz", hash = "sha256:8cb546eed318009ee1a8a381d108074eddf0395ae61eb243db00d76e1e265e89"},
 ]
 
 [package.dependencies]
 anyio = ">=3,<5"
 jsonpatch = ">=1.33,<2.0"
-langsmith = ">=0.0.63,<0.1.0"
+langsmith = ">=0.0.83,<0.1"
 packaging = ">=23.2,<24.0"
 pydantic = ">=1,<3"
 PyYAML = ">=5.3"
@@ -3097,6 +3123,23 @@ files = [
 langchain-core = ">=0.1,<0.2"
 mistralai = ">=0.0.11,<0.0.12"
 
+[[package]]
+name = "langchain-openai"
+version = "0.0.5"
+description = "An integration package connecting OpenAI and LangChain"
+optional = false
+python-versions = ">=3.8.1,<4.0"
+files = [
+    {file = "langchain_openai-0.0.5-py3-none-any.whl", hash = "sha256:93b37dfac274adad65e46d5d6e71411e00c6984bcc5e10f1d6bb58e7944dc01b"},
+    {file = "langchain_openai-0.0.5.tar.gz", hash = "sha256:f317fee5b652949ad96ad7edf8ef7a044a6a3f0cc71d1e12f9d5261789fd68c4"},
+]
+
+[package.dependencies]
+langchain-core = ">=0.1.16,<0.2"
+numpy = ">=1,<2"
+openai = ">=1.10.0,<2.0.0"
+tiktoken = ">=0.5.2,<0.6.0"
+
 [[package]]
 name = "langdetect"
 version = "1.0.9"
@@ -3113,13 +3156,13 @@ six = "*"
 
 [[package]]
 name = "langsmith"
-version = "0.0.65"
+version = "0.0.83"
 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-0.0.65-py3-none-any.whl", hash = "sha256:92450957d1c6b6be814f9b726f3bc751deca684535fb404508ccad7aec1bb049"},
-    {file = "langsmith-0.0.65.tar.gz", hash = "sha256:ef20e2e32392fb1a0fc5d171e8de595d868b4153a10cc119d7bf8418192c06b6"},
+    {file = "langsmith-0.0.83-py3-none-any.whl", hash = "sha256:a5bb7ac58c19a415a9d5f51db56dd32ee2cd7343a00825bbc2018312eb3d122a"},
+    {file = "langsmith-0.0.83.tar.gz", hash = "sha256:94427846b334ad9bdbec3266fee12903fe9f5448f628667689d0412012aaf392"},
 ]
 
 [package.dependencies]
@@ -4187,22 +4230,23 @@ sympy = "*"
 
 [[package]]
 name = "openai"
-version = "1.1.2"
-description = "Client library for the openai API"
+version = "1.10.0"
+description = "The official Python library for the openai API"
 optional = false
 python-versions = ">=3.7.1"
 files = [
-    {file = "openai-1.1.2-py3-none-any.whl", hash = "sha256:72fa414378913ca74432ac618ca6cdfd78a502fcfad1e06cc499b9dba8ff2c8e"},
-    {file = "openai-1.1.2.tar.gz", hash = "sha256:bcb4d1fd471cf616031053636841acdc820cd42cbc6cd3e4036c85f682752656"},
+    {file = "openai-1.10.0-py3-none-any.whl", hash = "sha256:aa69e97d0223ace9835fbf9c997abe9ee95318f684fd2de6d02c870700c71ebc"},
+    {file = "openai-1.10.0.tar.gz", hash = "sha256:208886cb501b930dc63f48d51db9c15e5380380f80516d07332adad67c9f1053"},
 ]
 
 [package.dependencies]
-anyio = ">=3.5.0,<4"
+anyio = ">=3.5.0,<5"
 distro = ">=1.7.0,<2"
 httpx = ">=0.23.0,<1"
 pydantic = ">=1.9.0,<3"
+sniffio = "*"
 tqdm = ">4"
-typing-extensions = ">=4.5,<5"
+typing-extensions = ">=4.7,<5"
 
 [package.extras]
 datalib = ["numpy (>=1)", "pandas (>=1.2.3)", "pandas-stubs (>=1.1.0.11)"]
@@ -5676,6 +5720,7 @@ files = [
     {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
     {file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"},
     {file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"},
+    {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a08c6f0fe150303c1c6b71ebcd7213c2858041a7e01975da3a99aed1e7a378ef"},
     {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"},
     {file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"},
     {file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"},
@@ -5857,7 +5902,7 @@ full = ["numpy"]
 name = "regex"
 version = "2023.8.8"
 description = "Alternative regular expression module, to replace re."
-optional = true
+optional = false
 python-versions = ">=3.6"
 files = [
     {file = "regex-2023.8.8-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:88900f521c645f784260a8d346e12a1590f79e96403971241e64c3a265c8ecdb"},
@@ -6833,40 +6878,47 @@ files = [
 
 [[package]]
 name = "tiktoken"
-version = "0.4.0"
+version = "0.5.2"
 description = "tiktoken is a fast BPE tokeniser for use with OpenAI's models"
-optional = true
+optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "tiktoken-0.4.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:176cad7f053d2cc82ce7e2a7c883ccc6971840a4b5276740d0b732a2b2011f8a"},
-    {file = "tiktoken-0.4.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:450d504892b3ac80207700266ee87c932df8efea54e05cefe8613edc963c1285"},
-    {file = "tiktoken-0.4.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:00d662de1e7986d129139faf15e6a6ee7665ee103440769b8dedf3e7ba6ac37f"},
-    {file = "tiktoken-0.4.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5727d852ead18b7927b8adf558a6f913a15c7766725b23dbe21d22e243041b28"},
-    {file = "tiktoken-0.4.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:c06cd92b09eb0404cedce3702fa866bf0d00e399439dad3f10288ddc31045422"},
-    {file = "tiktoken-0.4.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:9ec161e40ed44e4210d3b31e2ff426b4a55e8254f1023e5d2595cb60044f8ea6"},
-    {file = "tiktoken-0.4.0-cp310-cp310-win_amd64.whl", hash = "sha256:1e8fa13cf9889d2c928b9e258e9dbbbf88ab02016e4236aae76e3b4f82dd8288"},
-    {file = "tiktoken-0.4.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:bb2341836b725c60d0ab3c84970b9b5f68d4b733a7bcb80fb25967e5addb9920"},
-    {file = "tiktoken-0.4.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:2ca30367ad750ee7d42fe80079d3092bd35bb266be7882b79c3bd159b39a17b0"},
-    {file = "tiktoken-0.4.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3dc3df19ddec79435bb2a94ee46f4b9560d0299c23520803d851008445671197"},
-    {file = "tiktoken-0.4.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4d980fa066e962ef0f4dad0222e63a484c0c993c7a47c7dafda844ca5aded1f3"},
-    {file = "tiktoken-0.4.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:329f548a821a2f339adc9fbcfd9fc12602e4b3f8598df5593cfc09839e9ae5e4"},
-    {file = "tiktoken-0.4.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:b1a038cee487931a5caaef0a2e8520e645508cde21717eacc9af3fbda097d8bb"},
-    {file = "tiktoken-0.4.0-cp311-cp311-win_amd64.whl", hash = "sha256:08efa59468dbe23ed038c28893e2a7158d8c211c3dd07f2bbc9a30e012512f1d"},
-    {file = "tiktoken-0.4.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:f3020350685e009053829c1168703c346fb32c70c57d828ca3742558e94827a9"},
-    {file = "tiktoken-0.4.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:ba16698c42aad8190e746cd82f6a06769ac7edd415d62ba027ea1d99d958ed93"},
-    {file = "tiktoken-0.4.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9c15d9955cc18d0d7ffcc9c03dc51167aedae98542238b54a2e659bd25fe77ed"},
-    {file = "tiktoken-0.4.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:64e1091c7103100d5e2c6ea706f0ec9cd6dc313e6fe7775ef777f40d8c20811e"},
-    {file = "tiktoken-0.4.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:e87751b54eb7bca580126353a9cf17a8a8eaadd44edaac0e01123e1513a33281"},
-    {file = "tiktoken-0.4.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:e063b988b8ba8b66d6cc2026d937557437e79258095f52eaecfafb18a0a10c03"},
-    {file = "tiktoken-0.4.0-cp38-cp38-win_amd64.whl", hash = "sha256:9c6dd439e878172dc163fced3bc7b19b9ab549c271b257599f55afc3a6a5edef"},
-    {file = "tiktoken-0.4.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:8d1d97f83697ff44466c6bef5d35b6bcdb51e0125829a9c0ed1e6e39fb9a08fb"},
-    {file = "tiktoken-0.4.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:1b6bce7c68aa765f666474c7c11a7aebda3816b58ecafb209afa59c799b0dd2d"},
-    {file = "tiktoken-0.4.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5a73286c35899ca51d8d764bc0b4d60838627ce193acb60cc88aea60bddec4fd"},
-    {file = "tiktoken-0.4.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d0394967d2236a60fd0aacef26646b53636423cc9c70c32f7c5124ebe86f3093"},
-    {file = "tiktoken-0.4.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:dae2af6f03ecba5f679449fa66ed96585b2fa6accb7fd57d9649e9e398a94f44"},
-    {file = "tiktoken-0.4.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:55e251b1da3c293432179cf7c452cfa35562da286786be5a8b1ee3405c2b0dd2"},
-    {file = "tiktoken-0.4.0-cp39-cp39-win_amd64.whl", hash = "sha256:c835d0ee1f84a5aa04921717754eadbc0f0a56cf613f78dfc1cf9ad35f6c3fea"},
-    {file = "tiktoken-0.4.0.tar.gz", hash = "sha256:59b20a819969735b48161ced9b92f05dc4519c17be4015cfb73b65270a243620"},
+    {file = "tiktoken-0.5.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8c4e654282ef05ec1bd06ead22141a9a1687991cef2c6a81bdd1284301abc71d"},
+    {file = "tiktoken-0.5.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:7b3134aa24319f42c27718c6967f3c1916a38a715a0fa73d33717ba121231307"},
+    {file = "tiktoken-0.5.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6092e6e77730929c8c6a51bb0d7cfdf1b72b63c4d033d6258d1f2ee81052e9e5"},
+    {file = "tiktoken-0.5.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:72ad8ae2a747622efae75837abba59be6c15a8f31b4ac3c6156bc56ec7a8e631"},
+    {file = "tiktoken-0.5.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:51cba7c8711afa0b885445f0637f0fcc366740798c40b981f08c5f984e02c9d1"},
+    {file = "tiktoken-0.5.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:3d8c7d2c9313f8e92e987d585ee2ba0f7c40a0de84f4805b093b634f792124f5"},
+    {file = "tiktoken-0.5.2-cp310-cp310-win_amd64.whl", hash = "sha256:692eca18c5fd8d1e0dde767f895c17686faaa102f37640e884eecb6854e7cca7"},
+    {file = "tiktoken-0.5.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:138d173abbf1ec75863ad68ca289d4da30caa3245f3c8d4bfb274c4d629a2f77"},
+    {file = "tiktoken-0.5.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:7388fdd684690973fdc450b47dfd24d7f0cbe658f58a576169baef5ae4658607"},
+    {file = "tiktoken-0.5.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a114391790113bcff670c70c24e166a841f7ea8f47ee2fe0e71e08b49d0bf2d4"},
+    {file = "tiktoken-0.5.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ca96f001e69f6859dd52926d950cfcc610480e920e576183497ab954e645e6ac"},
+    {file = "tiktoken-0.5.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:15fed1dd88e30dfadcdd8e53a8927f04e1f6f81ad08a5ca824858a593ab476c7"},
+    {file = "tiktoken-0.5.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:93f8e692db5756f7ea8cb0cfca34638316dcf0841fb8469de8ed7f6a015ba0b0"},
+    {file = "tiktoken-0.5.2-cp311-cp311-win_amd64.whl", hash = "sha256:bcae1c4c92df2ffc4fe9f475bf8148dbb0ee2404743168bbeb9dcc4b79dc1fdd"},
+    {file = "tiktoken-0.5.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:b76a1e17d4eb4357d00f0622d9a48ffbb23401dcf36f9716d9bd9c8e79d421aa"},
+    {file = "tiktoken-0.5.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:01d8b171bb5df4035580bc26d4f5339a6fd58d06f069091899d4a798ea279d3e"},
+    {file = "tiktoken-0.5.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42adf7d4fb1ed8de6e0ff2e794a6a15005f056a0d83d22d1d6755a39bffd9e7f"},
+    {file = "tiktoken-0.5.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4c3f894dbe0adb44609f3d532b8ea10820d61fdcb288b325a458dfc60fefb7db"},
+    {file = "tiktoken-0.5.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:58ccfddb4e62f0df974e8f7e34a667981d9bb553a811256e617731bf1d007d19"},
+    {file = "tiktoken-0.5.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:58902a8bad2de4268c2a701f1c844d22bfa3cbcc485b10e8e3e28a050179330b"},
+    {file = "tiktoken-0.5.2-cp312-cp312-win_amd64.whl", hash = "sha256:5e39257826d0647fcac403d8fa0a474b30d02ec8ffc012cfaf13083e9b5e82c5"},
+    {file = "tiktoken-0.5.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:8bde3b0fbf09a23072d39c1ede0e0821f759b4fa254a5f00078909158e90ae1f"},
+    {file = "tiktoken-0.5.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:2ddee082dcf1231ccf3a591d234935e6acf3e82ee28521fe99af9630bc8d2a60"},
+    {file = "tiktoken-0.5.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:35c057a6a4e777b5966a7540481a75a31429fc1cb4c9da87b71c8b75b5143037"},
+    {file = "tiktoken-0.5.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4c4a049b87e28f1dc60509f8eb7790bc8d11f9a70d99b9dd18dfdd81a084ffe6"},
+    {file = "tiktoken-0.5.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:5bf5ce759089f4f6521ea6ed89d8f988f7b396e9f4afb503b945f5c949c6bec2"},
+    {file = "tiktoken-0.5.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:0c964f554af1a96884e01188f480dad3fc224c4bbcf7af75d4b74c4b74ae0125"},
+    {file = "tiktoken-0.5.2-cp38-cp38-win_amd64.whl", hash = "sha256:368dd5726d2e8788e47ea04f32e20f72a2012a8a67af5b0b003d1e059f1d30a3"},
+    {file = "tiktoken-0.5.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:a2deef9115b8cd55536c0a02c0203512f8deb2447f41585e6d929a0b878a0dd2"},
+    {file = "tiktoken-0.5.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:2ed7d380195affbf886e2f8b92b14edfe13f4768ff5fc8de315adba5b773815e"},
+    {file = "tiktoken-0.5.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c76fce01309c8140ffe15eb34ded2bb94789614b7d1d09e206838fc173776a18"},
+    {file = "tiktoken-0.5.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:60a5654d6a2e2d152637dd9a880b4482267dfc8a86ccf3ab1cec31a8c76bfae8"},
+    {file = "tiktoken-0.5.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:41d4d3228e051b779245a8ddd21d4336f8975563e92375662f42d05a19bdff41"},
+    {file = "tiktoken-0.5.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:a5c1cdec2c92fcde8c17a50814b525ae6a88e8e5b02030dc120b76e11db93f13"},
+    {file = "tiktoken-0.5.2-cp39-cp39-win_amd64.whl", hash = "sha256:84ddb36faedb448a50b246e13d1b6ee3437f60b7169b723a4b2abad75e914f3e"},
+    {file = "tiktoken-0.5.2.tar.gz", hash = "sha256:f54c581f134a8ea96ce2023ab221d4d4d81ab614efa0b2fbce926387deb56c80"},
 ]
 
 [package.dependencies]
@@ -8260,4 +8312,4 @@ youtube = ["youtube-transcript-api", "yt_dlp"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.9,<3.12"
-content-hash = "a16addd3362ae70c79b15677c6815f708677f11f636093f4e1f5084ba44b5a36"
+content-hash = "7efcfdf75c6295ff7fe98e6eb19f98f4dd3aab789033999ea0d90e621826e66a"

pyproject.toml

@@ -93,7 +93,7 @@ color = true
 [tool.poetry.dependencies]
 python = ">=3.9,<3.12"
 python-dotenv = "^1.0.0"
-langchain = "^0.0.336"
+langchain = "^0.1.4"
 requests = "^2.31.0"
 openai = ">=1.1.1"
 chromadb = "^0.4.17"
@@ -103,7 +103,7 @@ beautifulsoup4 = "^4.12.2"
 pypdf = "^3.11.0"
 gptcache = "^0.1.43"
 pysbd = "^0.3.4"
-tiktoken = { version = "^0.4.0", optional = true }
+tiktoken = { version = "^0.5.2", optional = true }
 youtube-transcript-api = { version = "^0.6.1", optional = true }
 pytube = { version = "^15.0.0", optional = true }
 duckduckgo-search = { version = "^3.8.5", optional = true }
@@ -151,6 +151,7 @@ google-auth-httplib2 = { version = "^0.2.0", optional = true }
 google-api-core = { version = "^2.15.0", optional = true }
 boto3 = { version = "^1.34.20", optional = true }
 langchain-mistralai = { version = "^0.0.3", optional = true }
+langchain-openai = "^0.0.5"
 
 [tool.poetry.group.dev.dependencies]
 black = "^23.3.0"

tests/llm/test_anthrophic.py

@@ -24,7 +24,7 @@ def test_get_llm_model_answer(anthropic_llm):
 
 
 def test_get_answer(anthropic_llm):
-    with patch("langchain.chat_models.ChatAnthropic") as mock_chat:
+    with patch("langchain_community.chat_models.ChatAnthropic") as mock_chat:
         mock_chat_instance = mock_chat.return_value
         mock_chat_instance.return_value = MagicMock(content="Test Response")
 
@@ -53,7 +53,7 @@ def test_get_messages(anthropic_llm):
 
 
 def test_get_answer_max_tokens_is_provided(anthropic_llm, caplog):
-    with patch("langchain.chat_models.ChatAnthropic") as mock_chat:
+    with patch("langchain_community.chat_models.ChatAnthropic") as mock_chat:
         mock_chat_instance = mock_chat.return_value
         mock_chat_instance.return_value = MagicMock(content="Test Response")
 

tests/llm/test_azure_openai.py

@@ -28,7 +28,7 @@ def test_get_llm_model_answer(azure_openai_llm):
 
 
 def test_get_answer(azure_openai_llm):
-    with patch("langchain.chat_models.AzureChatOpenAI") as mock_chat:
+    with patch("langchain_community.chat_models.AzureChatOpenAI") as mock_chat:
         mock_chat_instance = mock_chat.return_value
         mock_chat_instance.return_value = MagicMock(content="Test Response")
 
@@ -60,7 +60,7 @@ def test_get_messages(azure_openai_llm):
 
 
 def test_get_answer_top_p_is_provided(azure_openai_llm, caplog):
-    with patch("langchain.chat_models.AzureChatOpenAI") as mock_chat:
+    with patch("langchain_community.chat_models.AzureChatOpenAI") as mock_chat:
         mock_chat_instance = mock_chat.return_value
         mock_chat_instance.return_value = MagicMock(content="Test Response")
 

tests/llm/test_gpt4all.py

@@ -1,5 +1,5 @@
 import pytest
-from langchain.llms.gpt4all import GPT4All as LangchainGPT4All
+from langchain_community.llms.gpt4all import GPT4All as LangchainGPT4All
 
 from embedchain.config import BaseLlmConfig
 from embedchain.llm.gpt4all import GPT4ALLLlm

tests/llm/test_openai.py

@@ -74,3 +74,32 @@ def test_get_llm_model_answer_without_system_prompt(config, mocker):
         model_kwargs={"top_p": config.top_p},
         api_key=os.environ["OPENAI_API_KEY"],
     )
+
+
+@pytest.mark.parametrize(
+    "mock_return, expected",
+    [
+        ([{"test": "test"}], '{"test": "test"}'),
+        ([], "Input could not be mapped to the function!"),
+    ],
+)
+def test_get_llm_model_answer_with_tools(config, mocker, mock_return, expected):
+    mocked_openai_chat = mocker.patch("embedchain.llm.openai.ChatOpenAI")
+    mocked_convert_to_openai_tool = mocker.patch("langchain_core.utils.function_calling.convert_to_openai_tool")
+    mocked_json_output_tools_parser = mocker.patch("langchain.output_parsers.openai_tools.JsonOutputToolsParser")
+    mocked_openai_chat.return_value.bind.return_value.pipe.return_value.invoke.return_value = mock_return
+
+    llm = OpenAILlm(config, tools={"test": "test"})
+    answer = llm.get_llm_model_answer("Test query")
+
+    mocked_openai_chat.assert_called_once_with(
+        model=config.model,
+        temperature=config.temperature,
+        max_tokens=config.max_tokens,
+        model_kwargs={"top_p": config.top_p},
+        api_key=os.environ["OPENAI_API_KEY"],
+    )
+    mocked_convert_to_openai_tool.assert_called_once_with({"test": "test"})
+    mocked_json_output_tools_parser.assert_called_once()
+
+    assert answer == expected

tests/llm/test_vertex_ai.py

@@ -22,7 +22,7 @@ def test_get_llm_model_answer(vertexai_llm):
 
 
 def test_get_answer_with_warning(vertexai_llm, caplog):
-    with patch("langchain.chat_models.ChatVertexAI") as mock_chat:
+    with patch("langchain_community.chat_models.ChatVertexAI") as mock_chat:
         mock_chat_instance = mock_chat.return_value
         mock_chat_instance.return_value = MagicMock(content="Test Response")
 
@@ -39,7 +39,7 @@ def test_get_answer_with_warning(vertexai_llm, caplog):
 
 
 def test_get_answer_no_warning(vertexai_llm, caplog):
-    with patch("langchain.chat_models.ChatVertexAI") as mock_chat:
+    with patch("langchain_community.chat_models.ChatVertexAI") as mock_chat:
         mock_chat_instance = mock_chat.return_value
         mock_chat_instance.return_value = MagicMock(content="Test Response")