Update app.py

app.py

@@ -1,6 +1,6 @@
 import os
 import gradio as gr
-from langchain.document_loaders import PyPDFLoader, YoutubeLoader
+from langchain.document_loaders import PyPDFLoader, YoutubeLoader, TextLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_openai import OpenAIEmbeddings
 from langchain_community.vectorstores import FAISS
@@ -12,61 +12,72 @@ 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 in Hugging Face secrets as 'OPENAI_API_KEY' or 'openai'.")
 
-# --- PROCESSING PIPELINE FUNCTION ---
-def process_inputs(pdf_file, youtube_url, query):
+# --- PROCESSING FUNCTION ---
+def process_inputs(pdf_file, youtube_url, txt_file, query):
     docs = []
 
     # Load PDF
     try:
-        pdf_path = pdf_file.name  # ✅ Use .name to get the actual file path from Gradio
+        pdf_path = pdf_file.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}"
+    # Load YouTube Transcript (optional)
+    yt_loaded = False
+    if youtube_url:
+        try:
+            yt_loader = YoutubeLoader.from_youtube_url(youtube_url, add_video_info=False)
+            docs.extend(yt_loader.load())
+            yt_loaded = True
+        except Exception as e:
+            print(f"⚠️ YouTube transcript not loaded: {e}")
+
+    # Load text transcript file (optional fallback)
+    if not yt_loaded and txt_file is not None:
+        try:
+            txt_path = txt_file.name
+            txt_loader = TextLoader(txt_path)
+            docs.extend(txt_loader.load())
+        except Exception as e:
+            return f"❌ Failed to load transcript file: {e}"
 
     if not docs:
-        return "❌ No documents could be loaded from the PDF or YouTube URL."
+        return "❌ No documents could be loaded. Please check your inputs."
 
-    # Split documents
+    # Split text into chunks
     splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=150)
     splits = splitter.split_documents(docs)
 
-    # Embedding + Vector Store
-    try:
-        embedding = OpenAIEmbeddings(model="text-embedding-3-large", api_key=OPENAI_API_KEY)
-        db = FAISS.from_documents(splits, embedding)
-    except Exception as e:
-        return f"❌ Embedding failed: {e}"
+    # Embed documents
+    embedding = OpenAIEmbeddings(model="text-embedding-3-large", api_key=OPENAI_API_KEY)
+    db = FAISS.from_documents(splits, embedding)
+
+    # Query using RetrievalQA
+    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())
 
-    # QA Chain
     try:
-        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())
         result = qa.invoke({"query": query})
         return result["result"]
     except Exception as e:
         return f"❌ Retrieval failed: {e}"
 
-# --- GRADIO APP ---
+# --- GRADIO UI ---
 with gr.Blocks() as demo:
-    gr.Markdown("## 📚 Ask Questions from PDF + YouTube Transcript")
+    gr.Markdown("## 📚 Ask Questions from PDF + YouTube Transcript or .txt Upload")
 
     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=...")
+        yt_input = gr.Textbox(label="YouTube URL (Optional)", placeholder="https://www.youtube.com/watch?v=...")
+        txt_input = gr.File(label="Upload Transcript .txt (Optional fallback)", file_types=[".txt"])
 
-    query_input = gr.Textbox(label="Your Question", placeholder="e.g., What did the PDF say about X?")
+    query_input = gr.Textbox(label="Your Question", placeholder="e.g., What did the document 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)
+    run_button.click(fn=process_inputs, inputs=[pdf_input, yt_input, txt_input, query_input], outputs=output)
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()