Create app.py

app.py

@@ -0,0 +1,99 @@
+# Add this import
+import tempfile
+from dotenv import load_dotenv
+import os
+from docling.document_converter import DocumentConverter
+from langchain_community.document_loaders import TextLoader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.vectorstores import FAISS
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain_openai import ChatOpenAI
+from langchain_community.chat_models import ChatAnthropic
+from langchain.chains import RetrievalQA
+import gradio as gr
+import tempfile
+
+
+llm = None
+qa_chain = None
+vectorstore = None
+retriever = None
+
+def process_pdf(file_path):
+    global vectorstore, retriever, qa_chain
+
+    # Parse PDF with Docling
+    converter = DocumentConverter()
+    result = converter.convert(file_path)
+    markdown_content = result.document.export_to_markdown()
+
+    # Save markdown temporarily
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".md", mode="w", encoding="utf-8") as tmp_md:
+        tmp_md.write(markdown_content)
+        tmp_md_path = tmp_md.name
+
+    # Load and split documents
+    loader = TextLoader(tmp_md_path)
+    documents = loader.load()
+
+    splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    docs = splitter.split_documents(documents)
+
+    embeddings = HuggingFaceEmbeddings(model_name="BAAI/bge-small-en-v1.5")
+    vectorstore = FAISS.from_documents(docs, embeddings)
+    retriever = vectorstore.as_retriever()
+
+    # Rebuild QA chain with current LLM
+    if llm is not None:
+        qa_chain = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever)
+
+def setup_chain(api_key, provider):
+    global llm, qa_chain
+
+    if provider.lower() == "anthropic":
+        os.environ["ANTHROPIC_API_KEY"] = api_key
+        llm = ChatAnthropic(model_name="claude-3-sonnet-20240229")
+    elif provider.lower() == "openai":
+        os.environ["OPENAI_API_KEY"] = api_key
+        llm = ChatOpenAI(model_name="gpt-4o")
+    else:
+        return "Unsupported provider. Please select 'openai' or 'anthropic'."
+
+    # If vectorstore and retriever are already set (PDF uploaded), rebuild qa_chain
+    global vectorstore, retriever
+    if retriever is not None:
+        qa_chain = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever)
+
+    return "API key and provider set successfully. You can now upload a PDF and ask questions."
+
+def answer_question(user_input):
+    if qa_chain is None:
+        return "Please upload a PDF and set your API key and provider first."
+    if user_input.strip() == "":
+        return "Please enter a question."
+    response = qa_chain.run(user_input)
+    return response
+
+import gradio as gr
+
+with gr.Blocks() as iface:
+    gr.Markdown("# PDF Chat App with Docling and LangChain\nAsk questions directly from your PDF document.")
+
+    with gr.Row():
+        api_key_input = gr.Textbox(label="API Key", type="password", placeholder="Enter your API Key")
+        provider_input = gr.Dropdown(choices=["openai", "anthropic"], label="Provider", value="openai")
+        set_api_button = gr.Button("Set API Key and Provider")
+
+    api_status = gr.Textbox(label="Status", interactive=False)
+
+    pdf_uploader = gr.File(label="Upload PDF", file_types=[".pdf"])
+
+    question_input = gr.Textbox(lines=2, placeholder="Ask a question about the PDF...")
+    ask_button = gr.Button("Ask")
+    answer_output = gr.Textbox(label="Answer", interactive=False)
+
+    set_api_button.click(fn=setup_chain, inputs=[api_key_input, provider_input], outputs=api_status)
+    pdf_uploader.change(fn=process_pdf, inputs=pdf_uploader, outputs=api_status)
+    ask_button.click(fn=answer_question, inputs=question_input, outputs=answer_output)
+
+iface.launch(share=True)