Upload 3 files

Dockerfile

@@ -0,0 +1,21 @@
+# Use an official lightweight Python image
+FROM python:3.12-slim
+
+# Set working directory inside the container
+WORKDIR /app
+
+# Set the Hugging Face cache directory to /tmp, which is writable
+ENV HF_HOME="/tmp"
+
+# Copy requirements and install dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the rest of the app
+COPY . .
+
+# Expose Gradio's default port
+EXPOSE 7860
+
+# Run the app
+CMD ["python", "-u", "app.py"]

app.py

@@ -123,8 +123,9 @@ def load_pdf(files):
     # Embed the chunks 
     # embedding_model_name = "sentence-transformers/all-MiniLM-L6-v2" 
     embedding_model_name = "bert-base-uncased"
-    embeddings = HuggingFaceEmbeddings(model_name=embedding_model_name, encode_kwargs={"normalize_embeddings": True})
-
+    # embeddings = HuggingFaceEmbeddings(model_name=embedding_model_name, encode_kwargs={"normalize_embeddings": True})
+    embeddings = HuggingFaceEmbeddings()
+    
     # Store the embeddings in the vector store
     vector_store = FAISS.from_documents(texts, embeddings)
 

requirements.txt

@@ -1,9 +1,116 @@
-gradio==4.38.1
-pypdf
-groq
-langchain
-langchain_core
-langchain_groq
-langchain_community
-langchain_huggingface
-faiss-cpu
+aiofiles==24.1.0
+aiohappyeyeballs==2.6.1
+aiohttp==3.12.4
+aiosignal==1.3.2
+annotated-types==0.7.0
+anyio==4.9.0
+attrs==25.3.0
+certifi==2025.4.26
+charset-normalizer==3.4.2
+click==8.2.1
+dataclasses-json==0.6.7
+distro==1.9.0
+faiss-cpu==1.11.0
+fastapi==0.115.12
+ffmpy==0.5.0
+filelock==3.18.0
+frozenlist==1.6.0
+fsspec==2025.5.1
+gradio==5.31.0
+gradio_client==1.10.1
+greenlet==3.2.2
+groovy==0.1.2
+groq==0.25.0
+h11==0.16.0
+hf-xet==1.1.2
+httpcore==1.0.9
+httpx==0.28.1
+httpx-sse==0.4.0
+huggingface-hub==0.32.2
+idna==3.10
+Jinja2==3.1.6
+joblib==1.5.1
+jsonpatch==1.33
+jsonpointer==3.0.0
+langchain==0.3.25
+langchain-community==0.3.24
+langchain-core==0.3.62
+langchain-groq==0.3.2
+langchain-huggingface==0.2.0
+langchain-text-splitters==0.3.8
+langsmith==0.3.43
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+marshmallow==3.26.1
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.4.4
+mypy_extensions==1.1.0
+networkx==3.5
+numpy==2.2.6
+nvidia-cublas-cu12==12.6.4.1
+nvidia-cuda-cupti-cu12==12.6.80
+nvidia-cuda-nvrtc-cu12==12.6.77
+nvidia-cuda-runtime-cu12==12.6.77
+nvidia-cudnn-cu12==9.5.1.17
+nvidia-cufft-cu12==11.3.0.4
+nvidia-cufile-cu12==1.11.1.6
+nvidia-curand-cu12==10.3.7.77
+nvidia-cusolver-cu12==11.7.1.2
+nvidia-cusparse-cu12==12.5.4.2
+nvidia-cusparselt-cu12==0.6.3
+nvidia-nccl-cu12==2.26.2
+nvidia-nvjitlink-cu12==12.6.85
+nvidia-nvtx-cu12==12.6.77
+orjson==3.10.18
+packaging==24.2
+pandas==2.2.3
+pillow==11.2.1
+propcache==0.3.1
+pydantic==2.11.5
+pydantic-settings==2.9.1
+pydantic_core==2.33.2
+pydub==0.25.1
+Pygments==2.19.1
+pypdf==5.5.0
+python-dateutil==2.9.0.post0
+python-dotenv==1.1.0
+python-multipart==0.0.20
+pytz==2025.2
+PyYAML==6.0.2
+regex==2024.11.6
+requests==2.32.3
+requests-toolbelt==1.0.0
+rich==14.0.0
+ruff==0.11.12
+safehttpx==0.1.6
+safetensors==0.5.3
+scikit-learn==1.6.1
+scipy==1.15.3
+semantic-version==2.10.0
+sentence-transformers==4.1.0
+setuptools==80.9.0
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+SQLAlchemy==2.0.41
+starlette==0.46.2
+sympy==1.14.0
+tenacity==9.1.2
+threadpoolctl==3.6.0
+tokenizers==0.21.1
+tomlkit==0.13.2
+torch==2.7.0
+tqdm==4.67.1
+transformers==4.52.3
+triton==3.3.0
+typer==0.16.0
+typing-inspect==0.9.0
+typing-inspection==0.4.1
+typing_extensions==4.13.2
+tzdata==2025.2
+urllib3==2.4.0
+uvicorn==0.34.2
+websockets==15.0.1
+yarl==1.20.0
+zstandard==0.23.0