DO NOT MERGE - reduced dependencies list

backend/requirements.txt

@@ -1,79 +1,19 @@
-aiohttp==3.9.3
-aiosignal==1.3.1
-annotated-types==0.6.0
-antlr4-python3-runtime==4.9.3
-anyio==4.3.0
-async-timeout==4.0.3
 asyncio==3.4.3
-attrs==23.2.0
-backoff==2.2.1
-beautifulsoup4==4.12.3
 boto3==1.34.140
 botocore==1.34.140
-cachetools==5.3.3
 certifi==2024.2.2
-cffi==1.16.0
-chardet==5.2.0
-charset-normalizer==3.3.2
-click==8.1.7
-coloredlogs==15.0.1
-contourpy==1.2.0
-cryptography==42.0.2
-cycler==0.12.1
-dataclasses-json==0.6.4
-dataclasses-json-speakeasy==0.5.11
-Deprecated==1.2.14
-distro==1.9.0
-docstring_parser==0.16
-effdet==0.4.1
-emoji==2.10.1
-exceptiongroup==1.2.0
 fastapi==0.111.0
 fastapi-health==0.4.0
-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-api-core==2.18.0
 google-auth==2.29.0
 google_auth_oauthlib==1.2.0
-google-cloud-aiplatform==1.58.0
-google-cloud-bigquery==3.19.0
 google-cloud-core==2.4.1
-google-cloud-resource-manager==1.12.3
-google-cloud-storage==2.17.0
-google-crc32c==1.5.0
-google-resumable-media==2.7.0
-googleapis-common-protos==1.63.0
-greenlet==3.0.3
-grpc-google-iam-v1==0.13.0
-grpcio==1.62.1
-google-ai-generativelanguage==0.6.6
-grpcio-status==1.62.1
-h11==0.14.0
-httpcore==1.0.4
-httpx==0.27.0
-huggingface-hub
-humanfriendly==10.0
-idna==3.6
-importlib-resources==6.1.1
-pip-install==1.3.5
-iopath==0.1.10
-Jinja2==3.1.3
-jmespath==1.0.1
-joblib==1.3.2
-jsonpatch==1.33
-jsonpath-python==1.0.6
-jsonpointer==2.4
 json-repair==0.25.2
-kiwisolver==1.4.5
+pip-install==1.3.5
 langchain==0.3.0
 langchain-aws==0.2.1
 langchain-anthropic==0.2.1
 langchain-fireworks==0.2.0
-langchain-google-genai==2.0.0
 langchain-community==0.3.0
 langchain-core==0.3.5
 langchain-experimental==0.3.1
@@ -83,87 +23,21 @@ langchain-openai==0.2.0
 langchain-text-splitters==0.3.0
 langdetect==1.0.9
 langsmith==0.1.128
-layoutparser==0.3.4
 langserve==0.3.0
-#langchain-cli==0.0.25
-lxml==5.1.0
-MarkupSafe==2.1.5
-marshmallow==3.20.2
-matplotlib==3.7.2
-mpmath==1.3.0
-multidict==6.0.5
-mypy-extensions==1.0.0
 neo4j-rust-ext
-networkx==3.2.1
 nltk==3.8.1
-numpy==1.26.4
-omegaconf==2.3.0
-onnx==1.16.1
-onnxruntime==1.18.1
 openai==1.47.1
 opencv-python==4.8.0.76
-orjson==3.9.15
-packaging==23.2
-pandas==2.2.0
-pdf2image==1.17.0
-pdfminer.six==20221105
-pdfplumber==0.10.4
-pikepdf==8.11.0
-pillow==10.2.0
-pillow_heif==0.15.0
-portalocker==2.8.2
-proto-plus==1.23.0
-protobuf==4.23.4
-psutil==6.0.0
-pyasn1==0.6.0
-pyasn1_modules==0.4.0
-pycocotools==2.0.7
-pycparser==2.21
+psutil==6.1.0
 pydantic==2.8.2
-pydantic_core==2.20.1
-pyparsing==3.0.9
-pypdf==4.0.1
-PyPDF2==3.0.1
-pypdfium2==4.27.0
-pytesseract==0.3.10
-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
 pytube==15.0.0
-pytz==2024.1
-PyYAML==6.0.1
-rapidfuzz==3.6.1
-regex==2023.12.25
-requests==2.32.3
-rsa==4.9
-s3transfer==0.10.1
-safetensors==0.4.1
-shapely==2.0.3
-six==1.16.0
-sniffio==1.3.1
-soupsieve==2.5
+PyPDF2==3.0.1
+PyMuPDF==1.24.5
 starlette==0.37.2
 sse-starlette==2.1.2
 starlette-session==0.4.3
-sympy==1.12
-tabulate==0.9.0
-tenacity==8.2.3
-tiktoken==0.7.0
-timm==0.9.12
-tokenizers==0.19
 tqdm==4.66.2
-transformers==4.42.3
-types-protobuf
-types-requests
-typing-inspect==0.9.0
-typing_extensions==4.12.2
-tzdata==2024.1
-unstructured==0.14.9
-unstructured-client==0.23.8
-unstructured-inference==0.7.36
-unstructured.pytesseract==0.3.12
 unstructured[all-docs]==0.14.9
 urllib3==2.2.2
 uvicorn==0.30.1
@@ -175,7 +49,6 @@ youtube-transcript-api==0.6.2
 zipp==3.17.0
 sentence-transformers==3.0.1
 google-cloud-logging==3.10.0
-PyMuPDF==1.24.5
 pypandoc==1.13
 graphdatascience==1.10
 Secweb==1.11.0

docker-compose.yml

@@ -75,4 +75,4 @@ services:
       - net
 
 networks:
-  net:
+  net: