Use LangChain

.gitignore

@@ -0,0 +1 @@
+.env

app.py

@@ -1,50 +1,32 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from langchain_core.messages import HumanMessage
+from langchain.chat_models import init_chat_model
 
-"""
-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("HuggingFaceTB/SmolLM2-135M-Instruct")
+model = init_chat_model("gemini-2.0-flash", model_provider="google_genai")
 
 
 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
-
+    user_input: str,
+    messages: list[dict],
+    system_message: str,
+    max_new_tokens: int,
+    temperature: float,
+    top_p: float,
+) -> str:
+    """
+    Respond to user input using the model.
+    """
+    response = model.invoke(
+        messages + [HumanMessage(content=user_input)],
+    )
+    return response.content
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
 demo = gr.ChatInterface(
-    respond,
+    fn=respond,
+    type="messages",
     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"),

requirements.txt

@@ -1 +1,5 @@
-huggingface_hub==0.25.2
+huggingface_hub
+langchain-text-splitters 
+langchain-community 
+langgraph
+langchain-google-genai