Spaces:
Sleeping
Sleeping
File size: 3,062 Bytes
0b7e06b 57037e0 0b7e06b | 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 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 | import os
import gradio as gr
import tempfile
from dotenv import load_dotenv
from langchain_community.document_loaders import PyPDFLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_community.vectorstores import FAISS
from groq import Groq
# ================= ENVIRONMENT =================
load_dotenv()
GROQ_API_KEY = os.getenv("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")
client = None
if GROQ_API_KEY:
client = Groq(api_key=GROQ_API_KEY)
vector_db = None
# ================= LLM FUNCTION =================
def groq_llm(prompt):
if client is None:
return "❌ GROQ API key not set. Set it in Hugging Face Secrets."
response = client.chat.completions.create(
model="llama-3.3-70b-versatile",
messages=[{"role": "user", "content": prompt}],
)
return response.choices[0].message.content
# ================= PROCESS PDF =================
def process_pdf(file):
global vector_db
if file is None:
return "❌ Please upload a PDF."
with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp:
tmp.write(file)
pdf_path = tmp.name
loader = PyPDFLoader(pdf_path)
documents = loader.load()
splitter = RecursiveCharacterTextSplitter(
chunk_size=500,
chunk_overlap=100
)
docs = splitter.split_documents(documents)
embeddings = HuggingFaceEmbeddings(
model_name="sentence-transformers/all-MiniLM-L6-v2"
)
vector_db = FAISS.from_documents(docs, embeddings)
return f"✅ PDF processed successfully! {len(docs)} chunks created."
# ================= ASK QUESTION =================
def ask_question(question):
global vector_db
if vector_db is None:
return "❌ Please upload and process a document first."
retriever = vector_db.as_retriever(search_kwargs={"k": 3})
docs = retriever.get_relevant_documents(question)
context = "\n\n".join([doc.page_content for doc in docs])
prompt = f"""
You are an intelligent assistant.
Answer ONLY using the provided context.
Context:
{context}
Question:
{question}
Answer:
"""
return groq_llm(prompt)
# ================= GRADIO UI =================
with gr.Blocks(title="📄 RAG PDF QA App") as demo:
gr.Markdown("# 📄 RAG (Retrieval-Augmented Generation) PDF QA")
gr.Markdown("Upload a PDF and ask questions about its content.")
if client is None:
gr.Markdown("⚠️ GROQ_API_KEY not set. Set it in Hugging Face Secrets to enable answering.")
with gr.Row():
pdf_upload = gr.File(label="Upload PDF", file_types=[".pdf"])
process_btn = gr.Button("Process PDF")
status = gr.Textbox(label="Status", interactive=False)
question = gr.Textbox(label="Ask Question")
answer = gr.Textbox(label="Answer", lines=10)
process_btn.click(process_pdf, inputs=pdf_upload, outputs=status)
question.submit(ask_question, inputs=question, outputs=answer)
demo.launch()
|