PraisonAI 2.0.12__tar.gz → 2.0.14__tar.gz

{praisonai-2.0.12 → praisonai-2.0.14}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: PraisonAI
-Version: 2.0.12
+Version: 2.0.14
 Summary: PraisonAI application combines AutoGen and CrewAI or similar frameworks into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customization, and efficient human-agent collaboration.
 Author: Mervin Praison
 Requires-Python: >=3.10,<3.13
@@ -46,7 +46,7 @@ Requires-Dist: openai (>=1.54.0) ; extra == "call"
 Requires-Dist: playwright (>=1.47.0) ; extra == "chat" or extra == "code"
 Requires-Dist: plotly (>=5.24.0) ; extra == "realtime"
 Requires-Dist: praisonai-tools (>=0.0.7) ; extra == "crewai" or extra == "autogen"
-Requires-Dist: praisonaiagents (>=0.0.4)
+Requires-Dist: praisonaiagents (>=0.0.6)
 Requires-Dist: pyautogen (>=0.2.19) ; extra == "autogen"
 Requires-Dist: pydantic (<=2.10.1) ; extra == "chat" or extra == "code"
 Requires-Dist: pyngrok (>=1.4.0) ; extra == "call"
@@ -85,7 +85,129 @@ Description-Content-Type: text/markdown
 
 </div>
 
-Praison AI, leveraging both AutoGen and CrewAI or any other agent framework, represents a low-code, centralised framework designed to simplify the creation and orchestration of multi-agent systems for various LLM applications, emphasizing ease of use, customization, and human-agent interaction.
+PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human–agent collaboration.
+
+## Key Features
+
+- 🤖 Automated AI Agents Creation
+- 🔄 Use CrewAI or AutoGen Framework
+- 💯 100+ LLM Support
+- 💻 Chat with ENTIRE Codebase
+- 🖥️ Interactive UIs
+- 📄 YAML-based Configuration
+- 🛠️ Custom Tool Integration
+- 🔍 Internet Search Capability (using Crawl4AI and Tavily)
+- 👁️ Vision Language Model (VLM) Support
+- 🎙️ Real-time Voice Interaction
+
+## Using No Code
+
+### Auto Mode:
+```bash
+pip install praisonai
+export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
+praisonai --auto create a movie script about Robots in Mars
+```
+
+### Initialise Mode:
+```bash
+pip install praisonai
+export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
+praisonai --init create a movie script about Robots in Mars
+praisonai
+```
+
+## Using Coding
+
+Light weight package dedicated for coding:
+```bash
+pip install praisonaiagents
+```
+
+```bash
+export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
+```
+
+Create app.py file and add the code below:
+```python
+from praisonaiagents import Agent, Task, PraisonAIAgents
+
+# 1. Create agents
+researcher = Agent(
+    name="Researcher",
+    role="Senior Research Analyst",
+    goal="Uncover cutting-edge developments in AI and data science",
+    backstory="""You are an expert at a technology research group, 
+    skilled in identifying trends and analyzing complex data.""",
+    verbose=True,
+    llm="gpt-4o",
+    markdown=True
+)
+writer = Agent(
+    name="Writer",
+    role="Tech Content Strategist",
+    goal="Craft compelling content on tech advancements",
+    backstory="""You are a content strategist known for 
+    making complex tech topics interesting and easy to understand.""",
+    llm="gpt-4o",
+    markdown=True
+)
+
+# 2. Define Tasks
+task1 = Task(
+    name="research_task",
+    description="""Analyze 2024's AI advancements. 
+    Find major trends, new technologies, and their effects.""",
+    expected_output="""A detailed report on 2024 AI advancements""",
+    agent=researcher
+)
+
+task2 = Task(
+    name="writing_task",
+    description="""Create a blog post about major AI advancements using the insights you have.
+    Make it interesting, clear, and suited for tech enthusiasts. 
+    It should be at least 4 paragraphs long.""",
+    expected_output="A blog post of at least 4 paragraphs",
+    agent=writer,
+)
+
+agents = PraisonAIAgents(
+    agents=[researcher, writer],
+    tasks=[task1, task2],
+    verbose=False,
+    process="hierarchical",
+    manager_llm="gpt-4o"
+)
+
+result = agents.start()
+```
+
+Run:
+```bash
+python app.py
+```
+
+## Ollama Integration
+```bash
+export OPENAI_BASE_URL=http://localhost:11434/v1
+```
+
+## Groq Integration
+Replace xxxx with Groq API KEY:
+```bash
+export OPENAI_API_KEY=xxxxxxxxxxx
+export OPENAI_BASE_URL=https://api.groq.com/openai/v1
+```
+
+## Logging
+```bash
+export LOGLEVEL=info
+```
+
+Advanced logging:
+```bash
+export LOGLEVEL=debug
+```
 
 <div align="center">
   <picture>
@@ -195,18 +317,7 @@ When installing with `pip install "praisonai[autogen]"`, you get:
 - Multi-agent conversation capabilities
 - Code execution environment
 
-## Key Features
 
-- 🤖 Automated AI Agents Creation
-- 🔄 Use CrewAI or AutoGen Framework
-- 💯 100+ LLM Support
-- 💻 Chat with ENTIRE Codebase
-- 🖥️ Interactive UIs
-- 📄 YAML-based Configuration
-- 🛠️ Custom Tool Integration
-- 🔍 Internet Search Capability (using Crawl4AI and Tavily)
-- 👁️ Vision Language Model (VLM) Support
-- 🎙️ Real-time Voice Interaction
 
 ## TL;DR Multi Agents
 

{praisonai-2.0.12 → praisonai-2.0.14}/README.md

@@ -20,7 +20,129 @@
 
 </div>
 
-Praison AI, leveraging both AutoGen and CrewAI or any other agent framework, represents a low-code, centralised framework designed to simplify the creation and orchestration of multi-agent systems for various LLM applications, emphasizing ease of use, customization, and human-agent interaction.
+PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human–agent collaboration.
+
+## Key Features
+
+- 🤖 Automated AI Agents Creation
+- 🔄 Use CrewAI or AutoGen Framework
+- 💯 100+ LLM Support
+- 💻 Chat with ENTIRE Codebase
+- 🖥️ Interactive UIs
+- 📄 YAML-based Configuration
+- 🛠️ Custom Tool Integration
+- 🔍 Internet Search Capability (using Crawl4AI and Tavily)
+- 👁️ Vision Language Model (VLM) Support
+- 🎙️ Real-time Voice Interaction
+
+## Using No Code
+
+### Auto Mode:
+```bash
+pip install praisonai
+export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
+praisonai --auto create a movie script about Robots in Mars
+```
+
+### Initialise Mode:
+```bash
+pip install praisonai
+export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
+praisonai --init create a movie script about Robots in Mars
+praisonai
+```
+
+## Using Coding
+
+Light weight package dedicated for coding:
+```bash
+pip install praisonaiagents
+```
+
+```bash
+export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
+```
+
+Create app.py file and add the code below:
+```python
+from praisonaiagents import Agent, Task, PraisonAIAgents
+
+# 1. Create agents
+researcher = Agent(
+    name="Researcher",
+    role="Senior Research Analyst",
+    goal="Uncover cutting-edge developments in AI and data science",
+    backstory="""You are an expert at a technology research group, 
+    skilled in identifying trends and analyzing complex data.""",
+    verbose=True,
+    llm="gpt-4o",
+    markdown=True
+)
+writer = Agent(
+    name="Writer",
+    role="Tech Content Strategist",
+    goal="Craft compelling content on tech advancements",
+    backstory="""You are a content strategist known for 
+    making complex tech topics interesting and easy to understand.""",
+    llm="gpt-4o",
+    markdown=True
+)
+
+# 2. Define Tasks
+task1 = Task(
+    name="research_task",
+    description="""Analyze 2024's AI advancements. 
+    Find major trends, new technologies, and their effects.""",
+    expected_output="""A detailed report on 2024 AI advancements""",
+    agent=researcher
+)
+
+task2 = Task(
+    name="writing_task",
+    description="""Create a blog post about major AI advancements using the insights you have.
+    Make it interesting, clear, and suited for tech enthusiasts. 
+    It should be at least 4 paragraphs long.""",
+    expected_output="A blog post of at least 4 paragraphs",
+    agent=writer,
+)
+
+agents = PraisonAIAgents(
+    agents=[researcher, writer],
+    tasks=[task1, task2],
+    verbose=False,
+    process="hierarchical",
+    manager_llm="gpt-4o"
+)
+
+result = agents.start()
+```
+
+Run:
+```bash
+python app.py
+```
+
+## Ollama Integration
+```bash
+export OPENAI_BASE_URL=http://localhost:11434/v1
+```
+
+## Groq Integration
+Replace xxxx with Groq API KEY:
+```bash
+export OPENAI_API_KEY=xxxxxxxxxxx
+export OPENAI_BASE_URL=https://api.groq.com/openai/v1
+```
+
+## Logging
+```bash
+export LOGLEVEL=info
+```
+
+Advanced logging:
+```bash
+export LOGLEVEL=debug
+```
 
 <div align="center">
   <picture>
@@ -130,18 +252,7 @@ When installing with `pip install "praisonai[autogen]"`, you get:
 - Multi-agent conversation capabilities
 - Code execution environment
 
-## Key Features
 
-- 🤖 Automated AI Agents Creation
-- 🔄 Use CrewAI or AutoGen Framework
-- 💯 100+ LLM Support
-- 💻 Chat with ENTIRE Codebase
-- 🖥️ Interactive UIs
-- 📄 YAML-based Configuration
-- 🛠️ Custom Tool Integration
-- 🔍 Internet Search Capability (using Crawl4AI and Tavily)
-- 👁️ Vision Language Model (VLM) Support
-- 🎙️ Real-time Voice Interaction
 
 ## TL;DR Multi Agents
 

{praisonai-2.0.12 → praisonai-2.0.14}/praisonai/agents_generator.py

@@ -200,6 +200,57 @@ class AgentsGenerator:
                     tools_dict[name] = obj
         return tools_dict
 
+    def load_tools_from_tools_py(self):
+        """
+        Automatically loads all tools (functions and tool definitions) from tools.py file.
+
+        Returns:
+            dict: A dictionary containing:
+                - Function names as keys and function objects as values
+                - Tool definition names as keys and tool definition dictionaries as values
+
+        Note:
+            This function looks for:
+            1. Regular functions
+            2. Tool definition dictionaries (containing 'type' and 'function' keys)
+            3. Variables named as tools or ending with '_tool'
+        """
+        tools_dict = {}
+        try:
+            # Try to import tools.py from current directory
+            spec = importlib.util.spec_from_file_location("tools", "tools.py")
+            if spec is None:
+                self.logger.warning("tools.py not found in current directory")
+                return tools_dict
+
+            module = importlib.util.module_from_spec(spec)
+            spec.loader.exec_module(module)
+
+            # Get all module attributes
+            for name, obj in inspect.getmembers(module):
+                # Skip private attributes
+                if name.startswith('_'):
+                    continue
+                    
+                # Case 1: Regular functions
+                if inspect.isfunction(obj) and obj.__module__ == "tools":
+                    tools_dict[name] = obj
+                    
+                # Case 2: Tool definition dictionaries
+                elif isinstance(obj, dict) and obj.get('type') == 'function' and 'function' in obj:
+                    tools_dict[name] = obj
+                    
+                # Case 3: Variables named as tools
+                elif (name.endswith('_tool') or name == 'tools') and not inspect.ismodule(obj):
+                    tools_dict[name] = obj
+
+            self.logger.debug(f"Loaded {len(tools_dict)} tools from tools.py")
+            
+        except Exception as e:
+            self.logger.warning(f"Error loading tools from tools.py: {e}")
+            
+        return tools_dict
+
     def generate_crew_and_kickoff(self):
         """
         Generates a crew of agents and initiates tasks based on the provided configuration.
@@ -271,7 +322,7 @@ class AgentsGenerator:
         elif tools_dir_path.is_dir():
             tools_dict.update(self.load_tools_from_module_class(tools_dir_path))
             self.logger.debug("tools folder exists in the root directory")
-        
+
         framework = self.framework or config.get('framework')
 
         if framework == "autogen":
@@ -498,6 +549,8 @@ class AgentsGenerator:
         tasks = []
         tasks_dict = {}
 
+        tools_dict = self.load_tools_from_tools_py()
+
         # Create agents from config
         for role, details in config['roles'].items():
             role_filled = details['role'].format(topic=topic)

{praisonai-2.0.12 → praisonai-2.0.14}/praisonai/deploy.py

@@ -56,7 +56,7 @@ class CloudDeployer:
             file.write("FROM python:3.11-slim\n")
             file.write("WORKDIR /app\n")
             file.write("COPY . .\n")
-            file.write("RUN pip install flask praisonai==2.0.10 gunicorn markdown\n")
+            file.write("RUN pip install flask praisonai==2.0.14 gunicorn markdown\n")
             file.write("EXPOSE 8080\n")
             file.write('CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]\n')
             

{praisonai-2.0.12 → praisonai-2.0.14}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "PraisonAI"
-version = "2.0.12"
+version = "2.0.14"
 description = "PraisonAI application combines AutoGen and CrewAI or similar frameworks into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customization, and efficient human-agent collaboration."
 readme = "README.md"
 license = ""
@@ -12,7 +12,7 @@ dependencies = [
     "rich>=13.7",
     "markdown>=3.5",
     "pyparsing>=3.0.0",
-    "praisonaiagents>=0.0.4",
+    "praisonaiagents>=0.0.6",
     "python-dotenv>=0.19.0",
     "instructor>=1.3.3",
     "PyYAML>=6.0",
@@ -78,7 +78,7 @@ autogen = ["pyautogen>=0.2.19", "praisonai-tools>=0.0.7", "crewai"]
 
 [tool.poetry]
 name = "PraisonAI"
-version = "2.0.12"
+version = "2.0.14"
 description = "PraisonAI application combines AutoGen and CrewAI or similar frameworks into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customization, and efficient human-agent collaboration."
 authors = ["Mervin Praison"]
 license = ""
@@ -96,7 +96,7 @@ python = ">=3.10,<3.13"
 rich = ">=13.7"
 markdown = ">=3.5"
 pyparsing = ">=3.0.0"
-praisonaiagents = ">=0.0.4"
+praisonaiagents = ">=0.0.6"
 python-dotenv = ">=0.19.0"
 instructor = ">=1.3.3"
 PyYAML = ">=6.0"