cognitrix 0.2.3__tar.gz → 0.2.4__tar.gz

cognitrix-0.2.4/PKG-INFO

@@ -0,0 +1,162 @@
+Metadata-Version: 2.1
+Name: cognitrix
+Version: 0.2.4
+Summary: Package for creating AI Agents using llms
+Home-page: https://github.com/theonlyamos/cognitrix
+License: Apache2
+Keywords: cognitrix,ai,agents,ai agents,ai-agents,llms,autonomous agents
+Author: theonlyamos
+Author-email: theonlyamos@gmail.com
+Requires-Python: >=3.12,<4.0
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: License :: Other/Proprietary License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Topic :: Software Development :: Build Tools
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Dist: aiofiles (>=23.2.1,<24.0.0)
+Requires-Dist: aiohttp (>=3.9.3,<4.0.0)
+Requires-Dist: anthropic (>=0.17.0,<0.18.0)
+Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
+Requires-Dist: clarifai (>=10.1.0,<11.0.0)
+Requires-Dist: cohere (>=4.50,<5.0)
+Requires-Dist: deepgram-sdk (==3.*)
+Requires-Dist: google-generativeai (>=0.4.0,<0.5.0)
+Requires-Dist: google-search-results (>=2.4.2,<3.0.0)
+Requires-Dist: groq (>=0.4.1,<0.5.0)
+Requires-Dist: ollama (>=0.2.0,<0.3.0)
+Requires-Dist: openai (>=1.12.0,<2.0.0)
+Requires-Dist: pillow (>=10.2.0,<11.0.0)
+Requires-Dist: pyaudio (>=0.2.14,<0.3.0)
+Requires-Dist: pyautogui (>=0.9.54,<0.10.0)
+Requires-Dist: pydantic (>=2.6.2,<3.0.0)
+Requires-Dist: pydub (>=0.25.1,<0.26.0)
+Requires-Dist: python-dotenv (>=1.0.1,<2.0.0)
+Requires-Dist: requests (>=2.31.0,<3.0.0)
+Requires-Dist: serpapi (>=0.1.5,<0.2.0)
+Requires-Dist: together (>=0.2.11,<0.3.0)
+Requires-Dist: uuid (>=1.30,<2.0)
+Requires-Dist: xmltodict (>=0.13.0,<0.14.0)
+Project-URL: Bug Tracker, https://github.com/theonlyamos/cognitrix/issues
+Project-URL: Repository, https://github.com/theonlyamos/cognitrix
+Description-Content-Type: text/markdown
+
+# Cognitrix
+
+Cognitrix is an open-source autonomous AI agents orchestrator built in Python. It allows you to create and manage AI agents with ease and integrates seamlessly with large language models (LLMs) from various providers. 
+
+## Features
+
+- **Agent Creation and Management:** Create, list, and load AI agents with customizable names, tasks, and configurations.
+- **LLM Integration:** Integrates with multiple LLM providers, including Anthropic (Claude), Cohere, Groq, Google, OpenAI, and Together.
+- **Modular Architecture:** Easily extensible, allowing the addition of new tools, agents, and LLM integrations.
+- **Conversational Interface:** Interact with AI agents through a command-line interface, providing queries and receiving responses.
+- **Tool Integration:** Agents can utilize a variety of tools, including calculators, web searches, file system browsers, and more.
+- **Autonomous Agent Mode:** Agents can operate autonomously, visually perceiving the screen, interacting with UI elements, and performing tasks.
+- **Multimodal Support:** Handles both text and image inputs/outputs, enabling multimodal interactions.
+
+## Architecture
+
+Cognitrix's architecture is designed to be highly modular and extensible:
+
+- **Agents:** The base `Agent` class and specialized classes like `AIAssistant` for creating and managing AI agents.
+- **LLMs:** A collection of classes for integrating with various LLM providers (Cohere, OpenAI, Claude, etc.).
+- **Tools:** A set of tools that agents can utilize. Each tool has a `category` attribute for grouping and management.
+- **Templates:** Customizable prompt templates guide the behavior and output formats of LLMs.
+
+More tools can be added by creating new classes that inherit from the `Tool` base class and specifying a unique `category`.
+
+## Installation
+
+```bash
+pip install cognitrix
+```
+
+Alternatively, you can install directly from GitHub:
+
+```bash
+pip install https://github.com/theonlyamos/cognitrix/archive/main.zip
+```
+
+## Usage
+
+To run Cognitrix with default settings:
+
+```bash
+cognitrix
+```
+
+To list supported LLM providers:
+
+```bash
+cognitrix --providers
+```
+
+To list created agents:
+
+```bash
+cognitrix agents
+```
+
+To list available tools:
+
+```bash
+cognitrix --tools
+```
+
+To run Cognitrix with a specific provider:
+
+```bash
+cognitrix --provider <provider_name>
+```
+
+To run Cognitrix with a specific agent:
+
+```bash
+cognitrix --agent <agent_name>
+```
+
+To run Cognitrix with a category of tools:
+
+```bash
+cognitrix --load-tools "web"
+```
+
+To run Cognitrix with categories of tools:
+
+```bash
+cognitrix --load-tools "web,general"
+```
+
+To create a new agent:
+
+```bash
+cognitrix agents --new
+```
+
+For more options and usage details, use the help command:
+
+```bash
+cognitrix --help
+```
+
+## Contributing
+
+Cognitrix is open source and contributions are welcome! Please refer to [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines on how to contribute.
+
+## License
+
+This project is licensed under the MIT license. See [LICENSE.md](LICENSE.md) for more information.
+
+## Acknowledgments
+
+Cognitrix was created by [Amos Amissah](https://github.com/theonlyamos) and is inspired by projects like AutoGPT and GPT Engineer. Special thanks to the open-source community and AI companies providing LLM APIs.

cognitrix-0.2.4/README.md

@@ -0,0 +1,110 @@
+# Cognitrix
+
+Cognitrix is an open-source autonomous AI agents orchestrator built in Python. It allows you to create and manage AI agents with ease and integrates seamlessly with large language models (LLMs) from various providers. 
+
+## Features
+
+- **Agent Creation and Management:** Create, list, and load AI agents with customizable names, tasks, and configurations.
+- **LLM Integration:** Integrates with multiple LLM providers, including Anthropic (Claude), Cohere, Groq, Google, OpenAI, and Together.
+- **Modular Architecture:** Easily extensible, allowing the addition of new tools, agents, and LLM integrations.
+- **Conversational Interface:** Interact with AI agents through a command-line interface, providing queries and receiving responses.
+- **Tool Integration:** Agents can utilize a variety of tools, including calculators, web searches, file system browsers, and more.
+- **Autonomous Agent Mode:** Agents can operate autonomously, visually perceiving the screen, interacting with UI elements, and performing tasks.
+- **Multimodal Support:** Handles both text and image inputs/outputs, enabling multimodal interactions.
+
+## Architecture
+
+Cognitrix's architecture is designed to be highly modular and extensible:
+
+- **Agents:** The base `Agent` class and specialized classes like `AIAssistant` for creating and managing AI agents.
+- **LLMs:** A collection of classes for integrating with various LLM providers (Cohere, OpenAI, Claude, etc.).
+- **Tools:** A set of tools that agents can utilize. Each tool has a `category` attribute for grouping and management.
+- **Templates:** Customizable prompt templates guide the behavior and output formats of LLMs.
+
+More tools can be added by creating new classes that inherit from the `Tool` base class and specifying a unique `category`.
+
+## Installation
+
+```bash
+pip install cognitrix
+```
+
+Alternatively, you can install directly from GitHub:
+
+```bash
+pip install https://github.com/theonlyamos/cognitrix/archive/main.zip
+```
+
+## Usage
+
+To run Cognitrix with default settings:
+
+```bash
+cognitrix
+```
+
+To list supported LLM providers:
+
+```bash
+cognitrix --providers
+```
+
+To list created agents:
+
+```bash
+cognitrix agents
+```
+
+To list available tools:
+
+```bash
+cognitrix --tools
+```
+
+To run Cognitrix with a specific provider:
+
+```bash
+cognitrix --provider <provider_name>
+```
+
+To run Cognitrix with a specific agent:
+
+```bash
+cognitrix --agent <agent_name>
+```
+
+To run Cognitrix with a category of tools:
+
+```bash
+cognitrix --load-tools "web"
+```
+
+To run Cognitrix with categories of tools:
+
+```bash
+cognitrix --load-tools "web,general"
+```
+
+To create a new agent:
+
+```bash
+cognitrix agents --new
+```
+
+For more options and usage details, use the help command:
+
+```bash
+cognitrix --help
+```
+
+## Contributing
+
+Cognitrix is open source and contributions are welcome! Please refer to [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines on how to contribute.
+
+## License
+
+This project is licensed under the MIT license. See [LICENSE.md](LICENSE.md) for more information.
+
+## Acknowledgments
+
+Cognitrix was created by [Amos Amissah](https://github.com/theonlyamos) and is inspired by projects like AutoGPT and GPT Engineer. Special thanks to the open-source community and AI companies providing LLM APIs.

{cognitrix-0.2.3 → cognitrix-0.2.4}/cognitrix/agents/base.py

@@ -115,19 +115,21 @@ class Agent(BaseModel):
     def get_tool_by_name(self, name: str) -> Optional[Tool]:
         return next((tool for tool in self.tools if tool.name.lower() == name.lower()), None)
 
-    async def process_response(self, response: str) -> Union[dict, str]:
+    async def process_response(self, response: str|dict) -> Union[dict, str]:
         # response = response.replace("'", '"')
-        response = response.replace('\\n', '')
-        response = response.replace("'", "\"")
-        # response = response.replace('"', '\\"')
-        response_data = extract_json(response)
+        response_data = response
+        if isinstance(response, str):
+            response = response.replace('\\n', '')
+            response = response.replace("'", "\"")
+            # response = response.replace('"', '\\"')
+            response_data = extract_json(response)
         
 
         try:
             if isinstance(response_data, dict):
-                final_result_keys = ['final_answer', 'function_call_result', 'respons']
+                # final_result_keys = ['final_answer', 'function_call_result', 'respons']
 
-                if response_data['type'].replace('\\', '') in final_result_keys:
+                if response_data['type'].replace('\\', '') != 'function_call':
                     return response_data['result']
 
                 tool = self.get_tool_by_name(response_data['function'])
@@ -251,16 +253,16 @@ class Agent(BaseModel):
             if isinstance(processsed_response, dict) and processsed_response['type'] == 'function_call_result':
                 query = processsed_response
             else:
-                print(f"\n{self.name}: {processsed_response}")
                 if isinstance(processsed_response, str):
                     transcriber.text_to_speech(processsed_response)
+                print(f"\n{self.name}: {processsed_response}")
 
 
     def start_audio(self, **kwargs):
         transcriber = Transcriber(on_message_callback=self.handle_transcription)  # Pass callback to Transcriber
         if transcriber.start_transcription():
             print("Audio transcription started.")
-            input("\n\nPress Enter to stop recording...\n\n")
+            input("\n\nPress Enter to quit...\n\n")
             transcriber.stop_transcription()
         else:
             print("Failed to start audio transcription.")
@@ -343,7 +345,7 @@ class Agent(BaseModel):
                 async with aiofiles.open(AGENTS_FILE, 'r') as file:
                     content = await file.read()
                     agents = json.loads(content) if content else []
-                    agents.append(new_agent.model_dump())
+                    agents.append(new_agent.dict()) 
 
                 async with aiofiles.open(AGENTS_FILE, 'w') as file:
                     await file.write(json.dumps(agents, indent=4))
@@ -409,7 +411,7 @@ class Agent(BaseModel):
             if agent.id == self.id:
                 agents[index] = self
             
-            updated_agents.append(agent.model_dump())
+            updated_agents.append(agent.dict())
         
         async with aiofiles.open(AGENTS_FILE, 'w') as file:
             await file.write(json.dumps(updated_agents, indent=4))

{cognitrix-0.2.3 → cognitrix-0.2.4}/cognitrix/agents/templates.py

@@ -346,6 +346,8 @@ Example 5 (Final Answer with Chain of Thought):
     "type": "final_answer",
     "result": "25 degrees Celsius is equivalent to 77 degrees Fahrenheit."
 }
+
+The only keys allowed in the json response are ["observervation", "tought", "type", "function", "arguments", "result"].
 """
 
 AUTONOMOUSE_AGENT_2_JSON_REMINDER = """

{cognitrix-0.2.3 → cognitrix-0.2.4}/cognitrix/cli.py

@@ -29,20 +29,58 @@ def add_agent():
     sys.exit()
 
 def list_agents():
-    agents_str = "\nAvailable Agents:"
-    for index, agent in enumerate(asyncio.run(Agent.list_agents())):
-        agents_str += (f"\n[{index}] {agent.name}")                 #type: ignore
-    print(agents_str)
+    agents = asyncio.run(Agent.list_agents())
+    agent_names = [agent.name for agent in agents]
+    max_col = len(max(agent_names, key=len))
+    max_width = 10
+    max_col = max_col if max_col >= max_width else max_width
+    
+    print(max_col)
+    print("\nAvailable Agents:")
+    print(f" {'_'*((int(len(agents)/10)+5)+max_width+1)}")
+    print(f"| #{' '*(int(len(agents)/10))} | {'Agent Name'+' '*(max_col-max_width)} |")
+    print(f"|{'-'*(int(len(agents)/10)+3)}|-{'-'*(max_col)}-|")
+    for index, a in enumerate(agents):
+        padding = (len(str(index)))-int(len(agents)/10)
+        padding = padding if padding else padding + 2
+        print(f"| {str(index) + ' '*padding}| {a.name + ' '*(max_col-len(a.name))} |")
     
 def list_providers():
-    print("\nAvailable providers:")
-    for index, l in enumerate(LLM.list_llms()):
-        print(f"[{index}] {l}")
+    providers = LLM.list_llms()
+    provider_names = [p for p in providers]
+    max_col = len(max(provider_names, key=len))
+    max_width = 9
+    max_col = max_col if max_col >= max_width else max_width
+
+    print("\nAvailable Providers:")
+    print(f" {'_'*((int(len(providers)/10)+5)+max_width+1)}")
+    print(f"| #{' '*(int(len(providers)/10))} | {'Provider'+' '*(max_col-7)}|")
+    print(f"|{'-'*(int(len(providers)/10)+3)}|-{'-'*(max_col)}-|")
+    for index, p in enumerate(providers):
+        padding = (len(str(index)))-int(len(providers)/10)
+        padding = padding if padding else padding + 2
+        print(f"| {str(index) + ' '*padding}| {p + ' '*(max_col-len(p))} |")
+
         
-def list_tools():
+def list_tools(category='all'):
+    tools = []
+    if category == 'all':
+        tools = Tool.list_all_tools()
+    else:
+        tools = Tool.get_tools_by_category(category)
+    tool_names = [t.name for t in tools]
+    max_col = len(max(tool_names, key=len))
+    max_width = 13
+    max_col = max_col if max_col >= max_width else max_width
+
     print("\nAvailable Tools:")
-    for index, l in enumerate(Tool.list_all_tools()):
-        print(f"[{index}] {l.name}")
+    print(f" {'_'*((int(len(tools)/10)+5)+max_col+max_width+4)}")
+    print(f"| #{' '*(int(len(tools)/10))} | {'Tool Name'+' '*(max_col-9)} | {'Tool category'+' '*(max_width-13)} |")
+    print(f"|{'-'*(int(len(tools)/10)+3)}|-{'-'*(max_col)}-|-{'-'*(max_width)}-|")
+    for index, t in enumerate(tools):
+        padding = (len(str(index)))-int(len(tools)/10)
+        padding = padding if padding else padding + 2
+        print(f"| {str(index) + ' '*padding}| {t.name + ' '*(max_col-len(t.name))} | {t.category + ' '*(max_width-len(t.category))} |")
         
 def list_sessions():
     print("\nSaved Sessions:")
@@ -54,7 +92,7 @@ def manage_agents(args: Namespace):
     try:
         if args.new:
             add_agent()
-        elif args.list:
+        if args.list:
             list_agents()
     except KeyboardInterrupt:
         print()
@@ -62,6 +100,17 @@ def manage_agents(args: Namespace):
     except Exception as e:
         logging.exception(e)
         sys.exit(1)
+        
+def manage_tools(args: Namespace):
+    try:
+        if args.list:
+            list_tools(args.list)
+    except KeyboardInterrupt:
+        print()
+        sys.exit()
+    except Exception as e:
+        logging.exception(e)
+        sys.exit(1)
 
 def str_or_file(string):
     if len(string) > 100:
@@ -118,8 +167,16 @@ def start(args: Namespace):
             if args.provider:
                 assistant.llm = provider
             assistant.name = args.name
-            if args.load_all_tools:
+            if 'all' in args.load_tools:
                 assistant.tools = Tool.list_all_tools()
+            else:
+                tools = []
+                for cat in args.load_tools:
+                    loaded_tools = Tool.get_tools_by_category(cat.lower())
+                    tools.extend(loaded_tools)
+
+                assistant.tools = tools
+                
             
             assistant.format_system_prompt()
             asyncio.run(assistant.save())
@@ -137,19 +194,21 @@ def get_arguments():
     agents_parser = subparsers.add_parser('agents', help="Manage agents")
     agents_parser.add_argument("name", type=str, nargs="?", help="Name of an agent to manage (details|update|remove)")  
     agents_parser.add_argument('--new', action='store_true', help='Create a new agent')
-    agents_parser.add_argument('--list', action='store_false', help='List all saved agents')
+    agents_parser.add_argument('-l', '--list', action='store_false', help='List all saved agents')
     agents_parser.add_argument('--update', action='store_true', help='Update an agent')
     agents_parser.add_argument('--remove', action='store_true', help='Delete an agent')
-    
     agents_parser.set_defaults(func=manage_agents)
+    
+    agents_parser = subparsers.add_parser('tools', help="Manage tools")
+    agents_parser.add_argument('-l', '--list', type=str, default='all', nargs='?', choices=['all', 'general', 'system', 'web'], help='List tools by category')
+    agents_parser.set_defaults(func=manage_tools)
 
     parser.add_argument('--name', type=str, default='Assistant', help='Set name of agent')
     parser.add_argument('--provider', default='', help='Set llm provider to use')
     parser.add_argument('--providers', action='store_true', help='Get a list of all supported providers')
     parser.add_argument('--agents', action='store_true', help='List all saved agents')
     parser.add_argument('--agent', type=str, default='Assistant', help='Set which saved agent to use')
-    parser.add_argument('--tools', action='store_true', help='List all available tools')
-    parser.add_argument('--load-all-tools', action='store_true', help='Add all available tools to agent')
+    parser.add_argument('--load-tools', type=lambda s: [i for i in s.split(',')], default='general', help='Add tools by categories to agent')
     parser.add_argument('--model', type=str, default='', help='Specify model or model_url to use')
     parser.add_argument('--api-key', type=str, default='', help='Set api key of selected llm')
     parser.add_argument('--api-base', type=str, default='', help='Set api base of selected llm. Set if using local llm.')

{cognitrix-0.2.3 → cognitrix-0.2.4}/cognitrix/config.py

@@ -3,7 +3,7 @@ import asyncio
 import aiofiles
 import json
 
-VERSION = '0.2.3'
+VERSION = '0.2.4'
 SPIRAL_WORKDIR = Path('~').expanduser() / '.cognitrix'
 
 AGENTS_FILE = SPIRAL_WORKDIR / 'agents.json'

{cognitrix-0.2.3 → cognitrix-0.2.4}/cognitrix/llms/__init__.py

@@ -7,4 +7,5 @@ from cognitrix.llms.google_llm import Google
 from cognitrix.llms.anthropic_llm import Anthropic
 from cognitrix.llms.together_llm import Together
 from cognitrix.llms.clarifai_llm import Clarifai
-from cognitrix.llms.mindsdb_llm import MindsDB
+from cognitrix.llms.mindsdb_llm import MindsDB
+from cognitrix.llms.ollama_llm import Ollama

{cognitrix-0.2.3 → cognitrix-0.2.4}/cognitrix/llms/google_llm.py

@@ -31,7 +31,7 @@ class Google(LLM):
         supports_system_prompt (bool): Flag to indicate if system prompt should be supported
         system_prompt (str): System prompt to prepend to queries
     """
-    model: str = 'gemini-1.5-pro-latest'
+    model: str = 'gemini-1.5-flash'
     """model endpoint to use""" 
     
     temperature: float = 0.0

cognitrix-0.2.4/cognitrix/llms/ollama_llm.py

@@ -0,0 +1,115 @@
+from cognitrix.llms.base import LLM
+from cognitrix.utils import image_to_base64
+from typing import Any, Optional
+from dotenv import load_dotenv
+from ollama import Client
+import logging
+import sys
+import os
+
+logging.basicConfig(
+    format='%(asctime)s - %(levelname)s - [%(filename)s:%(lineno)d] - %(message)s',
+    datefmt='%d-%b-%y %H:%M:%S',
+    level=logging.WARNING
+)
+logger = logging.getLogger('cognitrix.log')
+load_dotenv()
+
+
+class Ollama(LLM):
+    """A class for interacting with the Ollama API.
+
+    Args:
+        model (str): The name of the Local model to use
+        temperature (float): The temperature to use when generating text
+        base_url (str): Base url of local llm server
+        chat_history (list): Chat history
+        max_tokens (int): The maximum number of tokens to generate in the completion
+        supports_system_prompt (bool): Flag to indicate if system prompt should be supported
+        system_prompt (str): System prompt to prepend to queries
+    """
+    
+    model: str = 'llama3'
+    """model endpoint to use""" 
+    
+    vision_model: str = 'llava-phi3'
+    """vision model endpoint to use""" 
+    
+    temperature: float = 0.1
+    """What sampling temperature to use.""" 
+    
+    api_key: str = 'not-needed'
+    """API key""" 
+    
+    base_url: str = 'http://localhost:11434'
+    """Base url of local llm server"""
+    
+    max_tokens: int = 4048
+    """The maximum number of tokens to generate in the completion.""" 
+    
+    chat_history: list[str] = []
+    """Chat history"""
+    
+    supports_system_prompt: bool = True
+    """Flag to indicate if system prompt should be supported"""
+    
+    system_prompt: str = ""
+    """System prompt to prepend to queries"""
+    
+    def format_query(self, message: dict[str, str]) -> list:
+        """Formats a message for the Claude API.
+
+        Args:
+            message (dict[str, str]): The message to be formatted for the Claude API.
+
+        Returns:
+            list: A list of formatted messages for the Claude API.
+        """
+        
+        formatted_message = [*self.chat_history, message]
+        
+        messages = []
+        
+        for fm in formatted_message:
+            if fm['type'] == 'text':
+                messages.append({
+                    "role": fm['role'].lower(),
+                    "content": fm['message']
+                })
+            else:
+                base64_image = image_to_base64(fm['image'])
+                self.model = self.vision_model
+                new_message = {
+                    "role": fm['role'].lower(),
+                    "content": "This is the result of the latest screenshot",
+                    "images": [base64_image]
+                }
+                messages.append(new_message)
+            
+        return messages
+
+    def __call__(self, query: dict, **kwds: dict)->Optional[str]:
+        """Generates a response to a query using the OpenAI API.
+
+        Args:
+            query (dict): The query to generate a response to.
+            kwds (dict): Additional keyword arguments to pass to the OpenAI API.
+
+        Returns:
+            A string containing the generated response.
+        """
+        
+        client = Client('http://localhost:11434')
+        
+        formatted_messages = self.format_query(query)
+        
+        response = client.chat(
+            model=self.model,
+            messages=[
+                {"role": "user", "content": self.system_prompt},
+                *formatted_messages
+            ],
+            stream=False,
+        )
+        print(response)
+        return response['message']['content']                        #type: ignore

{cognitrix-0.2.3 → cognitrix-0.2.4}/cognitrix/llms/openai_llm.py

@@ -30,12 +30,9 @@ class OpenAI(LLM):
         system_prompt (str): System prompt to prepend to queries
     """
     
-    model: str = 'gpt-4-turbo-preview'
+    model: str = 'gpt-4o'
     """model endpoint to use""" 
     
-    vision_model: str = 'gpt-4-vision-preview'
-    """vision model endpoint to use""" 
-    
     temperature: float = 0.1
     """What sampling temperature to use.""" 
     
@@ -84,7 +81,6 @@ class OpenAI(LLM):
                 })
             elif fm['type'] == 'image':
                 base64_image = image_to_base64(fm['image'])
-                # self.model = self.vision_model
                 messages.append({
                     "role": fm['role'].lower(),
                     "content": [
@@ -94,7 +90,9 @@ class OpenAI(LLM):
                         },
                         {
                             "type": "image_url",
-                            "image_url": f"data:image/jpeg;base64,{base64_image}"
+                            "image_url": {
+                                "url": f"data:image/jpeg;base64,{base64_image}"
+                            }
                         }
                     ]
                 })

{cognitrix-0.2.3 → cognitrix-0.2.4}/cognitrix/llms/session.py

@@ -33,10 +33,10 @@ class Session(BaseModel):
                 sessions[index] = self
                 session_exist = True
             
-            updated_sessions.append(session.model_dump())
+            updated_sessions.append(session.dict())
         
         if not session_exist:
-            updated_sessions.append(self.model_dump())
+            updated_sessions.append(self.dict())
             
         with open(SESSIONS_FILE, 'w') as file:
             json.dump(updated_sessions, file, indent=4)