Update app.py

app.py

@@ -2,13 +2,11 @@ import os
 import json
 import subprocess
 import re
-import ast
 import requests
 from datetime import datetime
 
 import gradio as gr
-from transformers import (pipeline, AutoModelForCausalLM, AutoTokenizer, TextGenerationPipeline, 
-                          TrainingArguments, Trainer, AutoModel, RagRetriever, AutoModelForSeq2SeqLM)
+from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer, TextGenerationPipeline, AutoModel, RagRetriever, AutoModelForSeq2SeqLM
 import torch
 import tree_sitter
 from tree_sitter import Language, Parser
@@ -18,556 +16,235 @@ from io import StringIO
 import sys
 from huggingface_hub import Repository, hf_hub_url, HfApi, snapshot_download
 import tempfile
-
+import logging
+from loguru import logger
+logger.add("app.log", format="{time} {level} {message}", level="INFO")
 
 # Constants
 MODEL_NAME = "bigscience/bloom"
 PROJECT_ROOT = "projects"
 AGENT_DIRECTORY = "agents"
 AVAILABLE_CODE_GENERATIVE_MODELS = [
-    "bigcode/starcoder",  
-    "Salesforce/codegen-350M-mono",  
-    "microsoft/CodeGPT-small",  
-    "google/flan-t5-xl",
-    "facebook/bart-large-cnn", 
+    "bigcode/starcoder",
+    "Salesforce/codegen-350M-mono",
+    "microsoft/CodeGPT-small-py",
+    "NinedayWang/PolyCoder-2.7B",
+    "facebook/incoder-1B",
 ]
 
-
 # Load Models and Resources
 tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
 model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.float16)
 pipe = TextGenerationPipeline(model=model, tokenizer=tokenizer)
 
 # Build Tree-sitter parser libraries (if not already built)
-Language.build_library('build/my-languages.so', ['tree-sitter-python', 'tree-sitter-javascript'])
-PYTHON_LANGUAGE = Language('build/my-languages.so', 'python')
-JAVASCRIPT_LANGUAGE = Language('build/my-languages.so', 'javascript')
+Language.build_library("build/my-languages.so", ["tree-sitter-python", "tree-sitter-javascript"])
+PYTHON_LANGUAGE = Language("build/my-languages.so", "python")
+JAVASCRIPT_LANGUAGE = Language("build/my-languages.so", "javascript")
 parser = Parser()
 
 # Session State Initialization
-if 'chat_history' not in st.session_state:
-    st.session_state.chat_history = []
-if 'terminal_history' not in st.session_state:
-    st.session_state.terminal_history = []
-if 'workspace_projects' not in st.session_state:
-    st.session_state.workspace_projects = {}
-if 'available_agents' not in st.session_state:
-    st.session_state.available_agents = []
-if 'current_state' not in st.session_state:
-    st.session_state.current_state = {
+if 'chat_history' not in gr.State.session_state:
+    gr.State.chat_history = []
+if 'terminal_history' not in gr.State.session_state:
+    gr.State.terminal_history = []
+if 'workspace_projects' not in gr.State.session_state:
+    gr.State.workspace_projects = {}
+if 'available_agents' not in gr.State.session_state:
+    gr.State.available_agents = []
+if 'current_state' not in gr.State.session_state:
+    gr.State.current_state = {
         'toolbox': {},
         'workspace_chat': {}
     }
 
+# Define is_code function
+def is_code(message):
+    return message.lstrip().startswith("```") or message.lstrip().startswith("code:")
 
-# List of top downloaded free code-generative models from Hugging Face Hub
-AVAILABLE_CODE_GENERATIVE_MODELS = [
-    "bigcode/starcoder",  # Popular and powerful
-    "Salesforce/codegen-350M-mono",  # Smaller, good for quick tasks
-    "microsoft/CodeGPT-small",  # Smaller, good for quick tasks
-    "google/flan-t5-xl",  # Powerful, good for complex tasks
-    "facebook/bart-large-cnn",  # Good for text-to-code tasks
-]
+# Define agents variable
+agents = ["python", "javascript", "java"]
 
-# Load pre-trained RAG retriever
-rag_retriever = RagRetriever.from_pretrained("facebook/rag-token-base")  # Use a Hugging Face RAG model
-
-# Load pre-trained chat model
-chat_model = AutoModelForSeq2SeqLM.from_pretrained("microsoft/DialoGPT-medium")  # Use a Hugging Face chat model
-
-# Load tokenizer
-tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-medium")
-
-def process_input(user_input):
-    # Input pipeline: Tokenize and preprocess user input
-    input_ids = tokenizer(user_input, return_tensors="pt").input_ids
-    attention_mask = tokenizer(user_input, return_tensors="pt").attention_mask
-
-    # RAG model: Generate response
-    with torch.no_grad():
-        output = rag_retriever(input_ids, attention_mask=attention_mask)
-        response = output.generator_outputs[0].sequences[0]
-
-    # Chat model: Refine response
-    chat_input = tokenizer(response, return_tensors="pt")
-    chat_input["input_ids"] = chat_input["input_ids"].unsqueeze(0)
-    chat_input["attention_mask"] = chat_input["attention_mask"].unsqueeze(0)
-    with torch.no_grad():
-        chat_output = chat_model(**chat_input)
-        refined_response = chat_output.sequences[0]
-
-    # Output pipeline: Return final response
-    return refined_response
-
-class AIAgent:
-    def __init__(self, name, description, skills):
-        self.name = name
-        self.description = description
-        self.skills = skills
-
-    def create_agent_prompt(self):
-        skills_str = '\n'.join([f"* {skill}" for skill in self.skills])
-        agent_prompt = f"""
-As an elite expert developer, my name is {self.name}. I possess a comprehensive understanding of the following areas:
-{skills_str}
-I am confident that I can leverage my expertise to assist you in developing and deploying cutting-edge web applications. Please feel free to ask any questions or present any challenges you may encounter.
-"""
-        return agent_prompt
-
-    def autonomous_build(self, chat_history, workspace_projects, project_name, selected_model):
-        """
-        Autonomous build logic that continues based on the state of chat history and workspace projects.
-        """
-        summary = "Chat History:\n" + "\n".join([f"User: {u}\nAgent: {a}" for u, a in chat_history])
-        summary += "\n\nWorkspace Projects:\n" + "\n".join([f"{p}: {details}" for p, details in workspace_projects.items()])
-
-        # Analyze chat history and workspace projects to suggest actions
-        # Example:
-        # - Check if the user has requested to create a new file
-        # - Check if the user has requested to install a package
-        # - Check if the user has requested to run a command
-        # - Check if the user has requested to generate code
-        # - Check if the user has requested to translate code
-        # - Check if the user has requested to summarize text
-        # - Check if the user has requested to analyze sentiment
-
-        # Generate a response based on the analysis
-        next_step = "Based on the current state, the next logical step is to implement the main application logic."
-
-        # Ensure project folder exists
-        project_path = os.path.join(PROJECT_ROOT, project_name)
-        if not os.path.exists(project_path):
-            os.makedirs(project_path)
-
-        # Create requirements.txt if it doesn't exist
-        requirements_file = os.path.join(project_path, "requirements.txt")
-        if not os.path.exists(requirements_file):
-            with open(requirements_file, "w") as f:
-                f.write("# Add your project's dependencies here\n")
-
-        # Create app.py if it doesn't exist
-        app_file = os.path.join(project_path, "app.py")
-        if not os.path.exists(app_file):
-            with open(app_file, "w") as f:
-                f.write("# Your project's main application logic goes here\n")
-
-        # Generate GUI code for app.py if requested
-        if "create a gui" in summary.lower():
-            gui_code = generate_code("Create a simple GUI for this application", selected_model)
-            with open(app_file, "a") as f:
-                f.write(gui_code)
-
-        # Run the default build process
-        build_command = "pip install -r requirements.txt && python app.py"
-        try:
-            result = subprocess.run(build_command, shell=True, capture_output=True, text=True, cwd=project_path)
-            st.write(f"Build Output:\n{result.stdout}")
-            if result.stderr:
-                st.error(f"Build Errors:\n{result.stderr}")
-        except Exception as e:
-            st.error(f"Build Error: {e}")
-
-        return summary, next_step
-
-def save_agent_to_file(agent):
-    """Saves the agent's prompt to a file."""
-    if not os.path.exists(AGENT_DIRECTORY):
-        os.makedirs(AGENT_DIRECTORY)
-    file_path = os.path.join(AGENT_DIRECTORY, f"{agent.name}.txt")
-    with open(file_path, "w") as file:
-        file.write(agent.create_agent_prompt())
-    st.session_state.available_agents.append(agent.name)
-
-def load_agent_prompt(agent_name):
-    """Loads an agent prompt from a file."""
-    file_path = os.path.join(AGENT_DIRECTORY, f"{agent_name}.txt")
-    if os.path.exists(file_path):
-        with open(file_path, "r") as file:
-            agent_prompt = file.read()
-        return agent_prompt
-    else:
+# Define load_agent_from_file function
+def load_agent_from_file(agent_name):
+    try:
+        with open(os.path.join(AGENT_DIRECTORY, agent_name + ".json"), "r") as f:
+            return json.load(f)
+    except FileNotFoundError:
         return None
 
-def create_agent_from_text(name, text):
-    skills = text.split('\n')
-    agent = AIAgent(name, "AI agent created from text input.", skills)
-    save_agent_to_file(agent)
-    return agent.create_agent_prompt()
+# Define load_pipeline function
+def load_pipeline(model_category, model_name):
+    return available_models[model_category][model_name]
 
-def chat_interface_with_agent(input_text, agent_name):
-    agent_prompt = load_agent_prompt(agent_name)
-    if agent_prompt is None:
-        return f"Agent {agent_name} not found."
-
-    model_name ="MaziyarPanahi/Codestral-22B-v0.1-GGUF"
-    try:
-        from transformers import AutoModel, AutoTokenizer  # Import AutoModel here
-        model = AutoModel.from_pretrained("MaziyarPanahi/Codestral-22B-v0.1-GGUF")
-        tokenizer = AutoTokenizer.from_pretrained(model_name)
-        generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
-    except EnvironmentError as e:
-        return f"Error loading model: {e}"
-
-    combined_input = f"{agent_prompt}\n\nUser: {input_text}\nAgent:"
-    
-    input_ids = tokenizer.encode(combined_input, return_tensors="pt")
-    max_input_length = 900
-    if input_ids.shape[1] > max_input_length:
-        input_ids = input_ids[:, :max_input_length]
-
-    outputs = model.generate(
-        input_ids, max_new_tokens=50, num_return_sequences=1, do_sample=True,
-        pad_token_id=tokenizer.eos_token_id  # Set pad_token_id to eos_token_id
-    )
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return response
-
-# Terminal interface
-def terminal_interface(command, project_name=None):
-    if project_name:
-        project_path = os.path.join(PROJECT_ROOT, project_name)
-        if not os.path.exists(project_path):
-            return f"Project {project_name} does not exist."
-        result = subprocess.run(command, shell=True, capture_output=True, text=True, cwd=project_path)
-    else:
-        result = subprocess.run(command, shell=True, capture_output=True, text=True)
-    return result.stdout
-
-# Code editor interface
-def code_editor_interface(code):
-    try:
-        formatted_code = black.format_str(code, mode=black.FileMode())
-    except black.NothingChanged:
-        formatted_code = code
-
-    result = StringIO()
-    sys.stdout = result
-    sys.stderr = result
-
-    (pylint_stdout, pylint_stderr) = lint.py_run(code, return_std=True)
-    sys.stdout = sys.__stdout__
-    sys.stderr = sys.__stderr__
-
-    lint_message = pylint_stdout.getvalue() + pylint_stderr.getvalue()
-
-    return formatted_code, lint_message
-
-# Text summarization tool
-def summarize_text(text):
-    summarizer = pipeline("summarization")
-    summary = summarizer(text, max_length=130, min_length=30, do_sample=False)
-    return summary[0]['summary_text']
-
-# Sentiment analysis tool
-def sentiment_analysis(text):
-    analyzer = pipeline("sentiment-analysis")
-    result = analyzer(text)
-    return result[0]['label']
-
-# Text translation tool (code translation)
-def translate_code(code, source_language, target_language):
-    # Use a Hugging Face translation model instead of OpenAI
-    translator = pipeline("translation", model="bartowski/Codestral-22B-v0.1-GGUF")  # Example: English to Spanish
-    translated_code = translator(code, target_lang=target_language)[0]['translation_text']
-    return translated_code
-
-def generate_code(code_idea, model_name):
-    """Generates code using the selected model."""
+# Define execute_translation function
+def execute_translation(code, target_language, pipe):
     try:
-        generator = pipeline('text-generation', model=model_name)
-        generated_code = generator(code_idea, max_length=1000, num_return_sequences=1)[0]['generated_text']
-        return generated_code
+        output = pipe(code, max_length=1000)[0]["generated_text"]
+        return output
     except Exception as e:
-        return f"Error generating code: {e}"
+        logger.error(f"Error in execute_translation function: {e}")
+        return "Error: Unable to translate code."
 
-def chat_interface(input_text):
-    """Handles general chat interactions with the user."""
-    # Use a Hugging Face chatbot model or your own logic
-    chatbot = pipeline("text-generation", model="microsoft/DialoGPT-medium")
-    response = chatbot(input_text, max_length=50, num_return_sequences=1)[0]['generated_text']
-    return response
-
-# Workspace interface
-def workspace_interface(project_name):
-    project_path = os.path.join(PROJECT_ROOT, project_name)
-    if not os.path.exists(project_path):
-        os.makedirs(project_path)
-        st.session_state.workspace_projects[project_name] = {'files': []}
-        return f"Project '{project_name}' created successfully."
-    else:
-        return f"Project '{project_name}' already exists."
-
-# Add code to workspace
-def add_code_to_workspace(project_name, code, file_name):
-    project_path = os.path.join(PROJECT_ROOT, project_name)
-    if not os.path.exists(project_path):
-        return f"Project '{project_name}' does not exist."
-    
-    file_path = os.path.join(project_path, file_name)
-    with open(file_path, "w") as file:
-        file.write(code)
-    st.session_state.workspace_projects[project_name]['files'].append(file_name)
-    return f"Code added to '{file_name}' in project '{project_name}'."
-
-# Streamlit App
-st.title("AI Agent Creator")
-
-# Sidebar navigation
-st.sidebar.title("Navigation")
-app_mode = st.sidebar.selectbox("Choose the app mode", ["AI Agent Creator", "Tool Box", "Workspace Chat App"])
-
-# Get Hugging Face token from secrets.toml
-hf_token = st.secrets["huggingface"]["hf_token"]
-
-if app_mode == "AI Agent Creator":
-    # AI Agent Creator
-    st.header("Create an AI Agent from Text")
-
-    st.subheader("From Text")
-    agent_name = st.text_input("Enter agent name:")
-    text_input = st.text_area("Enter skills (one per line):")
-    if st.button("Create Agent"):
-        agent_prompt = create_agent_from_text(agent_name, text_input)
-        st.success(f"Agent '{agent_name}' created and saved successfully.")
-        st.session_state.available_agents.append(agent_name)
-
-elif app_mode == "Tool Box":
-    # Tool Box
-    st.header("AI-Powered Tools")
-
-    # Chat Interface
-    st.subheader("Chat with CodeCraft")
-    chat_input = st.text_area("Enter your message:")
-    if st.button("Send"):
-        chat_response = chat_interface(chat_input)
-        st.session_state.chat_history.append((chat_input, chat_response))
-        st.write(f"CodeCraft: {chat_response}")
-
-    # Terminal Interface
-    st.subheader("Terminal")
-    terminal_input = st.text_input("Enter a command:")
-    if st.button("Run"):
-        terminal_output = terminal_interface(terminal_input)
-        st.session_state.terminal_history.append((terminal_input, terminal_output))
-        st.code(terminal_output, language="bash")
-
-    # Code Editor Interface
-    st.subheader("Code Editor")
-    code_editor = st.text_area("Write your code:", height=300)
-    if st.button("Format & Lint"):
-        formatted_code, lint_message = code_editor_interface(code_editor)
-        st.code(formatted_code, language="python")
-        st.info(lint_message)
-
-    # Text Summarization Tool
-    st.subheader("Summarize Text")
-    text_to_summarize = st.text_area("Enter text to summarize:")
-    if st.button("Summarize"):
-        summary = summarize_text(text_to_summarize)
-        st.write(f"Summary: {summary}")
-
-    # Sentiment Analysis Tool
-    st.subheader("Sentiment Analysis")
-    sentiment_text = st.text_area("Enter text for sentiment analysis:")
-    if st.button("Analyze Sentiment"):
-        sentiment = sentiment_analysis(sentiment_text)
-        st.write(f"Sentiment: {sentiment}")
-
-    # Text Translation Tool (Code Translation)
-    st.subheader("Translate Code")
-    code_to_translate = st.text_area("Enter code to translate:")
-    source_language = st.text_input("Enter source language (e.g., 'Python'):")
-    target_language = st.text_input("Enter target language (e.g., 'JavaScript'):")
-    if st.button("Translate Code"):
-        translated_code = translate_code(code_to_translate, source_language, target_language)
-        st.code(translated_code, language=target_language.lower())
-
-    # Code Generation
-    st.subheader("Code Generation")
-    code_idea = st.text_input("Enter your code idea:")
-    if st.button("Generate Code"):
-        generated_code = generate_code(code_idea)
-        st.code(generated_code, language="python")
-
-elif app_mode == "Workspace Chat App":
-    # Workspace Chat App
-    st.header("Workspace Chat App")
-
-    # Project Workspace Creation
-    st.subheader("Create a New Project")
-    project_name = st.text_input("Enter project name:")
-    if st.button("Create Project"):
-        workspace_status = workspace_interface(project_name)
-        st.success(workspace_status)
-
-        # Automatically create requirements.txt and app.py
-        project_path = os.path.join(PROJECT_ROOT, project_name)
-        requirements_file = os.path.join(project_path, "requirements.txt")
-        if not os.path.exists(requirements_file):
-            with open(requirements_file, "w") as f:
-                f.write("# Add your project's dependencies here\n")
-
-        app_file = os.path.join(project_path, "app.py")
-        if not os.path.exists(app_file):
-            with open(app_file, "w") as f:
-                f.write("# Your project's main application logic goes here\n")
-
-    # Add Code to Workspace
-    st.subheader("Add Code to Workspace")
-    code_to_add = st.text_area("Enter code to add to workspace:")
-    file_name = st.text_input("Enter file name (e.g., 'app.py'):")
-    if st.button("Add Code"):
-        add_code_status = add_code_to_workspace(project_name, code_to_add, file_name)
-        st.session_state.terminal_history.append((f"Add Code: {code_to_add}", add_code_status))
-        st.success(add_code_status)
-
-    # Terminal Interface with Project Context
-    st.subheader("Terminal (Workspace Context)")
-    terminal_input = st.text_input("Enter a command within the workspace:")
-    if st.button("Run Command"):
-        terminal_output = terminal_interface(terminal_input, project_name)
-        st.session_state.terminal_history.append((terminal_input, terminal_output))
-        st.code(terminal_output, language="bash")
-
-    # Chat Interface for Guidance
-    st.subheader("Chat with CodeCraft for Guidance")
-    chat_input = st.text_area("Enter your message for guidance:")
-    if st.button("Get Guidance"):
-        chat_response = chat_interface(chat_input)
-        st.session_state.chat_history.append((chat_input, chat_response))
-        st.write(f"CodeCraft: {chat_response}")
-
-    # Display Chat History
-    st.subheader("Chat History")
-    for user_input, response in st.session_state.chat_history:
-        st.write(f"User: {user_input}")
-        st.write(f"CodeCraft: {response}")
-
-    # Display Terminal History
-    st.subheader("Terminal History")
-    for command, output in st.session_state.terminal_history:
-        st.write(f"Command: {command}")
-        st.code(output, language="bash")
-
-    # Display Projects and Files
-    st.subheader("Workspace Projects")
-    for project, details in st.session_state.workspace_projects.items():
-        st.write(f"Project: {project}")
-        for file in details['files']:
-            st.write(f"  - {file}")
-
-    # Chat with AI Agents
-    st.subheader("Chat with AI Agents")
-    selected_agent = st.selectbox("Select an AI agent", st.session_state.available_agents)
-    agent_chat_input = st.text_area("Enter your message for the agent:")
-    if st.button("Send to Agent"):
-        agent_chat_response = chat_interface_with_agent(agent_chat_input, selected_agent)
-        st.session_state.chat_history.append((agent_chat_input, agent_chat_response))
-        st.write(f"{selected_agent}: {agent_chat_response}")
-
-    # Code Generation
-    st.subheader("Code Generation")
-    code_idea = st.text_input("Enter your code idea:")
-
-    # Model Selection Menu
-    selected_model = st.selectbox("Select a code-generative model", AVAILABLE_CODE_GENERATIVE_MODELS)
-
-    if st.button("Generate Code"):
-        generated_code = generate_code(code_idea, selected_model)
-        st.code(generated_code, language="python")
-
-    # Automate Build Process
-    st.subheader("Automate Build Process")
-    if st.button("Automate"):
-        agent = AIAgent(selected_agent, "", [])  # Load the agent without skills for now
-        summary, next_step = agent.autonomous_build(st.session_state.chat_history, st.session_state.workspace_projects, project_name, selected_model)
-        st.write("Autonomous Build Summary:")
-        st.write(summary)
-        st.write("Next Step:")
-        st.write(next_step)
-
-        # Use the hf_token to interact with the Hugging Face API
-        api = HfApi(token=hf_token)
-        # Function to create a Space on Hugging Face
-def create_space(api, name, description, public, files, entrypoint="launch.py"):
-    url = f"{hf_hub_url()}spaces/{name}/prepare-repo"
-    headers = {"Authorization": f"Bearer {api.access_token}"}
-
-# Set your Hugging Face API key here
-hf_token = "YOUR_HUGGING_FACE_API_KEY"  # Replace with your actual token
-
-# Other code remains unchanged
-
-class AIAgent:
-    def __init__(self, name, description, skills, hf_api=None):
-        self.name = name
-        self.description = description
-        self.skills = skills
-        self._hf_api = hf_api
-
-    @property
-    def hf_api(self):
-        if not self._hf_api and self.has_valid_hf_token():
-            self._hf_api = HfApi(token=self._hf_token)
-        return self._hf_api
-
-    def has_valid_hf_token(self):
-        return bool(self._hf_token)
-
-    async def autonomous_build(self, chat_history, workspace_projects, project_name, selected_model, hf_token):
-        self._hf_token = hf_token
-        # Continuation of previous methods
-
-    def deploy_built_space_to_hf(self):
-        if not self._hf_api or not self._hf_token:
-            raise ValueError("Cannot deploy the Space since no valid Hugoging Face API connection was established.")
-
-        repository_name = f"my-awesome-space_{datetime.now().timestamp()}"
-        files = get_built_space_files()
-
-        commit_response = self.hf_api.commit_repo(
-            repo_id=repository_name,
-            branch="main",
-            commits=[{"message": "Built Space Commit", "tree": tree_payload}]
-        )
+# Refactor using CodeT5+
+def execute_refactoring_codet5(code: str) -> str:
+    """
+    Refactors the provided code using the CodeT5+ model.
 
-        print("Commit successful:", commit_response)
-        self.publish_space(repository_name)
+    Args:
+        code (str): The code to refactor.
 
-    def publish_space(self, repository_name):
-        publishing_response = self.hf_api.create_model_version(
-            model_name=repository_name,
-            repo_id=repository_name,
-            model_card={},
-            library_card={}
+    Returns:
+        str: The refactored code.
+    """
+    try:
+        refactor_pipe = pipeline(
+            "text2text-generation",
+            model="Salesforce/codet5p-220m-finetune-Refactor"
         )
+        prompt = f"Refactor this Python code:\n{code}"
+        output = refactor_pipe(prompt, max_length=1000)[0]["generated_text"]
+        return output
+    except Exception as e:
+        logger.error(f"Error in execute_refactoring_codet5 function: {e}")
+        return "Error: Unable to refactor code."
+
+# Chat interface with agent
+def chat_interface_with_agent(input_text, agent_name, selected_model):
+    """
+    Handles interaction with the selected AI agent.
+    """
+    agent = load_agent_from_file(agent_name)
+    if not agent:
+        return f"Agent {agent_name} not found."
 
-        print("Space published:", publishing_response)
+    agent.pipeline = available_models[selected_model]
+    agent_prompt = agent.create_agent_prompt()
+    full_prompt = f"{agent_prompt}\n\nUser: {input_text}\nAgent:"
 
-def create_space(api, name, description, public, files, entrypoint="launch.py"):
-    url = f"{hf_hub_url()}spaces/{name}/prepare-repo"
-    headers = {"Authorization": f"Bearer {api.access_token}"}
+    try:
+        response = agent.generate_response(full_prompt)
+    except Exception as e:
+        logger.error(f"Error generating agent response: {e}")
+        response = "Error: Unable to process your request."
 
-    payload = {
-        "public": public,
-        "gitignore_template": "web",
-        "default_branch": "main",
-        "archived": False,
-        "files": []
-    }
+    return response
 
-    for filename, contents in files.items():
-        data = {
-            "content": contents,
-            "path": filename,
-            "encoding": "utf-8",
-            "mode": "overwrite" if "#{random.randint(0, 1)}" not in contents else "merge",
-        }
-        payload["files"].append(data)
-
-    response = requests.post(url, json=payload, headers=headers)
-    response.raise_for_status()
-    location = response.headers.get("Location")
-    wait_for_processing(location, api)
-
-    return Repository(name=name, api=api)
+# Available models
+available_models = {
+    "Code Generation & Completion": {
+        "Salesforce CodeGen-350M (Mono)": pipeline("text-generation", model="Salesforce/codegen-350M-mono"),
+        "BigCode StarCoder": pipeline("text-generation", model="bigcode/starcoder"),
+        "Mixtral-8x7B-v0.1": pipeline("text-generation", model="mistralai/Mixtral-8x7B-v0.1"),
+        "CodeGPT-small-py": pipeline("text-generation", model="microsoft/CodeGPT-small-py"),
+        "PolyCoder-2.7B": pipeline("text-generation", model="NinedayWang/PolyCoder-2.7B"),
+        "InCoder-1B": pipeline("text-generation", model="facebook/incoder-1B"),
+        #... more code generation models
+    },
+    "Code Translation": {
+        "Python to JavaScript": (lambda code, pipe=pipeline("translation", model="transformersbook/codeparrot-translation-en-java"): execute_translation(code, "javascript", pipe), []),  # Pipeline for Python to JavaScript
+        "Python to C++": (lambda code, pipe=pipeline("text-generation", model="konodyuk/codeparrot-small-trans-py-cpp"): execute_translation(code, "cpp", pipe), []),   # Pipeline for Python to C++
+        #... more language pairs
+    },
+    #... other categories
+}
+
+# Gradio interface with tabs
+with gr.Blocks(title="AI Power Tools for Developers") as demo:
+    # --- State ---
+    code = gr.State("")  # Use gr.State to store code across tabs
+    task_dropdown = gr.State(list(available_models.keys())[0])  # Initialize task dropdown
+    model_dropdown = gr.State(
+        list(available_models[task_dropdown.value].keys())[0]
+    )  # Initialize model dropdown
+
+    def update_model_dropdown(selected_task):
+        models_for_task = list(available_models[selected_task].keys())
+        return gr.Dropdown.update(choices=models_for_task)
+
+    with gr.Tab("Chat & Code"):
+        chatbot = gr.Chatbot(elem_id="chatbot")
+        msg = gr.Textbox(label="Enter your message", placeholder="Type your message here...")
+        clear = gr.ClearButton([msg, chatbot])
+
+        def user(message, history):
+            if is_code(message):
+                response = ""  # Initialize response
+                task = message.split()[0].lower()  # Extract task keyword
+
+                # Use the selected model or a default one
+                model_category = task_dropdown.value
+                model_name = model_dropdown.value
+                pipeline = load_pipeline(model_category, model_name)
+
+                if task in agents:
+                    agent = load_agent_from_file(task)
+                    try:
+                        response = agent.generate_response(message)
+                    except Exception as e:
+                        logger.error(f"Error executing agent {task}: {e}")
+                        response = f"Error executing agent {task}: {e}"
+                else:
+                    response = "Invalid command or task not found."
+            else:
+                # Process as natural language request
+                response = pipe(message, max_length=1000)[0]["generated_text"]
+
+            return response, history + [(message, response)]
+
+        msg.change(user, inputs=[msg, chatbot], outputs=[chatbot, chatbot])
+        clear.click(lambda: None, None, chatbot, queue=False)
+
+    # Model Selection Tab
+    with gr.Tab("Model Selection"):
+        task_dropdown.render()
+        model_dropdown.render()
+        task_dropdown.change(update_model_dropdown, task_dropdown, model_dropdown)
+
+    # Workspace Tab
+    with gr.Tab("Workspace"):
+        with gr.Row():
+            with gr.Column():
+                code.render()
+                file_output = gr.File(label="Save File As...", interactive=False)
+            with gr.Column():
+                output = gr.Textbox(label="Output")
+
+        run_btn = gr.Button(value="Run Code")
+        upload_btn = gr.UploadButton("Upload Python File", file_types=[".py"])
+        save_button = gr.Button(value="Save Code")
+
+        def run_code(code_str):
+            try:
+                # Save code to a temporary file
+                with open("temp_code.py", "w") as f:
+                    f.write(code_str)
+
+                # Execute the code using subprocess
+                process = subprocess.Popen(["python", "temp_code.py"], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+                output, error = process.communicate()
+
+                # Return the output and error messages
+                if error:
+                    return "Error: " + error.decode("utf-8")
+                else:
+                    return output.decode("utf-8")
+
+            except Exception as e:
+                logger.error(f"Error running code: {e}")
+                return f"Error running code: {e}"
+
+        def upload_file(file):
+            with open("uploaded_code.py", "wb") as f:
+                f.write(file.file.getvalue())
+            return "File uploaded successfully!"
+
+        def save_code(code_str):
+            file_output.value = code_str
+            return file_output
+
+        run_btn.click(run_code, inputs=[code], outputs=[output])
+        upload_btn.click(upload_file, inputs=[upload_btn], outputs=[output])
+        save_button.click(save_code, inputs=[code], outputs=[file_output])
+
+    demo.launch()