modified temperature and max_tokens

ai_generate.py

@@ -42,27 +42,35 @@ vertexai.init(project="proprietary-info-detection", location="us-central1")
 gemini_client = GenerativeModel("gemini-1.5-pro-001")
 claude_client = anthropic.Anthropic(api_key=os.environ.get("ANTHROPIC_API_KEY"))
 
+# For GPT-4 1 word is about 1.3 tokens.
+temperature = 1.0
+max_tokens = 2048
 
 rag_llms = {
     "LLaMA 3": ChatGroq(
-        temperature=0,
+        temperature=temperature,
+        max_tokens=max_tokens,
         model_name="llama3-70b-8192",
     ),
     "OpenAI GPT 4o Mini": ChatOpenAI(
-        temperature=0,
+        temperature=temperature,
+        max_tokens=max_tokens,
         model_name="gpt-4o-mini",
     ),
     "OpenAI GPT 4o": ChatOpenAI(
-        temperature=0,
+        temperature=temperature,
+        max_tokens=max_tokens,
         model_name="gpt-4o",
     ),
     "OpenAI GPT 4": ChatOpenAI(
-        temperature=0,
+        temperature=temperature,
+        max_tokens=max_tokens,
         model_name="gpt-4-turbo",
     ),
-    "Gemini 1.5 Pro": ChatGoogleGenerativeAI(temperature=0, model="gemini-1.5-pro"),
+    "Gemini 1.5 Pro": ChatGoogleGenerativeAI(temperature=temperature, max_tokens=max_tokens, model="gemini-1.5-pro"),
     "Claude Sonnet 3.5": ChatAnthropic(
-        temperature=0,
+        temperature=temperature,
+        max_tokens=max_tokens,
         model_name="claude-3-5-sonnet-20240620",
     ),
 }
@@ -107,8 +115,8 @@ def generate_groq(text, model):
                 "content": "Please follow the instruction and write about the given topic in approximately the given number of words",
             },
         ],
-        temperature=1,
-        max_tokens=1024,
+        temperature=temperature,
+        max_tokens=max_tokens,
         stream=True,
         stop=None,
     )
@@ -124,8 +132,8 @@ def generate_openai(text, model, openai_client):
     response = openai_client.chat.completions.create(
         model=model,
         messages=message,
-        temperature=1,
-        max_tokens=1024,
+        temperature=temperature,
+        max_tokens=max_tokens,
     )
     return response.choices[0].message.content
 
@@ -138,9 +146,8 @@ def generate_gemini(text, model, gemini_client):
         generative_models.HarmCategory.HARM_CATEGORY_HARASSMENT: generative_models.HarmBlockThreshold.BLOCK_MEDIUM_AND_ABOVE,
     }
     generation_config = {
-        "max_output_tokens": 1024,
-        "temperature": 1.0,
-        "top_p": 1.0,
+        "max_output_tokens": max_tokens,
+        "temperature": temperature,
     }
     response = gemini_client.generate_content(
         [text],
@@ -154,8 +161,8 @@ def generate_gemini(text, model, gemini_client):
 def generate_claude(text, model, claude_client):
     response = claude_client.messages.create(
         model=model,
-        max_tokens=1024,
-        temperature=1.0,
+        max_tokens=max_tokens,
+        temperature=temperature,
         system="You are helpful assistant.",
         messages=[{"role": "user", "content": [{"type": "text", "text": text}]}],
     )

app.py

@@ -2,20 +2,18 @@
 nohup python3 app.py &
 """
 
-import openai
-import gradio as gr
-from typing import Dict, List
 import re
 import requests
+from typing import Dict
+from collections import defaultdict
+from datetime import date
+import gradio as gr
+from scipy.special import softmax
 import language_tool_python
+import nltk
 import torch
-from gradio_client import Client
 from transformers import GPT2LMHeadModel, GPT2TokenizerFast
 from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
-from scipy.special import softmax
-from collections import defaultdict
-import nltk
-from datetime import date
 
 from utils import remove_special_characters
 from plagiarism import google_search, months, domain_list, build_date