Create app.py

app.py

@@ -0,0 +1,74 @@
+import os
+import tempfile
+import gradio as gr
+from langchain.document_loaders import PyPDFLoader, YoutubeLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_openai import OpenAIEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain.chains import RetrievalQA
+from langchain.chat_models import init_chat_model
+
+# --- API KEY HANDLING ---
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY") or os.getenv("openai")
+if not OPENAI_API_KEY:
+    raise ValueError("❌ OPENAI API Key not found. Please add it to secrets as 'OPENAI_API_KEY' or 'openai'.")
+
+# --- GRADIO PIPELINE FUNCTION ---
+def process_inputs(pdf_file, youtube_url, query):
+    docs = []
+
+    # Load PDF
+    try:
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp:
+            tmp.write(pdf_file.read())
+            pdf_path = tmp.name
+        pdf_loader = PyPDFLoader(pdf_path)
+        docs.extend(pdf_loader.load())
+    except Exception as e:
+        return f"❌ Failed to load PDF: {e}"
+
+    # Load YouTube transcript
+    try:
+        yt_loader = YoutubeLoader.from_youtube_url(youtube_url, add_video_info=False)
+        docs.extend(yt_loader.load())
+    except Exception as e:
+        return f"❌ Failed to load YouTube video: {e}"
+
+    if not docs:
+        return "❌ No documents could be loaded from the PDF or YouTube URL."
+
+    # Split
+    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=150)
+    splits = splitter.split_documents(docs)
+
+    # Embed + Vectorstore
+    embedding = OpenAIEmbeddings(model="text-embedding-3-large", api_key=OPENAI_API_KEY)
+    db = FAISS.from_documents(splits, embedding)
+
+    # QA Chain
+    llm = init_chat_model("gpt-4o-mini", model_provider="openai", api_key=OPENAI_API_KEY)
+    qa = RetrievalQA.from_chain_type(llm, retriever=db.as_retriever())
+
+    # Query
+    try:
+        result = qa.invoke({"query": query})
+        return result["result"]
+    except Exception as e:
+        return f"❌ Error during retrieval: {e}"
+
+# --- GRADIO UI ---
+with gr.Blocks() as demo:
+    gr.Markdown("## 📚 Ask Questions from PDF + YouTube Transcript")
+
+    with gr.Row():
+        pdf_input = gr.File(label="Upload PDF", file_types=[".pdf"])
+        yt_input = gr.Textbox(label="YouTube URL", placeholder="https://www.youtube.com/watch?v=...")
+    
+    query_input = gr.Textbox(label="Your Question", placeholder="What did the video/PDF say about X?")
+    output = gr.Textbox(label="Answer")
+
+    run_button = gr.Button("Get Answer")
+    run_button.click(fn=process_inputs, inputs=[pdf_input, yt_input, query_input], outputs=output)
+
+if __name__ == "__main__":
+    demo.launch()