Refine requirements.txt for deployment

requirements.txt

@@ -1,170 +1,48 @@
-accelerate==1.6.0
-aiohappyeyeballs==2.6.1
-aiohttp==3.11.16
-aiosignal==1.3.2
-altair==5.5.0
-annotated-types==0.7.0
-anyio==4.9.0
-argon2-cffi==23.1.0
-argon2-cffi-bindings==21.2.0
-arrow==1.3.0
-asttokens==3.0.0
-async-lru==2.0.5
-attrs==25.3.0
-babel==2.17.0
-beautifulsoup4==4.13.3
-bleach==6.2.0
-blinker==1.9.0
-cachetools==5.5.2
-certifi==2025.1.31
-cffi==1.17.1
-charset-normalizer==3.4.1
-click==8.1.8
-colorama==0.4.6
-comm==0.2.2
-dataclasses-json==0.6.7
-datasets==3.5.0
-debugpy==1.8.13
-decorator==5.2.1
-defusedxml==0.7.1
-dill==0.3.8
-executing==2.2.0
-faiss-cpu==1.10.0
-fastjsonschema==2.21.1
-filelock==3.18.0
-fqdn==1.5.1
-frozenlist==1.5.0
-fsspec==2024.12.0
-gitdb==4.0.12
-GitPython==3.1.44
-greenlet==3.1.1
-h11==0.14.0
-hf-xet==1.0.3
-httpcore==1.0.7
-httpx==0.28.1
-httpx-sse==0.4.0
-huggingface-hub==0.30.1
-idna==3.10
-ipykernel==6.29.5
-ipython==9.0.2
-ipython_pygments_lexers==1.1.1
-ipywidgets==8.1.5
-isoduration==20.11.0
-jedi==0.19.2
-Jinja2==3.1.6
-joblib==1.4.2
-json5==0.12.0
-jsonpatch==1.33
-jsonpointer==3.0.0
-jsonschema==4.23.0
-jsonschema-specifications==2024.10.1
-jupyter-events==0.12.0
-jupyter-lsp==2.2.5
-jupyter_client==8.6.3
-jupyter_core==5.7.2
-jupyter_server==2.15.0
-jupyter_server_terminals==0.5.3
-jupyterlab==4.4.0
-jupyterlab_pygments==0.3.0
-jupyterlab_server==2.27.3
-jupyterlab_widgets==3.0.13
+streamlit==1.44.1
+# === LangChain & Dependencies ===
 langchain==0.3.23
-langchain-community==0.3.21
+langchain-huggingface==0.1.2 # Use specific package
+langchain-community==0.3.21 # Still needed for FAISS, TextLoader etc.
 langchain-core==0.3.51
-langchain-huggingface==0.1.2
 langchain-text-splitters==0.3.8
-langsmith==0.3.24
-MarkupSafe==3.0.2
-marshmallow==3.26.1
-matplotlib-inline==0.1.7
-mistune==3.1.3
-mpmath==1.3.0
-multidict==6.3.2
-multiprocess==0.70.16
-mypy-extensions==1.0.0
-narwhals==1.33.0
-nbclient==0.10.2
-nbconvert==7.16.6
-nbformat==5.10.4
-nest-asyncio==1.6.0
-networkx==3.4.2
-notebook_shim==0.2.4
-numpy==2.2.4
-orjson==3.10.16
-overrides==7.7.0
-packaging==24.2
-pandas==2.2.3
-pandocfilters==1.5.1
-parso==0.8.4
-pillow==11.1.0
-platformdirs==4.3.7
-prometheus_client==0.21.1
-prompt_toolkit==3.0.50
-propcache==0.3.1
-protobuf==5.29.4
-psutil==7.0.0
-pure_eval==0.2.3
-pyarrow==19.0.1
-pycparser==2.22
-pydantic==2.11.2
-pydantic-settings==2.8.1
-pydantic_core==2.33.1
-pydeck==0.9.1
-Pygments==2.19.1
-python-dateutil==2.9.0.post0
-python-dotenv==1.1.0
-python-json-logger==3.3.0
-pytz==2025.2
-pywin32==310
-pywinpty==2.0.15
-PyYAML==6.0.2
-pyzmq==26.4.0
-referencing==0.36.2
-regex==2024.11.6
-requests==2.32.3
-requests-toolbelt==1.0.0
-rfc3339-validator==0.1.4
-rfc3986-validator==0.1.1
-rpds-py==0.24.0
-safetensors==0.5.3
-scikit-learn==1.6.1
-scipy==1.15.2
-Send2Trash==1.8.3
+# --- FAISS ---
+faiss-cpu==1.10.0 # Explicitly CPU version
+# --- Embeddings ---
 sentence-transformers==4.0.2
-sentencepiece==0.2.0
-setuptools==78.1.0
-six==1.17.0
-smmap==5.0.2
-sniffio==1.3.1
-soupsieve==2.6
-SQLAlchemy==2.0.40
-stack-data==0.6.3
-streamlit==1.44.1
-sympy==1.13.1
-tenacity==9.1.2
-terminado==0.18.1
-threadpoolctl==3.6.0
-tinycss2==1.4.0
-tokenizers==0.21.1
-toml==0.10.2
-torch==2.6.0
-tornado==6.4.2
-tqdm==4.67.1
-traitlets==5.14.3
+# --- LLM & Transformers Backend ---
 transformers==4.51.2
-types-python-dateutil==2.9.0.20241206
-typing-inspect==0.9.0
-typing-inspection==0.4.0
-typing_extensions==4.13.1
-tzdata==2025.2
-uri-template==1.3.0
-urllib3==2.3.0
-watchdog==6.0.0
-wcwidth==0.2.13
-webcolors==24.11.1
-webencodings==0.5.1
-websocket-client==1.8.0
-widgetsnbextension==4.0.13
-xxhash==3.5.0
-yarl==1.18.3
-zstandard==0.23.0
+torch==2.6.0 # Base torch, allow HF Spaces to potentially provide CUDA if needed
+sentencepiece==0.2.0 # Often required by tokenizers
+accelerate==1.6.0 # Often helps Trainer/Pipeline performance
+# --- Data Handling (Minimal needed by LangChain/Models) ---
+numpy==2.2.4
+pandas==2.2.3 # Needed for DataFrame creation within API/Demo if used
+# --- Pydantic (Core LangChain dependency) ---
+pydantic==2.11.2 # Keep this version as LangChain depends on it
+# --- Other Core LangChain Deps (Often pulled automatically, but good to list) ---
+SQLAlchemy==2.0.40 # Often a core dep
+requests>=2.32.2 # For potential external calls / HF Hub downloads
+PyYAML==6.0.2 # For config parsing by libraries
+# --- Required by HuggingFaceEmbeddings/SentenceTransformers ---
+huggingface-hub>=0.24.0 # Crucial for downloading models
+filelock # Often used by HF Hub for caching
+packaging # Often used for version checks
+# --- Required by FAISS ---
+# numpy (already included)
+
+# --- Potentially Optional (If not directly used or pulled by above) ---
+# Remove if causing issues, add back if ModuleNotFoundError occurs:
+# aiohttp # Langchain async dependency
+# dataclasses-json # Langchain dependency
+# jsonpatch # Langchain dependency
+# tenacity # Langchain retry dependency
+# tqdm # For progress bars, might not be needed in deployed app logs
+
+# --- DEFINITELY REMOVE ---
+# - Jupyter related: jupyterlab, notebook, ipykernel, ipywidgets, nbclient, etc.
+# - Local Dev Tools: pytest, pylint, flake8, watchdog, debugpy, etc.
+# - EDA: ydata-profiling / pandas-profiling
+# - Ray Tune: ray, scikit-optimize, hyperopt
+# - Specific OS things: pywin32, pywinpty (unless specifically needed by a core lib)
+# - Database/Other format specific: gcsfs, etc. unless your KB needs them
+# - Build/Unused: setuptools, wheel, etc.