Upload 8 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+faiss_index.idx filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,18 @@
+FROM python:3.10-slim-bullseye
+
+WORKDIR /app
+
+# System dependencies
+RUN apt-get update && apt-get install -y git && apt-get upgrade -y && apt-get clean
+
+# Install Python deps
+COPY requirements.txt .
+RUN pip install --upgrade pip && pip install -r requirements.txt
+
+# Copy source
+COPY . .
+
+
+ENV PORT=7860
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]

embeddings.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:399d91b475a5284cb6da0772c2698c9a87cc2935d596336134d4034a1ef2fd6a
+size 652928

faiss_index.idx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b00ac992818054b7dbcb20ef43f3b62c9f24c7ce814bd0ef769738d4920e8cc
+size 652845

generate_chunks.py

@@ -0,0 +1,8 @@
+from app.utils.pdf_parser import extract_chunks_from_pdfs
+import os
+
+pdf_dir = "app/data"
+pdf_files = [os.path.join(pdf_dir, f) for f in os.listdir(pdf_dir) if f.endswith(".pdf")]
+
+extract_chunks_from_pdfs(pdf_files, "app/data/chunks.csv")
+print("✅ chunks.csv generated!")

metadata.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12f368e096c2788de86300c24ed8c4652aa7da370beec29087cd5124bb3b32e6
+size 921211

precompute_embeddings.py

@@ -0,0 +1,30 @@
+import pandas as pd
+import numpy as np
+import pickle
+import faiss
+from sentence_transformers import SentenceTransformer
+
+# Load CSV
+df = pd.read_csv("app/data/chunks.csv")
+texts = df["text"].tolist()
+metadata = df[['chunk_id', 'source_doc', 'page', 'text']].reset_index(drop=True)
+
+# Embed
+model = SentenceTransformer('all-MiniLM-L6-v2')
+embeddings = model.encode(texts, show_progress_bar=True)
+embedding_matrix = np.array(embeddings).astype('float32')
+
+# Build FAISS index
+dimension = embedding_matrix.shape[1]
+index = faiss.IndexFlatL2(dimension)
+index.add(embedding_matrix)
+
+# Save everything
+faiss.write_index(index, "faiss_index.idx")
+np.save("embeddings.npy", embedding_matrix)
+with open("texts.pkl", "wb") as f:
+    pickle.dump(texts, f)
+with open("metadata.pkl", "wb") as f:
+    pickle.dump(metadata, f)
+
+print("✅ Saved: faiss_index.idx, embeddings.npy, texts.pkl, metadata.pkl")

requirements.txt

@@ -0,0 +1,9 @@
+fastapi
+uvicorn
+python-dotenv
+pandas
+faiss-cpu
+sentence-transformers
+PyMuPDF
+google-generativeai
+gdown

texts.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3624250a9779ba5d446b69a9d2818a1d6ac47ebf9b1a00490e4672401a1dc3d
+size 898273