Changes in app.py

app.py

@@ -1,15 +1,12 @@
 import gradio as gr
+import os
 from huggingface_hub import InferenceClient
-
+import google.generativeai as genai
 """
 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")
 
-from transformers import AutoTokenizer, pipeline
-
-model_name = "glaiveai/Llama-3-8B-RAG-v1"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
 
 # Example user query
 user_query = """Document:0
@@ -35,6 +32,9 @@ chat = [
 ]
 
 
+genai.configure(api_key=os.environ["GOOGLE_API_KEY"])
+
+model = genai.GenerativeModel("gemini-pro-vision")
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -55,24 +55,11 @@ def respond(
             messages.append({"role": "system", "content": val[1]})
 
     messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    prompt = tokenizer.apply_chat_template(messages, tokenize=False,add_generation_prompt=True)
-    pipe = pipeline('text-generation', model= model_name, tokenizer=model_name, device=0)
-    output = pipe(prompt,
-              max_length=1000,
-              num_return_sequences=1,
-              top_k=50,
-              top_p=top_p,
-              temperature=temperature,
-              do_sample=True,
-              return_full_text=False
-              )
+    response = model.generate_content(messages)
     
-    response = output[0]['generated_text']
 
-    yield response
+    print(response)
+    return response
 
 
     # for message in client.chat_completion(

requirements.txt

@@ -1,3 +1,4 @@
 huggingface_hub==0.22.2
 transformers
-torch
+torch
+google-generativeai