File size: 2,185 Bytes
0cb2c48 de637e4 0cb2c48 de637e4 0cb2c48 de637e4 1490656 0cb2c48 de637e4 0cb2c48 de637e4 0cb2c48 de637e4 0cb2c48 de637e4 0cb2c48 de637e4 0cb2c48 de637e4 0cb2c48 de637e4 0cb2c48 de637e4 0cb2c48 de637e4 0cb2c48 de637e4 0cb2c48 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 |
import os
import gradio as gr
import tempfile
import faiss
from groq import Groq
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.document_loaders import PyPDFLoader
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import FAISS
# Set your Groq API key
os.environ["GROQ_API_KEY"] = "GROQ_API_KEY"
client = Groq(api_key=os.environ["GROQ_API_KEY"])
# Load PDF and split into chunks
def process_pdf(file):
loader = PyPDFLoader(file.name)
documents = loader.load()
# Split documents into chunks
splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
chunks = splitter.split_documents(documents)
# Create embeddings
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
db = FAISS.from_documents(chunks, embeddings)
return db
# Query handler
def query_pdf(pdf, question):
if pdf is None or question.strip() == "":
return "Please upload a PDF and enter a query."
db = process_pdf(pdf)
retriever = db.as_retriever()
relevant_docs = retriever.get_relevant_documents(question)
context = "\n\n".join([doc.page_content for doc in relevant_docs])
# Send to Groq API
chat_completion = client.chat.completions.create(
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": f"Answer the following question based on the context below:\n\n{context}\n\nQuestion: {question}"}
],
model="llama3-8b-8192"
)
return chat_completion.choices[0].message.content
# Gradio interface
with gr.Blocks() as demo:
gr.Markdown("## 🔍 RAG-based PDF QA with Groq & FAISS")
with gr.Row():
pdf_input = gr.File(label="Upload PDF", file_types=[".pdf"])
query_input = gr.Textbox(label="Ask a question", placeholder="What is the document about?")
answer_output = gr.Textbox(label="Answer")
submit_btn = gr.Button("Get Answer")
submit_btn.click(fn=query_pdf, inputs=[pdf_input, query_input], outputs=answer_output)
demo.launch(share=True, debug=True)
|