Update app.py

app.py

@@ -1,64 +1,55 @@
-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)",
-        ),
-    ],
+import gradio as gr
+from langchain.vectorstores import Chroma
+from langchain.storage import InMemoryStore
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.retrievers.multi_vector import MultiVectorRetriever
+
+from app_utils import multi_modal_rag_chain
+
+# Load the vector store and retriever
+vectorstore = Chroma(collection_name="multi_modal_rag",
+                     embedding_function=OpenAIEmbeddings(),
+                     persist_directory="chroma_langchain_db")
+
+id_key = "doc_id"
+store = InMemoryStore()
+retriever = MultiVectorRetriever(
+    vectorstore=vectorstore,
+    docstore=store,
+    id_key=id_key,
 )
-
-
-if __name__ == "__main__":
+retriever = vectorstore.as_retriever()
+chain_multimodal_rag = multi_modal_rag_chain(retriever)
+
+def generate_response(message, history):
+    """
+    This function will be called for each new user message.
+    We run the chain for the *latest user message only*.
+    Then return the chain response as a string.
+    """
+    # Run the chain using the user message
+    response_chunks = chain_multimodal_rag.invoke(message)
+
+    # If the chain is streaming, it might return chunks.
+    # We'll collect them into one final string for simplicity.
+    if hasattr(response_chunks, "__iter__"):
+        # It's a generator or list
+        response_text = "".join(response_chunks)
+    else:
+        response_text = response_chunks
+
+    # Return the final text
+    return response_text
+
+with gr.ChatInterface(
+    fn=generate_response,
+    title="Multi-modal RAG Chatbot",
+    description="Ask a question about the LongNet paper.",
+     examples=[
+        {"text": "What is Dilated attention?"},
+        {"text": "How is Dilated attention better than vanilla attention?"},
+        {"text": "What is the difference between the computational cost of Dilated and Vanilla Attention?"}
+     ],
+) as demo:
     demo.launch()