Upload 3 files

README.md

@@ -1,19 +1,23 @@
----
-title: Docuquery
-emoji: 🚀
-colorFrom: red
-colorTo: red
-sdk: docker
-app_port: 8501
-tags:
-- streamlit
-pinned: false
-short_description: Streamlit template space
----
-
-# Welcome to Streamlit!
-
-Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
-
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
+# 📄 DocuQuery - Free Document Q&A with LangChain + Hugging Face
+
+DocuQuery lets you **upload a PDF and ask questions** about it.  
+This version uses **free Hugging Face models** (no OpenAI required).  
+
+## 🚀 Features
+- Upload a PDF
+- Ask questions in natural language
+- Uses **sentence-transformers for embeddings** + **Flan-T5 for answering**
+- Runs free via Hugging Face Hub
+
+## 🛠️ Tech Stack
+- Python, Streamlit
+- LangChain, FAISS
+- Hugging Face Hub (Flan-T5, MiniLM embeddings)
+
+## ▶️ Run Locally
+```bash
+git clone https://github.com/<your-username>/docuquery.git
+cd docuquery
+pip install -r requirements.txt
+export HUGGINGFACEHUB_API_TOKEN="your_hf_token_here"
+streamlit run app.py

app.py

@@ -0,0 +1,51 @@
+import streamlit as st
+from langchain_community.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores import FAISS
+from langchain.chains import RetrievalQA
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.llms import HuggingFaceHub
+import tempfile
+import os
+
+# Hugging Face API token (free – just create an account on huggingface.co)
+HF_TOKEN = os.getenv("HuggingfacehubAPIToken")
+
+st.set_page_config(page_title="DocuQuery (Free)", page_icon="📄", layout="wide")
+st.title("📄 DocuQuery - Free RAG App with Hugging Face Models")
+
+# Upload PDF
+uploaded_file = st.file_uploader("Upload your PDF file", type="pdf")
+
+if uploaded_file:
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
+        tmp_file.write(uploaded_file.read())
+        file_path = tmp_file.name
+
+    # Load PDF and split text
+    loader = PyPDFLoader(file_path)
+    documents = loader.load()
+
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+    docs = text_splitter.split_documents(documents)
+
+    # Create embeddings with free Hugging Face model
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+    vectorstore = FAISS.from_documents(docs, embeddings)
+
+    retriever = vectorstore.as_retriever()
+
+    # Use a free Hugging Face LLM (lightweight for Q&A)
+    llm = HuggingFaceHub(
+        repo_id="google/flan-t5-base", 
+        huggingfacehub_api_token=HF_TOKEN,
+        model_kwargs={"temperature":0, "max_length":512}
+    )
+
+    qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever)
+
+    query = st.text_input("🔍 Ask a question about your document:")
+
+    if query:
+        answer = qa.run(query)
+        st.markdown(f"**Answer:** {answer}")

requirements.txt

@@ -1,3 +1,7 @@
-altair
-pandas
-streamlit
+streamlit
+langchain
+langchain-community
+faiss-cpu
+sentence-transformers
+pypdf
+huggingface_hub