Create app.py

app.py

@@ -0,0 +1,74 @@
+from haystack.nodes import DensePassageRetriever
+from haystack.document_stores import FAISSDocumentStore
+from haystack.pipelines import ExtractiveQAPipeline
+from transformers import pipeline
+import gradio as gr
+from haystack.utils import convert_files_to_docs
+
+# Step 1: Set up Document Store
+# Create a FAISS document store for efficient retrieval
+document_store = FAISSDocumentStore(embedding_dim=768, faiss_index_factory_str="Flat")
+
+# Step 2: Upload and Process PDF Documents
+def upload_and_process_pdf(file):
+    # Convert PDF file to documents
+    docs = convert_files_to_docs(dir_path=".", file_paths=[file.name])
+    document_store.write_documents(docs)
+    document_store.update_embeddings(retriever)
+    return "Document uploaded and processed successfully."
+
+# Step 3: Set up Retriever
+retriever = DensePassageRetriever(
+    document_store=document_store,
+    query_embedding_model="facebook/dpr-question_encoder-single-nq-base",
+    passage_embedding_model="facebook/dpr-ctx_encoder-single-nq-base",
+)
+
+# Step 4: Set up Generator (using FLAN-T5)
+generator = pipeline("text2text-generation", model="google/flan-t5-base")
+
+# Step 5: Build the Retrieval-Augmented Generation Function
+def rag_system(query):
+    # Retrieve relevant documents
+    retrieved_docs = retriever.retrieve(query, top_k=2)
+    context = " ".join([doc.content for doc in retrieved_docs])
+
+    # Generate answer using the context
+    input_text = f"Question: {query}\nContext: {context}"
+    answer = generator(input_text, max_length=100, do_sample=True)[0]['generated_text']
+
+    # Return results
+    return {
+        "Question": query,
+        "Answer": answer,
+        "Context": context
+    }
+
+# Step 6: Create Gradio Interface
+def query_rag(question):
+    result = rag_system(question)
+    return result["Answer"], result["Context"]
+
+def upload_document(file):
+    message = upload_and_process_pdf(file)
+    return message
+
+interface = gr.Blocks()
+
+with interface:
+    gr.Markdown("# RAG System with PDF Upload")
+    with gr.Tab("Ask a Question"):
+        question = gr.Textbox(label="Enter your question")
+        answer = gr.Textbox(label="Generated Answer")
+        context = gr.Textbox(label="Context")
+        query_button = gr.Button("Get Answer")
+        query_button.click(query_rag, inputs=question, outputs=[answer, context])
+    with gr.Tab("Upload Document"):
+        file_upload = gr.File(label="Upload PDF", file_types=[".pdf"])
+        upload_button = gr.Button("Upload and Process")
+        upload_output = gr.Textbox(label="Upload Status")
+        upload_button.click(upload_document, inputs=file_upload, outputs=upload_output)
+
+# Step 7: Launch the Interface
+if __name__ == "__main__":
+    interface.launch()