Update app.py

app.py

@@ -1,105 +1,79 @@
 import gradio as gr
 from openai import OpenAI
 import os
-import litellm
-from litellm import completion
-from crewai import Agent, Task, Crew, Process
-from langchain_community.tools.tavily_search import TavilySearchResults
 
-# Environment Variables
 ACCESS_TOKEN = os.getenv("HF_TOKEN")
 TAVILY_API_KEY = os.getenv("TAVILY_API_KEY")
-
-# OpenAI Client Initialization
 client = OpenAI(
     base_url="https://api-inference.huggingface.co/v1/",
     api_key=ACCESS_TOKEN,
 )
 
-# Search Tool Initialization
+# Search Tool
+from langchain_community.tools.tavily_search import TavilySearchResults
 search_tool = TavilySearchResults(tavily_api_key=TAVILY_API_KEY)
 
-# System Prompt
+# Define a comprehensive system prompt
 SYSTEM_PROMPT = """
 You are a highly knowledgeable and reliable Crypto Trading Advisor and Analyzer. 
 Your goal is to assist users in understanding, analyzing, and making informed decisions about cryptocurrency trading. 
 You provide accurate, concise, and actionable advice based on real-time data, historical trends, and established best practices.
 """
 
-# CrewAI Integration
-llm = client  # Using the OpenAI client for CrewAI agents
-
-def run_crypto_crew(topic):
-    researcher = Agent(
-        role='Market Researcher',
-        goal=f'Uncover emerging trends and investment opportunities in the cryptocurrency market. Focus on the topic: {topic}.',
-        backstory='Identify groundbreaking trends and actionable insights.',
-        verbose=True,
-        tools=[search_tool],
-        allow_delegation=False,
-        llm=llm,
-        max_iter=3,
-        max_rpm=10,
-    )
-
-    analyst = Agent(
-        role='Investment Analyst',
-        goal=f'Analyze cryptocurrency market data to extract actionable insights. Focus on the topic: {topic}.',
-        backstory='Draw meaningful conclusions from cryptocurrency market data.',
-        verbose=True,
-        allow_delegation=False,
-        llm=llm,
-    )
-
-    research_task = Task(
-        description=f'Explore the internet to identify trends and investment opportunities. Topic: {topic}.',
-        agent=researcher,
-        expected_output='Detailed summary of research results.'
-    )
-
-    analyst_task = Task(
-        description=f'Analyze the market data to compile a concise report. Topic: {topic}.',
-        agent=analyst,
-        expected_output='Finalized version of the analysis report.'
-    )
-
-    crypto_crew = Crew(
-        agents=[researcher, analyst],
-        tasks=[research_task, analyst_task],
-        process=Process.sequential
-    )
-
-    result = crypto_crew.kickoff()
-    return result.raw
-
-# Chatbot Response Function
-def respond(message, history):
-    max_tokens = 512
-    temperature = 0.7
-    top_p = 0.95
-    frequency_penalty = 0.0
-    seed = None
-
-    # CrewAI'den gelen analiz sonuçları alınır
-    crew_response = run_crypto_crew(message)
-
-    # LLM ile harmanlanarak daha kapsamlı bir cevap üretilir
+# Fixed settings for LLM
+MAX_TOKENS = 512
+TEMPERATURE = 0.3
+TOP_P = 0.95
+FREQUENCY_PENALTY = 0.0
+SEED = -1  # Use None if random seed is preferred
+
+# Function to handle chatbot responses
+def respond(message, history: list[tuple[str, str]]):
+    print(f"Received message: {message}")
+    print(f"History: {history}")
+
+    # Convert seed to None if -1 (meaning random)
+    if SEED == -1:
+        seed = None
+    else:
+        seed = SEED
+
     messages = [{"role": "system", "content": SYSTEM_PROMPT}]
-    for user_part, assistant_part in history:
+    print("System prompt added to messages.")
+
+    # Add conversation history to the context
+    for val in history:
+        user_part = val[0]
+        assistant_part = val[1]
         if user_part:
             messages.append({"role": "user", "content": user_part})
         if assistant_part:
             messages.append({"role": "assistant", "content": assistant_part})
-    messages.append({"role": "user", "content": f"{message}\n\nCrewAI Analysis:\n{crew_response}"})
 
+    # Append the latest user message
+    messages.append({"role": "user", "content": message})
+
+    # Use the search tool to get relevant results based on the message
+    search_results = search_tool.search(message)
+    if search_results:
+        # Combine search results into a string to send to the model
+        search_results_text = "Here are the search results:\n"
+        for result in search_results:
+            search_results_text += f"- {result['title']}: {result['url']}\n"
+        # Add the search results to the messages to be used by LLM
+        messages.append({"role": "assistant", "content": search_results_text})
+
+    # Start response generation
     response = ""
+    print("Sending request to OpenAI API.")
+
     for message_chunk in client.chat.completions.create(
         model="meta-llama/Llama-3.3-70B-Instruct",
-        max_tokens=max_tokens,
+        max_tokens=MAX_TOKENS,
         stream=True,
-        temperature=temperature,
-        top_p=top_p,
-        frequency_penalty=frequency_penalty,
+        temperature=TEMPERATURE,
+        top_p=TOP_P,
+        frequency_penalty=FREQUENCY_PENALTY,
         seed=seed,
         messages=messages,
     ):
@@ -107,8 +81,10 @@ def respond(message, history):
         response += token_text
         yield response
 
-# Gradio UI
-chatbot = gr.Chatbot(height=600, show_copy_button=True, placeholder="Ask about crypto trading or analysis.")
+    print("Completed response generation.")
+
+# Gradio UI (no sliders for the user, settings are fixed in code)
+chatbot = gr.Chatbot(height=600, show_copy_button=True, placeholder="Ask about crypto trading or analysis.", likeable=True)
 
 demo = gr.ChatInterface(
     fn=respond,