Update app.py

app.py

@@ -1,64 +1,38 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+from model_loader import load_embedding_model, load_llm
+from transcript_handler import chunk_text, embed_chunks, create_faiss_index
+from qa_engine import query_faiss, build_prompt
+
+embedder = load_embedding_model()
+llm = load_llm()
+
+index = None
+chunks = []
+
+def upload_transcript(file):
+    global index, chunks
+    text = file.read().decode("utf-8")
+    chunks = chunk_text(text)
+    embeddings, chunks = embed_chunks(chunks, embedder)
+    index = create_faiss_index(embeddings)
+    return "Transcript uploaded and indexed successfully!"
+
+def chat_with_transcript(query):
+    if not index:
+        return "Please upload a transcript first."
+    context = query_faiss(query, index, embedder, chunks)
+    prompt = build_prompt(context, query)
+    response = llm(prompt)[0]['generated_text'].split("Answer:")[-1].strip()
+    return response
+
+with gr.Blocks() as demo:
+    gr.Markdown("# 📄 Chat with a Transcript (Open Source + Free!)")
+    transcript_input = gr.File(label="Upload Transcript (.txt)")
+    upload_button = gr.Button("Upload and Process")
+    query_input = gr.Textbox(label="Ask a question about the transcript")
+    answer_output = gr.Textbox(label="Answer")
+
+    upload_button.click(upload_transcript, inputs=[transcript_input], outputs=[])
+    query_input.submit(chat_with_transcript, inputs=[query_input], outputs=[answer_output])
+
+demo.launch()