init

app.py

@@ -3,7 +3,7 @@ import fitz
 import re
 import numpy as np
 import tensorflow_hub as hub
-import openai
+from openai import OpenAI
 import gradio as gr
 import os
 import shutil
@@ -12,8 +12,13 @@ from tempfile import NamedTemporaryFile
 from sklearn.neighbors import NearestNeighbors
 import huggingface_hub
 
-openai.base_url = "https://api-inference.huggingface.co/models/mistralai/Mixtral-8x7B-Instruct-v0.1/v1/"
-openai.api_key = huggingface_hub.get_token()
+# openai.base_url = "https://api-inference.huggingface.co/models/mistralai/Mixtral-8x7B-Instruct-v0.1/v1/"
+# openai.api_key = huggingface_hub.get_token()
+
+clinet = OpenAI(
+    base_url='https://api-inference.huggingface.co/models/mistralai/Mixtral-8x7B-Instruct-v0.1/v1/',
+    api_key=huggingface_hub.get_token(),
+)
 
 from util import pdf_to_text, text_to_chunks, SemanticSearch
 
@@ -29,24 +34,15 @@ def load_recommender(path, start_page=1):
 def generate_text(prompt, model = "gpt-3.5-turbo-16k-0613"):
     
     model="mistralai/Mixtral-8x7B-Instruct-v0.1"
-    
-    temperature=0.7
     max_tokens=256
-    top_p=1
-    frequency_penalty=0
-    presence_penalty=0
-    message = openai.ChatCompletion.create(
+    message = clinet.chat.completions.create(
         model=model,
         messages=[
             {"role": "system", "content": "You are a helpful assistant."},
             {"role": "assistant", "content": "Here is some initial assistant message."},
             {"role": "user", "content": prompt}
         ],
-        temperature=.3,
         max_tokens=max_tokens,
-        top_p=top_p,
-        frequency_penalty=frequency_penalty,
-        presence_penalty=presence_penalty,
     ).choices[0].message['content']
     return message