Download app.py from TANVEERMAKHDOOM/Demo-Rag-based-app-doc: direct link, hf CLI and curl.
- Browser
- Download file 2.58 kB
-
https://huggingface.co/spaces/TANVEERMAKHDOOM/Demo-Rag-based-app-doc/resolve/main/app.py
- Command line
-
hf download hf://spaces/TANVEERMAKHDOOM/Demo-Rag-based-app-doc/app.py
-
curl -L -o app.py https://huggingface.co/spaces/TANVEERMAKHDOOM/Demo-Rag-based-app-doc/resolve/main/app.py
2.58 kB
| import os | |
| import gdown | |
| import streamlit as st | |
| from PyPDF2 import PdfReader | |
| from langchain_community.embeddings import HuggingFaceEmbeddings | |
| from langchain_community.vectorstores import FAISS | |
| from langchain.text_splitter import RecursiveCharacterTextSplitter | |
| from groq import Groq | |
| # Initialize Groq client | |
| client = Groq(api_key=os.environ['GROQ_API_KEY']) | |
| # Download and save PDF using gdown | |
| def download_pdf(url): | |
| output_path = "/tmp/drive_doc.pdf" | |
| try: | |
| gdown.download(url=url, output=output_path, quiet=True, fuzzy=True) | |
| return output_path | |
| except Exception as e: | |
| st.error(f"❌ Download failed: {e}") | |
| return None | |
| # Extract text from PDF | |
| def extract_text(pdf_path): | |
| reader = PdfReader(pdf_path) | |
| text = "" | |
| for page in reader.pages: | |
| content = page.extract_text() | |
| if content: | |
| text += content | |
| return text | |
| # Split text into chunks | |
| def chunk_text(text): | |
| splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50) | |
| return splitter.split_text(text) | |
| # Create embeddings and store in FAISS | |
| def build_vector_db(chunks): | |
| embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2") | |
| return FAISS.from_texts(chunks, embedding=embeddings) | |
| # Query the vector DB and get response from Groq | |
| def query_groq(query, vector_db): | |
| docs = vector_db.similarity_search(query, k=3) | |
| context = "\n".join([doc.page_content for doc in docs]) | |
| response = client.chat.completions.create( | |
| model="llama3-8b-8192", | |
| messages=[ | |
| {"role": "system", "content": f"Use the following context:\n{context}"}, | |
| {"role": "user", "content": query}, | |
| ] | |
| ) | |
| return response.choices[0].message.content | |
| # --- Streamlit App --- | |
| st.title("📄 RAG QA from Google Drive PDF") | |
| link = "https://drive.google.com/file/d/1SGXNLO841VyHnGiX81oo6x2RHIrTmP5S/view?usp=sharing" | |
| st.write("📥 Downloading and processing document...") | |
| pdf_path = download_pdf(link) | |
| if pdf_path: | |
| try: | |
| text = extract_text(pdf_path) | |
| chunks = chunk_text(text) | |
| vector_db = build_vector_db(chunks) | |
| st.success("✅ Document processed successfully.") | |
| except Exception as e: | |
| st.error(f"❌ Error processing PDF: {e}") | |
| vector_db = None | |
| else: | |
| vector_db = None | |
| query = st.text_input("🔍 Enter your query:") | |
| if query and vector_db: | |
| answer = query_groq(query, vector_db) | |
| st.subheader("💬 Answer:") | |
| st.write(answer) | |
| elif query: | |
| st.warning("⚠️ Document not ready yet.") | |