moved ollama agent to it's own folder

added mixtral agent
switched from serpapi to googleSearchAPI
added sources urls to final output

.gitignore

@@ -164,6 +164,7 @@ cython_debug/
 *.bin
 *.pickle
 chroma_db/*
+downloaded_papers/*
 bin
 obj
 .langchain.sqlite

hf_mixtral_agent.py

@@ -0,0 +1,157 @@
+# HF libraries
+from langchain_community.llms import HuggingFaceHub
+from langchain_core.prompts import ChatPromptTemplate
+from langchain import hub
+import gradio as gr
+from langchain.agents import AgentExecutor
+from langchain.agents.format_scratchpad import format_log_to_str
+from langchain.agents.output_parsers import (
+    ReActJsonSingleInputOutputParser,
+)
+# Import things that are needed generically
+from typing import List, Dict
+from langchain.tools.render import render_text_description
+import os
+from dotenv import load_dotenv
+from innovation_pathfinder_ai.structured_tools.structured_tools import (
+    arxiv_search, get_arxiv_paper, google_search, wikipedia_search
+)
+
+# hacky and should be replaced with a database
+from innovation_pathfinder_ai.source_container.container import (
+    all_sources
+)
+
+# from langchain_community.chat_message_histories import ChatMessageHistory
+# from langchain_core.runnables.history import RunnableWithMessageHistory
+
+# message_history = ChatMessageHistory()
+config = load_dotenv(".env")
+HUGGINGFACEHUB_API_TOKEN = os.getenv('HUGGINGFACEHUB_API_TOKEN')
+GOOGLE_CSE_ID = os.getenv('GOOGLE_CSE_ID')
+GOOGLE_API_KEY = os.getenv('GOOGLE_API_KEY')
+LANGCHAIN_TRACING_V2 = "true"
+LANGCHAIN_ENDPOINT = "https://api.smith.langchain.com"
+LANGCHAIN_API_KEY = os.getenv('LANGCHAIN_API_KEY')
+LANGCHAIN_PROJECT = os.getenv('LANGCHAIN_PROJECT')
+
+# Load the model from the Hugging Face Hub
+llm = HuggingFaceHub(repo_id="mistralai/Mixtral-8x7B-Instruct-v0.1", model_kwargs={
+    "temperature":0.1,
+    "max_new_tokens":1024,
+    "repetition_penalty":1.2,
+    "return_full_text":False
+    })
+
+
+tools = [
+    arxiv_search,
+    wikipedia_search,
+    google_search,
+#    get_arxiv_paper,
+    ]
+
+
+prompt = hub.pull("hwchase17/react-json")
+prompt = prompt.partial(
+    tools=render_text_description(tools),
+    tool_names=", ".join([t.name for t in tools]),
+)
+
+
+# define the agent
+chat_model_with_stop = llm.bind(stop=["\nObservation"])
+agent = (
+    {
+        "input": lambda x: x["input"],
+        "agent_scratchpad": lambda x: format_log_to_str(x["intermediate_steps"]),
+    }
+    | prompt
+    | chat_model_with_stop
+    | ReActJsonSingleInputOutputParser()
+)
+
+# instantiate AgentExecutor
+agent_executor = AgentExecutor(
+    agent=agent, 
+    tools=tools, 
+    verbose=True,
+    max_iterations=10,       # cap number of iterations
+    #max_execution_time=60,  # timout at 60 sec
+    return_intermediate_steps=True,
+    handle_parsing_errors=True,
+    )
+
+    
+if __name__ == "__main__":
+    
+    def add_text(history, text):
+        history = history + [(text, None)]
+        return history, ""
+
+    def bot(history):
+        response = infer(history[-1][0], history)
+        sources = collect_urls(all_sources)
+        src_list = '\n'.join(sources)
+        response_w_sources = response['output']+"\n\n\n Sources: \n\n\n"+src_list
+        history[-1][1] = response_w_sources
+        return history
+
+    def infer(question, history):
+        query =  question
+        result = agent_executor.invoke(
+            {
+                "input": question,
+            }
+        )
+        return result
+
+    def vote(data: gr.LikeData):
+        if data.liked:
+            print("You upvoted this response: " + data.value)
+        else:
+            print("You downvoted this response: " + data.value)
+    
+    def collect_urls(data_list):
+        urls = []
+        for item in data_list:
+            # Check if item is a string and contains 'link:'
+            if isinstance(item, str) and 'link:' in item:
+                start = item.find('link:') + len('link: ')
+                end = item.find(',', start)
+                url = item[start:end if end != -1 else None].strip()
+                urls.append(url)
+            # Check if item is a dictionary and has 'Entry ID'
+            elif isinstance(item, dict) and 'Entry ID' in item:
+                urls.append(item['Entry ID'])
+        return urls
+
+    css="""
+    #col-container {max-width: 700px; margin-left: auto; margin-right: auto;}
+    """
+
+    title = """
+    <div style="text-align: center;max-width: 700px;">
+        <p>Hello Dave, how can I help today?<br />
+    </div>
+    """
+
+    with gr.Blocks(theme=gr.themes.Soft()) as demo:
+        with gr.Tab("Google|Wikipedia|Arxiv"):
+            with gr.Column(elem_id="col-container"):
+                gr.HTML(title)
+                with gr.Row():
+                    question = gr.Textbox(label="Question", placeholder="Type your question and hit Enter ")
+                chatbot = gr.Chatbot([], elem_id="chatbot")
+                chatbot.like(vote, None, None)
+                clear = gr.Button("Clear")
+            question.submit(add_text, [chatbot, question], [chatbot, question], queue=False).then(
+                bot, chatbot, chatbot
+            )
+            clear.click(lambda: None, None, chatbot, queue=False)
+
+    demo.queue()
+    demo.launch(debug=True)
+
+
+    x = 0 # for debugging purposes

innovation_pathfinder_ai/agent_ollama/requirements.txt

@@ -0,0 +1,374 @@
+langchain 
+langchain-community 
+beautifulsoup4 
+faiss-cpu 
+chromadb 
+validators 
+sentence_transformers 
+typing-extensions==4.8.0 
+unstructured 
+gradio==3.48.0
+boto3
+aiofiles==23.2.1
+aiohttp==3.9.3
+aiosignal==1.3.1
+altair==5.2.0
+annotated-types==0.6.0
+anyio==4.2.0
+arxiv==2.1.0
+asgiref==3.7.2
+async-timeout==4.0.3
+attrs==23.2.0
+backoff==2.2.1
+bcrypt==4.1.2
+beautifulsoup4==4.12.3
+boto3==1.34.44
+botocore==1.34.44
+build==1.0.3
+cachetools==5.3.2
+certifi==2024.2.2
+chardet==5.2.0
+charset-normalizer==3.3.2
+chroma-hnswlib==0.7.3
+chromadb==0.4.22
+click==8.1.7
+coloredlogs==15.0.1
+contourpy==1.2.0
+cycler==0.12.1
+dataclasses-json==0.6.4
+dataclasses-json-speakeasy==0.5.11
+Deprecated==1.2.14
+emoji==2.10.1
+exceptiongroup==1.2.0
+faiss-cpu==1.7.4
+fastapi==0.109.2
+feedparser==6.0.10
+ffmpy==0.3.2
+filelock==3.13.1
+filetype==1.2.0
+flatbuffers==23.5.26
+fonttools==4.49.0
+frozenlist==1.4.1
+fsspec==2024.2.0
+google-auth==2.28.0
+google-search-results==2.4.2
+googleapis-common-protos==1.62.0
+gradio==3.48.0
+gradio_client==0.6.1
+greenlet==3.0.3
+grpcio==1.60.1
+h11==0.14.0
+httpcore==1.0.3
+httptools==0.6.1
+httpx==0.26.0
+huggingface-hub==0.20.3
+humanfriendly==10.0
+idna==3.6
+importlib-metadata==6.11.0
+importlib-resources==6.1.1
+Jinja2==3.1.3
+jmespath==1.0.1
+joblib==1.3.2
+jsonpatch==1.33
+jsonpath-python==1.0.6
+jsonpointer==2.4
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+kiwisolver==1.4.5
+kubernetes==29.0.0
+langchain==0.1.7
+langchain-community==0.0.20
+langchain-core==0.1.23
+langchainhub==0.1.14
+langdetect==1.0.9
+langsmith==0.0.87
+lxml==5.1.0
+MarkupSafe==2.1.5
+marshmallow==3.20.2
+matplotlib==3.8.3
+mmh3==4.1.0
+monotonic==1.6
+mpmath==1.3.0
+multidict==6.0.5
+mypy-extensions==1.0.0
+networkx==3.2.1
+nltk==3.8.1
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==8.9.2.26
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.19.3
+nvidia-nvjitlink-cu12==12.3.101
+nvidia-nvtx-cu12==12.1.105
+oauthlib==3.2.2
+onnxruntime==1.17.0
+opentelemetry-api==1.22.0
+opentelemetry-exporter-otlp-proto-common==1.22.0
+opentelemetry-exporter-otlp-proto-grpc==1.22.0
+opentelemetry-instrumentation==0.43b0
+opentelemetry-instrumentation-asgi==0.43b0
+opentelemetry-instrumentation-fastapi==0.43b0
+opentelemetry-proto==1.22.0
+opentelemetry-sdk==1.22.0
+opentelemetry-semantic-conventions==0.43b0
+opentelemetry-util-http==0.43b0
+orjson==3.9.14
+overrides==7.7.0
+packaging==23.2
+pandas==2.2.0
+pillow==10.2.0
+posthog==3.4.1
+protobuf==4.25.3
+pulsar-client==3.4.0
+pyasn1==0.5.1
+pyasn1-modules==0.3.0
+pydantic==2.6.1
+pydantic_core==2.16.2
+pydub==0.25.1
+pyparsing==3.1.1
+PyPika==0.48.9
+pyproject_hooks==1.0.0
+python-dateutil==2.8.2
+python-dotenv==1.0.1
+python-iso639==2024.2.7
+python-magic==0.4.27
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.1
+rapidfuzz==3.6.1
+referencing==0.33.0
+regex==2023.12.25
+requests==2.31.0
+requests-oauthlib==1.3.1
+rpds-py==0.18.0
+rsa==4.9
+s3transfer==0.10.0
+safetensors==0.4.2
+scikit-learn==1.4.1.post1
+scipy==1.12.0
+semantic-version==2.10.0
+sentence-transformers==2.3.1
+sentencepiece==0.1.99
+sgmllib3k==1.0.0
+six==1.16.0
+sniffio==1.3.0
+soupsieve==2.5
+SQLAlchemy==2.0.27
+starlette==0.36.3
+sympy==1.12
+tabulate==0.9.0
+tenacity==8.2.3
+threadpoolctl==3.3.0
+tokenizers==0.15.2
+tomli==2.0.1
+toolz==0.12.1
+torch==2.2.0
+tqdm==4.66.2
+transformers==4.37.2
+triton==2.2.0
+typer==0.9.0
+types-requests==2.31.0.20240125
+typing-inspect==0.9.0
+typing_extensions==4.8.0
+tzdata==2024.1
+unstructured==0.12.4
+unstructured-client==0.18.0
+urllib3==2.0.7
+uvicorn==0.27.1
+uvloop==0.19.0
+validators==0.22.0
+watchfiles==0.21.0
+websocket-client==1.7.0
+websockets==11.0.3
+wrapt==1.16.0
+yarl==1.9.4
+zipp==3.17.0
+aiofiles==23.2.1
+aiohttp==3.9.3
+aiosignal==1.3.1
+altair==5.2.0
+annotated-types==0.6.0
+anyio==4.2.0
+arxiv==2.1.0
+asgiref==3.7.2
+async-timeout==4.0.3
+attrs==23.2.0
+backoff==2.2.1
+bcrypt==4.1.2
+beautifulsoup4==4.12.3
+boto3==1.34.42
+botocore==1.34.42
+build==1.0.3
+cachetools==5.3.2
+certifi==2024.2.2
+chardet==5.2.0
+charset-normalizer==3.3.2
+chroma-hnswlib==0.7.3
+chromadb==0.4.22
+click==8.1.7
+coloredlogs==15.0.1
+contourpy==1.2.0
+cycler==0.12.1
+dataclasses-json==0.6.4
+dataclasses-json-speakeasy==0.5.11
+Deprecated==1.2.14
+emoji==2.10.1
+exceptiongroup==1.2.0
+faiss-cpu==1.7.4
+fastapi==0.109.2
+feedparser==6.0.10
+ffmpy==0.3.2
+filelock==3.13.1
+filetype==1.2.0
+flatbuffers==23.5.26
+fonttools==4.48.1
+frozenlist==1.4.1
+fsspec==2024.2.0
+gitdb==4.0.11
+GitPython==3.1.41
+google-auth==2.27.0
+google_search_results==2.4.2
+googleapis-common-protos==1.62.0
+gradio==3.48.0
+gradio_client==0.6.1
+greenlet==3.0.3
+grpcio==1.60.1
+h11==0.14.0
+httpcore==1.0.3
+httptools==0.6.1
+httpx==0.26.0
+huggingface-hub==0.20.3
+humanfriendly==10.0
+idna==3.6
+importlib-metadata==6.11.0
+importlib-resources==6.1.1
+Jinja2==3.1.3
+jmespath==1.0.1
+joblib==1.3.2
+jsonpatch==1.33
+jsonpath-python==1.0.6
+jsonpointer==2.4
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+kiwisolver==1.4.5
+kubernetes==29.0.0
+langchain==0.1.7
+langchain-community==0.0.20
+langchain-core==0.1.23
+langchainhub==0.1.14
+langdetect==1.0.9
+langsmith==0.0.87
+lxml==5.1.0
+MarkupSafe==2.1.5
+marshmallow==3.20.2
+matplotlib==3.8.3
+mmh3==4.1.0
+monotonic==1.6
+mpmath==1.3.0
+multidict==6.0.5
+mypy-extensions==1.0.0
+networkx==3.2.1
+nltk==3.8.1
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==8.9.2.26
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.19.3
+nvidia-nvjitlink-cu12==12.3.101
+nvidia-nvtx-cu12==12.1.105
+oauthlib==3.2.2
+onnxruntime==1.17.0
+opentelemetry-api==1.22.0
+opentelemetry-exporter-otlp-proto-common==1.22.0
+opentelemetry-exporter-otlp-proto-grpc==1.22.0
+opentelemetry-instrumentation==0.43b0
+opentelemetry-instrumentation-asgi==0.43b0
+opentelemetry-instrumentation-fastapi==0.43b0
+opentelemetry-proto==1.22.0
+opentelemetry-sdk==1.22.0
+opentelemetry-semantic-conventions==0.43b0
+opentelemetry-util-http==0.43b0
+orjson==3.9.14
+overrides==7.7.0
+packaging==23.2
+pandas==2.2.0
+pillow==10.2.0
+posthog==3.4.1
+protobuf==4.25.2
+pulsar-client==3.4.0
+pyasn1==0.5.1
+pyasn1-modules==0.3.0
+pydantic==2.6.1
+pydantic_core==2.16.2
+pydub==0.25.1
+pyparsing==3.1.1
+PyPika==0.48.9
+pyproject_hooks==1.0.0
+python-dateutil==2.8.2
+python-dotenv==1.0.1
+python-iso639==2024.2.7
+python-magic==0.4.27
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.1
+rapidfuzz==3.6.1
+referencing==0.33.0
+regex==2023.12.25
+requests==2.31.0
+requests-oauthlib==1.3.1
+rpds-py==0.18.0
+rsa==4.9
+s3transfer==0.10.0
+safetensors==0.4.2
+scikit-learn==1.4.0
+scipy==1.12.0
+semantic-version==2.10.0
+sentence-transformers==2.3.1
+sentencepiece==0.1.99
+sgmllib3k==1.0.0
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.0
+soupsieve==2.5
+SQLAlchemy==2.0.27
+starlette==0.36.3
+sympy==1.12
+tabulate==0.9.0
+tenacity==8.2.3
+threadpoolctl==3.3.0
+tokenizers==0.15.2
+tomli==2.0.1
+toolz==0.12.1
+torch==2.2.0
+tqdm==4.66.2
+transformers==4.37.2
+triton==2.2.0
+typer==0.9.0
+types-requests==2.31.0.20240125
+typing-inspect==0.9.0
+typing_extensions==4.8.0
+tzdata==2024.1
+unstructured==0.12.4
+unstructured-client==0.18.0
+urllib3==2.0.7
+uvicorn==0.27.1
+uvloop==0.19.0
+validators==0.22.0
+watchfiles==0.21.0
+websocket-client==1.7.0
+websockets==11.0.3
+wrapt==1.16.0
+yarl==1.9.4
+zipp==3.17.0

innovation_pathfinder_ai/structured_tools/structured_tools.py

@@ -1,6 +1,10 @@
 from langchain.tools import BaseTool, StructuredTool, tool
-from langchain.retrievers import ArxivRetriever
-from langchain_community.utilities import SerpAPIWrapper
+from langchain_community.retrievers import ArxivRetriever
+#from langchain_community.utilities import SerpAPIWrapper
+from langchain_community.tools import WikipediaQueryRun
+from langchain_community.utilities import WikipediaAPIWrapper
+#from langchain.tools import Tool
+from langchain_community.utilities import GoogleSearchAPIWrapper
 import arxiv
 
 # hacky and should be replaced with a database
@@ -10,7 +14,8 @@ from innovation_pathfinder_ai.source_container.container import (
 
 @tool
 def arxiv_search(query: str) -> str:
-    """Using the arxiv search and collects metadata."""
+    """Search arxiv database for scientific research papers and studies. This is your primary information source.
+    always check it first when you search for information, before using any other tool."""
     # return "LangChain"
     global all_sources
     arxiv_retriever = ArxivRetriever(load_max_docs=2)
@@ -40,23 +45,34 @@ def get_arxiv_paper(paper_id:str) -> None:
     number_without_period = paper_id.replace('.', '')
     
     # Download the PDF to a specified directory with a custom filename.
-    paper.download_pdf(dirpath="./mydir", filename=f"{number_without_period}.pdf")
+    paper.download_pdf(dirpath="./downloaded_papers", filename=f"{number_without_period}.pdf")
     
     
 @tool
 def google_search(query: str) -> str:
-    """Using the google search and collects metadata."""
+    """Search Google for additional results when you can't answer questions using arxiv search or wikipedia search."""
     # return "LangChain"
     global all_sources
     
-    x = SerpAPIWrapper()
-    search_results:dict = x.results(query)
+    websearch = GoogleSearchAPIWrapper()
+    search_results:dict = websearch.results(query, 5)
     
  
-    organic_source = search_results['organic_results']
+    #organic_source = search_results['organic_results']
     # formatted_string = "Title: {title}, link: {link}, snippet: {snippet}".format(**organic_source)
-    cleaner_sources = ["Title: {title}, link: {link}, snippet: {snippet}".format(**i) for i in organic_source]
+    cleaner_sources = ["Title: {title}, link: {link}, snippet: {snippet}".format(**i) for i in search_results]
     
     all_sources += cleaner_sources    
     
-    return cleaner_sources.__str__()
+    return cleaner_sources.__str__()
+
+@tool
+def wikipedia_search(query: str) -> str:
+    """Search Wikipedia for additional information to expand on research papers or when no papers can be found."""
+    global all_sources
+
+    api_wrapper = WikipediaAPIWrapper()
+    wikipedia_search = WikipediaQueryRun(api_wrapper=api_wrapper)
+    wikipedia_results = wikipedia_search.run(query)
+    all_sources += wikipedia_results
+    return wikipedia_results

requirements.txt

@@ -1,374 +1,10 @@
-langchain 
-langchain-community 
-beautifulsoup4 
-faiss-cpu 
-chromadb 
-validators 
-sentence_transformers 
-typing-extensions==4.8.0 
-unstructured 
+langchain-community
+langchain
+google-search-results
+langchainhub
+text_generation
+arxiv
+wikipedia
 gradio==3.48.0
-boto3
-aiofiles==23.2.1
-aiohttp==3.9.3
-aiosignal==1.3.1
-altair==5.2.0
-annotated-types==0.6.0
-anyio==4.2.0
-arxiv==2.1.0
-asgiref==3.7.2
-async-timeout==4.0.3
-attrs==23.2.0
-backoff==2.2.1
-bcrypt==4.1.2
-beautifulsoup4==4.12.3
-boto3==1.34.44
-botocore==1.34.44
-build==1.0.3
-cachetools==5.3.2
-certifi==2024.2.2
-chardet==5.2.0
-charset-normalizer==3.3.2
-chroma-hnswlib==0.7.3
-chromadb==0.4.22
-click==8.1.7
-coloredlogs==15.0.1
-contourpy==1.2.0
-cycler==0.12.1
-dataclasses-json==0.6.4
-dataclasses-json-speakeasy==0.5.11
-Deprecated==1.2.14
-emoji==2.10.1
-exceptiongroup==1.2.0
-faiss-cpu==1.7.4
-fastapi==0.109.2
-feedparser==6.0.10
-ffmpy==0.3.2
-filelock==3.13.1
-filetype==1.2.0
-flatbuffers==23.5.26
-fonttools==4.49.0
-frozenlist==1.4.1
-fsspec==2024.2.0
-google-auth==2.28.0
-google-search-results==2.4.2
-googleapis-common-protos==1.62.0
-gradio==3.48.0
-gradio_client==0.6.1
-greenlet==3.0.3
-grpcio==1.60.1
-h11==0.14.0
-httpcore==1.0.3
-httptools==0.6.1
-httpx==0.26.0
-huggingface-hub==0.20.3
-humanfriendly==10.0
-idna==3.6
-importlib-metadata==6.11.0
-importlib-resources==6.1.1
-Jinja2==3.1.3
-jmespath==1.0.1
-joblib==1.3.2
-jsonpatch==1.33
-jsonpath-python==1.0.6
-jsonpointer==2.4
-jsonschema==4.21.1
-jsonschema-specifications==2023.12.1
-kiwisolver==1.4.5
-kubernetes==29.0.0
-langchain==0.1.7
-langchain-community==0.0.20
-langchain-core==0.1.23
-langchainhub==0.1.14
-langdetect==1.0.9
-langsmith==0.0.87
-lxml==5.1.0
-MarkupSafe==2.1.5
-marshmallow==3.20.2
-matplotlib==3.8.3
-mmh3==4.1.0
-monotonic==1.6
-mpmath==1.3.0
-multidict==6.0.5
-mypy-extensions==1.0.0
-networkx==3.2.1
-nltk==3.8.1
-numpy==1.26.4
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==8.9.2.26
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-nccl-cu12==2.19.3
-nvidia-nvjitlink-cu12==12.3.101
-nvidia-nvtx-cu12==12.1.105
-oauthlib==3.2.2
-onnxruntime==1.17.0
-opentelemetry-api==1.22.0
-opentelemetry-exporter-otlp-proto-common==1.22.0
-opentelemetry-exporter-otlp-proto-grpc==1.22.0
-opentelemetry-instrumentation==0.43b0
-opentelemetry-instrumentation-asgi==0.43b0
-opentelemetry-instrumentation-fastapi==0.43b0
-opentelemetry-proto==1.22.0
-opentelemetry-sdk==1.22.0
-opentelemetry-semantic-conventions==0.43b0
-opentelemetry-util-http==0.43b0
-orjson==3.9.14
-overrides==7.7.0
-packaging==23.2
-pandas==2.2.0
-pillow==10.2.0
-posthog==3.4.1
-protobuf==4.25.3
-pulsar-client==3.4.0
-pyasn1==0.5.1
-pyasn1-modules==0.3.0
-pydantic==2.6.1
-pydantic_core==2.16.2
-pydub==0.25.1
-pyparsing==3.1.1
-PyPika==0.48.9
-pyproject_hooks==1.0.0
-python-dateutil==2.8.2
-python-dotenv==1.0.1
-python-iso639==2024.2.7
-python-magic==0.4.27
-python-multipart==0.0.9
-pytz==2024.1
-PyYAML==6.0.1
-rapidfuzz==3.6.1
-referencing==0.33.0
-regex==2023.12.25
-requests==2.31.0
-requests-oauthlib==1.3.1
-rpds-py==0.18.0
-rsa==4.9
-s3transfer==0.10.0
-safetensors==0.4.2
-scikit-learn==1.4.1.post1
-scipy==1.12.0
-semantic-version==2.10.0
-sentence-transformers==2.3.1
-sentencepiece==0.1.99
-sgmllib3k==1.0.0
-six==1.16.0
-sniffio==1.3.0
-soupsieve==2.5
-SQLAlchemy==2.0.27
-starlette==0.36.3
-sympy==1.12
-tabulate==0.9.0
-tenacity==8.2.3
-threadpoolctl==3.3.0
-tokenizers==0.15.2
-tomli==2.0.1
-toolz==0.12.1
-torch==2.2.0
-tqdm==4.66.2
-transformers==4.37.2
-triton==2.2.0
-typer==0.9.0
-types-requests==2.31.0.20240125
-typing-inspect==0.9.0
-typing_extensions==4.8.0
-tzdata==2024.1
-unstructured==0.12.4
-unstructured-client==0.18.0
-urllib3==2.0.7
-uvicorn==0.27.1
-uvloop==0.19.0
-validators==0.22.0
-watchfiles==0.21.0
-websocket-client==1.7.0
-websockets==11.0.3
-wrapt==1.16.0
-yarl==1.9.4
-zipp==3.17.0
-aiofiles==23.2.1
-aiohttp==3.9.3
-aiosignal==1.3.1
-altair==5.2.0
-annotated-types==0.6.0
-anyio==4.2.0
-arxiv==2.1.0
-asgiref==3.7.2
-async-timeout==4.0.3
-attrs==23.2.0
-backoff==2.2.1
-bcrypt==4.1.2
-beautifulsoup4==4.12.3
-boto3==1.34.42
-botocore==1.34.42
-build==1.0.3
-cachetools==5.3.2
-certifi==2024.2.2
-chardet==5.2.0
-charset-normalizer==3.3.2
-chroma-hnswlib==0.7.3
-chromadb==0.4.22
-click==8.1.7
-coloredlogs==15.0.1
-contourpy==1.2.0
-cycler==0.12.1
-dataclasses-json==0.6.4
-dataclasses-json-speakeasy==0.5.11
-Deprecated==1.2.14
-emoji==2.10.1
-exceptiongroup==1.2.0
-faiss-cpu==1.7.4
-fastapi==0.109.2
-feedparser==6.0.10
-ffmpy==0.3.2
-filelock==3.13.1
-filetype==1.2.0
-flatbuffers==23.5.26
-fonttools==4.48.1
-frozenlist==1.4.1
-fsspec==2024.2.0
-gitdb==4.0.11
-GitPython==3.1.41
-google-auth==2.27.0
-google_search_results==2.4.2
-googleapis-common-protos==1.62.0
-gradio==3.48.0
-gradio_client==0.6.1
-greenlet==3.0.3
-grpcio==1.60.1
-h11==0.14.0
-httpcore==1.0.3
-httptools==0.6.1
-httpx==0.26.0
-huggingface-hub==0.20.3
-humanfriendly==10.0
-idna==3.6
-importlib-metadata==6.11.0
-importlib-resources==6.1.1
-Jinja2==3.1.3
-jmespath==1.0.1
-joblib==1.3.2
-jsonpatch==1.33
-jsonpath-python==1.0.6
-jsonpointer==2.4
-jsonschema==4.21.1
-jsonschema-specifications==2023.12.1
-kiwisolver==1.4.5
-kubernetes==29.0.0
-langchain==0.1.7
-langchain-community==0.0.20
-langchain-core==0.1.23
-langchainhub==0.1.14
-langdetect==1.0.9
-langsmith==0.0.87
-lxml==5.1.0
-MarkupSafe==2.1.5
-marshmallow==3.20.2
-matplotlib==3.8.3
-mmh3==4.1.0
-monotonic==1.6
-mpmath==1.3.0
-multidict==6.0.5
-mypy-extensions==1.0.0
-networkx==3.2.1
-nltk==3.8.1
-numpy==1.26.4
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==8.9.2.26
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-nccl-cu12==2.19.3
-nvidia-nvjitlink-cu12==12.3.101
-nvidia-nvtx-cu12==12.1.105
-oauthlib==3.2.2
-onnxruntime==1.17.0
-opentelemetry-api==1.22.0
-opentelemetry-exporter-otlp-proto-common==1.22.0
-opentelemetry-exporter-otlp-proto-grpc==1.22.0
-opentelemetry-instrumentation==0.43b0
-opentelemetry-instrumentation-asgi==0.43b0
-opentelemetry-instrumentation-fastapi==0.43b0
-opentelemetry-proto==1.22.0
-opentelemetry-sdk==1.22.0
-opentelemetry-semantic-conventions==0.43b0
-opentelemetry-util-http==0.43b0
-orjson==3.9.14
-overrides==7.7.0
-packaging==23.2
-pandas==2.2.0
-pillow==10.2.0
-posthog==3.4.1
-protobuf==4.25.2
-pulsar-client==3.4.0
-pyasn1==0.5.1
-pyasn1-modules==0.3.0
-pydantic==2.6.1
-pydantic_core==2.16.2
-pydub==0.25.1
-pyparsing==3.1.1
-PyPika==0.48.9
-pyproject_hooks==1.0.0
-python-dateutil==2.8.2
-python-dotenv==1.0.1
-python-iso639==2024.2.7
-python-magic==0.4.27
-python-multipart==0.0.9
-pytz==2024.1
-PyYAML==6.0.1
-rapidfuzz==3.6.1
-referencing==0.33.0
-regex==2023.12.25
-requests==2.31.0
-requests-oauthlib==1.3.1
-rpds-py==0.18.0
-rsa==4.9
-s3transfer==0.10.0
-safetensors==0.4.2
-scikit-learn==1.4.0
-scipy==1.12.0
-semantic-version==2.10.0
-sentence-transformers==2.3.1
-sentencepiece==0.1.99
-sgmllib3k==1.0.0
-six==1.16.0
-smmap==5.0.1
-sniffio==1.3.0
-soupsieve==2.5
-SQLAlchemy==2.0.27
-starlette==0.36.3
-sympy==1.12
-tabulate==0.9.0
-tenacity==8.2.3
-threadpoolctl==3.3.0
-tokenizers==0.15.2
-tomli==2.0.1
-toolz==0.12.1
-torch==2.2.0
-tqdm==4.66.2
-transformers==4.37.2
-triton==2.2.0
-typer==0.9.0
-types-requests==2.31.0.20240125
-typing-inspect==0.9.0
-typing_extensions==4.8.0
-tzdata==2024.1
-unstructured==0.12.4
-unstructured-client==0.18.0
-urllib3==2.0.7
-uvicorn==0.27.1
-uvloop==0.19.0
-validators==0.22.0
-watchfiles==0.21.0
-websocket-client==1.7.0
-websockets==11.0.3
-wrapt==1.16.0
-yarl==1.9.4
-zipp==3.17.0
+chromadb
+google_api_python_client