Upload 6 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
+index.faiss filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.10
+
+# Copy files
+COPY . /app
+WORKDIR /app
+
+# Install dependencies
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+# Run FastAPI app on port 7860 (required by Hugging Face Spaces)
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,56 @@
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+from sentence_transformers import SentenceTransformer
+from transformers import pipeline
+import faiss
+import pickle
+
+app = FastAPI(title="RAG Chatbot API")
+
+# === Enable CORS (optional but recommended for browser-based Razor apps) ===
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # Replace with your domain in production
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# === Load once at startup ===
+chunks_path = "chunks.pkl"
+index_path = "index.faiss"
+
+with open(chunks_path, "rb") as f:
+    chunks = pickle.load(f)
+
+index = faiss.read_index(index_path)
+embedder = SentenceTransformer("all-MiniLM-L6-v2")
+generator = pipeline("text2text-generation", model="google/flan-t5-base")
+
+# === Retrieval and Generation ===
+def retrieve(query, top_k=3):
+    query_embedding = embedder.encode([query], convert_to_numpy=True)
+    distances, indices = index.search(query_embedding, top_k)
+    return [chunks[i] for i in indices[0]]
+
+def generate_answer(context, query):
+    prompt = f"Answer the question based on the context and give meaningfull ending.\n\nContext:\n{context}\n\nQuestion: {query}"
+    response = generator(prompt, max_new_tokens=150)[0]["generated_text"]
+    return response.strip()
+
+
+# === API Endpoint ===
+class QueryRequest(BaseModel):
+    query: str  # Must match Razor payload field
+
+@app.post("/query")
+def ask_question(request: QueryRequest):
+    print(f"✅ Received query: {request.query}")  # Debug log
+    retrieved = retrieve(request.query)
+    context = "\n".join(retrieved)
+    answer = generate_answer(context, request.query)
+    return {
+        "UserQuery": request.query,
+        "RetrievedContext": context,
+        "answer": answer
+    }

chunks.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e74eedc4f1b55a30bc3c2b7f72410d1d4e5bcd41b2f0022077293648bcb140c1
+size 91858

index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f0ded40a06ffe7b66332c82aa95fb01029c724161d60b2fd09f5ddd7b2b142f
+size 305709

process_pdf.py

@@ -0,0 +1,53 @@
+# process_pdf.py
+
+import fitz  # PyMuPDF
+from sentence_transformers import SentenceTransformer
+import faiss
+import numpy as np
+import pickle
+
+# === Step 1: Extract text from PDF ===
+def extract_text_from_pdf(pdf_path):
+    doc = fitz.open(pdf_path)
+    full_text = ""
+    for page in doc:
+        full_text += page.get_text()
+    return full_text
+
+# === Step 2: Chunk text ===
+def chunk_text(text, chunk_size=500):
+    paragraphs = text.split("\n")
+    chunks = []
+    current_chunk = ""
+    for para in paragraphs:
+        if len(current_chunk) + len(para) < chunk_size:
+            current_chunk += para + " "
+        else:
+            chunks.append(current_chunk.strip())
+            current_chunk = para + " "
+    if current_chunk:
+        chunks.append(current_chunk.strip())
+    return chunks
+
+# === Step 3: Embed and save ===
+def build_and_save_index(chunks, embedder, index_path="index.faiss", chunks_path="chunks.pkl"):
+    embeddings = embedder.encode(chunks, convert_to_numpy=True)
+    dimension = embeddings.shape[1]
+    index = faiss.IndexFlatL2(dimension)
+    index.add(embeddings)
+
+    faiss.write_index(index, index_path)
+    with open(chunks_path, "wb") as f:
+        pickle.dump(chunks, f)
+
+    print(f"✅ Saved FAISS index to {index_path}")
+    print(f"✅ Saved chunks to {chunks_path}")
+
+# === Run Once ===
+if __name__ == "__main__":
+    pdf_path = "input.pdf"  # Replace with your actual PDF
+    raw_text = extract_text_from_pdf(pdf_path)
+    chunks = chunk_text(raw_text)
+
+    embedder = SentenceTransformer("all-MiniLM-L6-v2")
+    build_and_save_index(chunks, embedder)

requirements.txt

@@ -0,0 +1,6 @@
+fastapi
+uvicorn
+sentence-transformers
+transformers
+faiss-cpu
+pickle5