some modifications, this is hacky. I'm trying to get some tangible result first and then will polish everything for production

.gitignore

@@ -1 +1,3 @@
-__pycache__
+__pycache__
+# script for some housekeeping
+f.py            

requirements.txt

@@ -1,209 +1,209 @@
-accelerate==0.30.1
-aiofiles==23.2.1
-aiohttp==3.9.5
-aiosignal==1.3.1
-altair==5.3.0
-annotated-types==0.6.0
-anyio==4.3.0
-asgiref==3.8.1
-asttokens==2.4.1
-attrs==23.2.0
-backoff==2.2.1
-bcrypt==4.1.2
-beautifulsoup4==4.12.3
-blinker==1.8.2
-build==1.2.1
-cachetools==5.3.3
-certifi==2024.2.2
-charset-normalizer==3.3.2
-chroma-hnswlib==0.7.3
-chromadb==0.5.0
-click==8.1.7
-colorama==0.4.6
-coloredlogs==15.0.1
-comm==0.2.2
-contourpy==1.2.1
-cycler==0.12.1
-dataclasses-json==0.6.5
-datasets==2.19.1
-debugpy==1.8.1
-decorator==5.1.1
-Deprecated==1.2.14
-dill==0.3.8
-diskcache==5.6.3
-distro==1.9.0
-dnspython==2.6.1
-email_validator==2.1.1
-evaluate==0.4.2
-executing==2.0.1
-faiss-cpu==1.8.0
-fastapi==0.110.3
-fastapi-cli==0.0.2
-ffmpy==0.3.2
-filelock==3.14.0
-Flask==3.0.3
-flatbuffers==24.3.25
-fonttools==4.51.0
-frozenlist==1.4.1
-fsspec==2024.3.1
-gitdb==4.0.11
-GitPython==3.1.43
-google-auth==2.29.0
-googleapis-common-protos==1.63.0
-gradio==4.31.0
-gradio_client==0.16.2
-greenlet==3.0.3
-grpcio==1.63.0
-h11==0.14.0
-httpcore==1.0.5
-httptools==0.6.1
-httpx==0.27.0
-huggingface-hub==0.23.0
-humanfriendly==10.0
-idna==3.7
-importlib-metadata==7.0.0
-importlib_resources==6.4.0
-ipykernel==6.29.4
-ipython==8.24.0
-itsdangerous==2.2.0
-jedi==0.19.1
-Jinja2==3.1.3
-jsonpatch==1.33
-jsonpointer==2.4
-jsonschema==4.22.0
-jsonschema-specifications==2023.12.1
-jupyter_client==8.6.1
-jupyter_core==5.7.2
-kiwisolver==1.4.5
-kubernetes==29.0.0
-langchain==0.1.17
-langchain-cli==0.0.22
-langchain-community==0.0.36
-langchain-core==0.1.50
-langchain-openai==0.1.6
-langchain-text-splitters==0.0.1
-langserve==0.2.0
-langsmith==0.1.53
-libcst==1.3.1
-llama_cpp_python==0.2.75
-markdown-it-py==3.0.0
-MarkupSafe==2.1.5
-marshmallow==3.21.2
-matplotlib==3.8.4
-matplotlib-inline==0.1.7
-mdurl==0.1.2
-mmh3==4.1.0
-monotonic==1.6
-mpmath==1.3.0
-multidict==6.0.5
-multiprocess==0.70.16
-mypy-extensions==1.0.0
-nest-asyncio==1.6.0
-networkx==3.3
-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==2.20.5
-nvidia-nvjitlink-cu12==12.4.127
-nvidia-nvtx-cu12==12.1.105
-oauthlib==3.2.2
-onnxruntime==1.17.3
-openai==1.25.1
-opentelemetry-api==1.24.0
-opentelemetry-exporter-otlp-proto-common==1.24.0
-opentelemetry-exporter-otlp-proto-grpc==1.24.0
-opentelemetry-instrumentation==0.45b0
-opentelemetry-instrumentation-asgi==0.45b0
-opentelemetry-instrumentation-fastapi==0.45b0
-opentelemetry-proto==1.24.0
-opentelemetry-sdk==1.24.0
-opentelemetry-semantic-conventions==0.45b0
-opentelemetry-util-http==0.45b0
-orjson==3.10.3
-overrides==7.7.0
-packaging==23.2
-pandas==2.2.2
-parso==0.8.4
-pexpect==4.9.0
-pillow==10.3.0
-platformdirs==4.2.1
-posthog==3.5.0
-prompt-toolkit==3.0.43
-protobuf==4.25.3
-psutil==5.9.8
-ptyprocess==0.7.0
-pure-eval==0.2.2
-pyarrow==16.1.0
-pyarrow-hotfix==0.6
-pyasn1==0.6.0
-pyasn1_modules==0.4.0
-pydantic==1.10.13
-pydantic_core==2.18.2
-pydub==0.25.1
-Pygments==2.17.2
-pyparsing==3.1.2
-PyPika==0.48.9
-pyproject-toml==0.0.10
-pyproject_hooks==1.1.0
-python-dateutil==2.9.0.post0
-python-dotenv==1.0.1
-python-multipart==0.0.9
-pytz==2024.1
-PyYAML==6.0.1
-pyzmq==26.0.3
-referencing==0.35.1
-regex==2024.4.28
-requests==2.31.0
-requests-oauthlib==2.0.0
-rich==13.7.1
-rpds-py==0.18.1
-rsa==4.9
-ruff==0.4.4
-safetensors==0.4.3
-semantic-version==2.10.0
-shellingham==1.5.4
-six==1.16.0
-smmap==5.0.1
-sniffio==1.3.1
-soupsieve==2.5
-SQLAlchemy==2.0.29
-sse-starlette==1.8.2
-stack-data==0.6.3
-starlette==0.37.2
-sympy==1.12
-tenacity==8.2.3
-tiktoken==0.6.0
-tokenizers==0.19.1
-toml==0.10.2
-tomlkit==0.12.5
-toolz==0.12.1
-torch==2.3.0
-tornado==6.4
-tqdm==4.66.4
-traitlets==5.14.3
-transformers==4.41.0
-triton==2.3.0
-typing-inspect==0.9.0
-typing_extensions==4.11.0
-tzdata==2024.1
-ujson==5.9.0
-urllib3==2.2.1
-uvicorn==0.23.2
-uvloop==0.19.0
-vtk==9.3.0
-watchfiles==0.21.0
-wcwidth==0.2.13
-websocket-client==1.8.0
-websockets==11.0.3
-Werkzeug==3.0.3
-wrapt==1.16.0
-xxhash==3.4.1
-yarl==1.9.4
-zipp==3.18.1
+accelerate
+aiofiles
+aiohttp
+aiosignal
+altair
+annotated-types
+anyio
+asgiref
+asttokens
+attrs
+backoff
+bcrypt
+beautifulsoup4
+blinker
+build
+cachetools
+certifi
+charset-normalizer
+chroma-hnswlib
+chromadb
+click
+colorama
+coloredlogs
+comm
+contourpy
+cycler
+dataclasses-json
+datasets
+debugpy
+decorator
+Deprecated
+dill
+diskcache
+distro
+dnspython
+email_validator
+evaluate
+executing
+faiss-cpu
+fastapi
+fastapi-cli
+ffmpy
+filelock
+Flask
+flatbuffers
+fonttools
+frozenlist
+fsspec
+gitdb
+GitPython
+google-auth
+googleapis-common-protos
+gradio
+gradio_client
+greenlet
+grpcio
+h11
+httpcore
+httptools
+httpx
+huggingface-hub
+humanfriendly
+idna
+importlib-metadata
+importlib_resources
+ipykernel
+ipython
+itsdangerous
+jedi
+Jinja2
+jsonpatch
+jsonpointer
+jsonschema
+jsonschema-specifications
+jupyter_client
+jupyter_core
+kiwisolver
+kubernetes
+langchain
+langchain-cli
+langchain-community
+langchain-core
+langchain-openai
+langchain-text-splitters
+langserve
+langsmith
+libcst
+llama_cpp_python
+markdown-it-py
+MarkupSafe
+marshmallow
+matplotlib
+matplotlib-inline
+mdurl
+mmh3
+monotonic
+mpmath
+multidict
+multiprocess
+mypy-extensions
+nest-asyncio
+networkx
+numpy
+nvidia-cublas-cu12
+nvidia-cuda-cupti-cu12
+nvidia-cuda-nvrtc-cu12
+nvidia-cuda-runtime-cu12
+nvidia-cudnn-cu12
+nvidia-cufft-cu12
+nvidia-curand-cu12
+nvidia-cusolver-cu12
+nvidia-cusparse-cu12
+nvidia-nccl-cu12
+nvidia-nvjitlink-cu12
+nvidia-nvtx-cu12
+oauthlib
+onnxruntime
+openai
+opentelemetry-api
+opentelemetry-exporter-otlp-proto-common
+opentelemetry-exporter-otlp-proto-grpc
+opentelemetry-instrumentation
+opentelemetry-instrumentation-asgi
+opentelemetry-instrumentation-fastapi
+opentelemetry-proto
+opentelemetry-sdk
+opentelemetry-semantic-conventions
+opentelemetry-util-http
+orjson
+overrides
+packaging
+pandas
+parso
+pexpect
+pillow
+platformdirs
+posthog
+prompt-toolkit
+protobuf
+psutil
+ptyprocess
+pure-eval
+pyarrow
+pyarrow-hotfix
+pyasn1
+pyasn1_modules
+pydantic
+pydantic_core
+pydub
+Pygments
+pyparsing
+PyPika
+pyproject-toml
+pyproject_hooks
+python-dateutil
+python-dotenv
+python-multipart
+pytz
+PyYAML
+pyzmq
+referencing
+regex
+requests
+requests-oauthlib
+rich
+rpds-py
+rsa
+ruff
+safetensors
+semantic-version
+shellingham
+six
+smmap
+sniffio
+soupsieve
+SQLAlchemy
+sse-starlette
+stack-data
+starlette
+sympy
+tenacity
+tiktoken
+tokenizers
+toml
+tomlkit
+toolz
+torch
+tornado
+tqdm
+traitlets
+transformers
+triton
+typing-inspect
+typing_extensions
+tzdata
+ujson
+urllib3
+uvicorn
+uvloop
+vtk
+watchfiles
+wcwidth
+websocket-client
+websockets
+Werkzeug
+wrapt
+xxhash
+yarl
+zipp