Create app.py

app.py

@@ -0,0 +1,230 @@
+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("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)
+
+# ================== GLOBAL DATABASE ==================
+vector_db = None
+
+# ================== LLM FUNCTION ==================
+def groq_llm(prompt):
+    if client is None:
+        return "❌ GROQ API key not set. Please set it in environment variables or 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
+
+# ================== PDF PROCESSING ==================
+def process_pdf(file):
+    global vector_db
+
+    if file is None:
+        return "❌ Please upload a PDF file."
+
+    # Save file temporarily
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp:
+        tmp.write(file)
+        pdf_path = tmp.name
+
+    # Load PDF
+    loader = PyPDFLoader(pdf_path)
+    documents = loader.load()
+
+    # Chunking
+    splitter = RecursiveCharacterTextSplitter(
+        chunk_size=500,
+        chunk_overlap=100
+    )
+    docs = splitter.split_documents(documents)
+
+    # Embeddings (open-source)
+    embeddings = HuggingFaceEmbeddings(
+        model_name="sentence-transformers/all-MiniLM-L6-v2"
+    )
+
+    # Vector store
+    vector_db = FAISS.from_documents(docs, embeddings)
+
+    return f"✅ Document processed successfully! {len(docs)} chunks created."
+
+# ================== QUESTION ANSWERING ==================
+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. Use the following context to answer the user's question.
+
+Context:
+{context}
+
+Question:
+{question}
+
+Answer:
+"""
+
+    answer = groq_llm(prompt)
+    return answer
+
+# ================== GRADIO UI ==================
+with gr.Blocks(title="📄 RAG PDF Question Answering App") as demo:
+    gr.Markdown("## 📄 RAG (Retrieval-Augmented Generation) Application")
+    gr.Markdown("Upload a PDF document and ask questions about its content.")
+
+    if client is None:
+        gr.Markdown("⚠️ **GROQ API key is not set.** Please set it to enable answering.")
+
+    with gr.Row():
+        pdf_upload = gr.File(label="Upload PDF", file_types=[".pdf"])
+        process_btn = gr.Button("📥 Process Document")
+
+    status = gr.Textbox(label="Status", interactive=False)
+
+    with gr.Row():
+        question = gr.Textbox(label="Ask a Question", placeholder="Type your question here...")
+        answer = gr.Textbox(label="Answer", interactive=False)
+
+    process_btn.click(fn=process_pdf, inputs=pdf_upload, outputs=status)
+    question.submit(fn=ask_question, inputs=question, outputs=answer)
+
+demo.launch()
+")
+
+client = None
+if GROQ_API_KEY:
+    client = Groq(api_key=GROQ_API_KEY)
+
+# ================== GLOBAL DATABASE ==================
+vector_db = None
+
+# ================== LLM FUNCTION ==================
+def groq_llm(prompt):
+    if client is None:
+        return "❌ GROQ API key not set. Please set it in environment variables or 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
+
+# ================== PDF PROCESSING ==================
+def process_pdf(file):
+    global vector_db
+
+    if file is None:
+        return "❌ Please upload a PDF file."
+
+    # Save file temporarily
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp:
+        tmp.write(file)
+        pdf_path = tmp.name
+
+    # Load PDF
+    loader = PyPDFLoader(pdf_path)
+    documents = loader.load()
+
+    # Chunking
+    splitter = RecursiveCharacterTextSplitter(
+        chunk_size=500,
+        chunk_overlap=100
+    )
+    docs = splitter.split_documents(documents)
+
+    # Embeddings (open-source)
+    embeddings = HuggingFaceEmbeddings(
+        model_name="sentence-transformers/all-MiniLM-L6-v2"
+    )
+
+    # Vector store
+    vector_db = FAISS.from_documents(docs, embeddings)
+
+    return f"✅ Document processed successfully! {len(docs)} chunks created."
+
+# ================== QUESTION ANSWERING ==================
+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. Use the following context to answer the user's question.
+
+Context:
+{context}
+
+Question:
+{question}
+
+Answer:
+"""
+
+    answer = groq_llm(prompt)
+    return answer
+
+# ================== GRADIO UI ==================
+with gr.Blocks(title="📄 RAG PDF Question Answering App") as demo:
+    gr.Markdown("## 📄 RAG (Retrieval-Augmented Generation) Application")
+    gr.Markdown("Upload a PDF document and ask questions about its content.")
+
+    if client is None:
+        gr.Markdown("⚠️ **GROQ API key is not set.** Please set it to enable answering.")
+
+    with gr.Row():
+        pdf_upload = gr.File(label="Upload PDF", file_types=[".pdf"])
+        process_btn = gr.Button("📥 Process Document")
+
+    status = gr.Textbox(label="Status", interactive=False)
+
+    with gr.Row():
+        question = gr.Textbox(label="Ask a Question", placeholder="Type your question here...")
+        answer = gr.Textbox(label="Answer", interactive=False)
+
+    process_btn.click(fn=process_pdf, inputs=pdf_upload, outputs=status)
+    question.submit(fn=ask_question, inputs=question, outputs=answer)
+
+demo.launch()