Update app.py

app.py

@@ -2,6 +2,7 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 from langchain_community.chat_models import ChatOllama
 from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.output_parsers import StrOutputParser
 """
 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
 """
@@ -40,19 +41,21 @@ def respond(
     # messages.append({"role": "user", "content": message})
     messages.append(("user", message))
 
-    response = ""
+    chain = ChatPromptTemplate.from_messages(messages) | ChatOllama | StrOutputParser()
+    return chain.invoke()
+    # 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
+    # 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
+    #     response += token
+    #     yield response
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface