Update main.py

main.py

@@ -1,46 +1,37 @@
-from fastapi import FastAPI, File, UploadFile
-from fastapi import FastAPI, File, UploadFile, Form, Request
-from fastapi.responses import HTMLResponse, FileResponse
-from fastapi.staticfiles import StaticFiles
-from fastapi.templating import Jinja2Templates
-from fastapi import FastAPI, File, UploadFile, HTTPException
-from fastapi.responses import JSONResponse
-from fastapi.responses import StreamingResponse
 from fastapi import FastAPI, Request, Form
-from fastapi.responses import HTMLResponse
+from fastapi.responses import HTMLResponse, FileResponse
 from fastapi.staticfiles import StaticFiles
-from fastapi.templating import Jinja2Templates
 from huggingface_hub import InferenceClient
-import random
-
-API_URL = "https://api-inference.huggingface.co/models/"
-
-client = InferenceClient(
-    "mistralai/Mistral-7B-Instruct-v0.1"
-)
-
-app = FastAPI()
-
-
-def format_prompt(message, history):
-  prompt = "<s>"
-  for user_prompt, bot_response in history:
-    prompt += f"[INST] {user_prompt} [/INST]"
-    prompt += f" {bot_response}</s> "
-  prompt += f"[INST] {message} [/INST]"
-  return prompt
-
 import logging
 
 # Initialize the logger
 logging.basicConfig(level=logging.INFO)  # Adjust the logging level as needed
 logger = logging.getLogger(__name__)
 
+# Hugging Face Inference Client
+client = InferenceClient("meta-llama/Meta-Llama-3-8B-Instruct")
+
+app = FastAPI()
+
+# Format the prompt for the model
+def format_prompt(message, history):
+    prompt = "<s>"
+    for user_prompt, bot_response in history:
+        prompt += f"[INST] {user_prompt} [/INST]"
+        prompt += f" {bot_response}</s> "
+    prompt += f"[INST] {message} [/INST]"
+    return prompt
+
+# Generate response from the model
 def generate(prompt: str, history: list, temperature: float = 0.9, max_new_tokens: int = 512, top_p: float = 0.95, repetition_penalty: float = 1.0) -> str:
     try:
         formatted_prompt = format_prompt(prompt, history)
         logger.info(f"Formatted prompt: {formatted_prompt}")
-        bot_response = client.text_generation(formatted_prompt, temperature=temperature, max_new_tokens=max_new_tokens, top_p=top_p, repetition_penalty=repetition_penalty, stream=True, details=True, return_full_text=False)
+        bot_response = client.text_generation(
+            formatted_prompt, temperature=temperature, max_new_tokens=max_new_tokens,
+            top_p=top_p, repetition_penalty=repetition_penalty, stream=True,
+            details=True, return_full_text=False
+        )
         output = [response.token.text.strip() for response in bot_response if response.token.text.strip()]
         logger.info(f"Bot response tokens: {output}")
         return " ".join(output)
@@ -48,16 +39,6 @@ def generate(prompt: str, history: list, temperature: float = 0.9, max_new_token
         logger.error(f"Error generating text: {e}")
         return ""
 
-
-
-
-
-
-
-
-
-
-
 @app.post("/generate/")
 async def generate_chat(request: Request, prompt: str = Form(...), history: str = Form(...), temperature: float = Form(0.9), max_new_tokens: int = Form(512), top_p: float = Form(0.95), repetition_penalty: float = Form(1.0)):
     history = eval(history)  # Convert history string back to list
@@ -73,5 +54,4 @@ app.mount("/", StaticFiles(directory="static", html=True), name="static")
 
 @app.get("/")
 def index() -> FileResponse:
-    return FileResponse(path="/app/static/index.html", media_type="text/html")
-    
+    return FileResponse(path="static/index.html", media_type="text/html")