Merge pull request #355 from MervinPraison/develop

Add Image Generation AI Agents with Async Support

docker/Dockerfile

@@ -1,6 +1,6 @@
 FROM python:3.11-slim
 WORKDIR /app
 COPY . .
-RUN pip install flask praisonai==2.0.60 gunicorn markdown
+RUN pip install flask praisonai==2.0.61 gunicorn markdown
 EXPOSE 8080
 CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]

docs/api/praisonai/deploy.html

@@ -110,7 +110,7 @@ <h2 id="raises">Raises</h2>
             file.write(&#34;FROM python:3.11-slim\n&#34;)
             file.write(&#34;WORKDIR /app\n&#34;)
             file.write(&#34;COPY . .\n&#34;)
-            file.write(&#34;RUN pip install flask praisonai==2.0.60 gunicorn markdown\n&#34;)
+            file.write(&#34;RUN pip install flask praisonai==2.0.61 gunicorn markdown\n&#34;)
             file.write(&#34;EXPOSE 8080\n&#34;)
             file.write(&#39;CMD [&#34;gunicorn&#34;, &#34;-b&#34;, &#34;0.0.0.0:8080&#34;, &#34;api:app&#34;]\n&#39;)
 

docs/features/image-generation.mdx

@@ -0,0 +1,126 @@
+---
+title: "Image Generation AI Agents"
+sidebarTitle: "Image Generation"
+description: "Generate high-quality images using PraisonAI Image Agents with both synchronous and asynchronous capabilities."
+icon: "image"
+---
+
+```mermaid
+flowchart LR
+    In[Start] --> Process[Image Description]
+    Process --> Agent[Image Agent]
+    Agent --> Out[Image URL]
+    
+    style In fill:#8B0000,color:#fff
+    style Process fill:#2E8B57,color:#fff
+    style Agent fill:#2E8B57,color:#fff
+    style Out fill:#8B0000,color:#fff
+```
+
+Image Generation in PraisonAI allows you to create high-quality images using natural language descriptions. The Image Agent supports both synchronous and asynchronous operations, making it flexible for various use cases.
+
+## Quick Start
+
+<Tabs>
+  <Tab title="Code">
+    <Steps>
+      <Step title="Install Package">
+        First, install the PraisonAI Agents package with LLM support:
+        ```bash
+        pip install "praisonaiagents[llm]"
+        ```
+      </Step>
+
+      <Step title="Set API Key">
+        Set your OpenAI API key as an environment variable:
+        ```bash
+        export OPENAI_API_KEY=your_api_key_here
+        ```
+      </Step>
+
+      <Step title="Create Agent">
+        Create a new file `image_gen.py` with the basic setup:
+        ```python
+        from praisonaiagents.agent.image_agent import ImageAgent
+
+        # Create an image agent
+        agent = ImageAgent(
+            llm="dall-e-3",
+            verbose=True
+        )
+
+        # Generate an image
+        result = agent.chat("A cute baby sea otter playing with a laptop")
+        print("Image generation result:", result)
+        ```
+      </Step>
+    </Steps>
+  </Tab>
+
+  <Tab title="Async">
+    <Steps>
+      <Step title="Install Package">
+        First, install the PraisonAI Agents package with LLM support:
+        ```bash
+        pip install "praisonaiagents[llm]"
+        ```
+      </Step>
+
+      <Step title="Set API Key">
+        Set your OpenAI API key as an environment variable:
+        ```bash
+        export OPENAI_API_KEY=your_api_key_here
+        ```
+      </Step>
+
+      <Step title="Create Async Agent">
+        Create a new file `image_gen_async.py` with the async setup:
+        ```python
+        import asyncio
+        from praisonaiagents import ImageAgent
+
+        async def main():
+            agent = ImageAgent(
+                name="ImageCreator",
+                llm="dall-e-3",
+                style="natural"
+            )
+
+            result = await agent.achat("A cute baby sea otter playing with a laptop")
+            print(f"Image generation result: {result}")
+
+        if __name__ == "__main__":
+            asyncio.run(main())
+        ```
+      </Step>
+    </Steps>
+  </Tab>
+</Tabs>
+
+## Features
+
+<CardGroup cols={2}>
+  <Card title="DALL-E Integration" icon="image">
+    Seamless integration with DALL-E for high-quality image generation.
+  </Card>
+  <Card title="Async Support" icon="bolt">
+    Asynchronous operations for better performance in concurrent environments.
+  </Card>
+  <Card title="Natural Style" icon="paintbrush">
+    Generate images with natural, realistic styling options.
+  </Card>
+  <Card title="Verbose Mode" icon="message">
+    Detailed output logging for better debugging and monitoring.
+  </Card>
+</CardGroup>
+
+## Next Steps
+
+<CardGroup>
+  <Card title="Agents Overview" icon="robot" href="/agents">
+    Learn more about PraisonAI Agents and their capabilities
+  </Card>
+  <Card title="API Reference" icon="code" href="/api-reference">
+    View the complete API documentation
+  </Card>
+</CardGroup>

docs/mint.json

@@ -120,6 +120,7 @@
       "group": "Features",
       "pages": [
         "features/autoagents",
+        "features/image-generation",
         "features/selfreflection",
         "features/rag",
         "features/reasoning-extract",

examples/image/image-agent-async.py

@@ -0,0 +1,15 @@
+import asyncio
+from praisonaiagents import ImageAgent
+
+async def main():
+    agent = ImageAgent(
+        name="ImageCreator",
+        llm="dall-e-3",
+        style="natural"
+    )
+
+    result = await agent.achat("A cute baby sea otter playing with a laptop")
+    print(f"Image generation result: {result}")
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/image/image-agent.py

@@ -0,0 +1,8 @@
+from praisonaiagents.agent.image_agent import ImageAgent
+
+# Create an image agent with normal mode
+agent = ImageAgent(llm="dall-e-3")
+
+# Generate an image
+result = agent.chat("A cute baby sea otter playing with a laptop")
+print("Image generation result:", result)

praisonai.rb

@@ -3,7 +3,7 @@ class Praisonai < Formula
 
     desc "AI tools for various AI applications"
     homepage "https://github.com/MervinPraison/PraisonAI"
-    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/2.0.60.tar.gz"
+    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/2.0.61.tar.gz"
     sha256 "1828fb9227d10f991522c3f24f061943a254b667196b40b1a3e4a54a8d30ce32"  # Replace with actual SHA256 checksum
     license "MIT"
 

praisonai/deploy.py

@@ -56,7 +56,7 @@ def create_dockerfile(self):
             file.write("FROM python:3.11-slim\n")
             file.write("WORKDIR /app\n")
             file.write("COPY . .\n")
-            file.write("RUN pip install flask praisonai==2.0.60 gunicorn markdown\n")
+            file.write("RUN pip install flask praisonai==2.0.61 gunicorn markdown\n")
             file.write("EXPOSE 8080\n")
             file.write('CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]\n')
 

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "PraisonAI"
-version = "2.0.60"
+version = "2.0.61"
 description = "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."
 readme = "README.md"
 license = ""
@@ -12,7 +12,7 @@ dependencies = [
     "rich>=13.7",
     "markdown>=3.5",
     "pyparsing>=3.0.0",
-    "praisonaiagents>=0.0.60",
+    "praisonaiagents>=0.0.61",
     "python-dotenv>=0.19.0",
     "instructor>=1.3.3",
     "PyYAML>=6.0",
@@ -84,7 +84,7 @@ autogen = ["pyautogen>=0.2.19", "praisonai-tools>=0.0.7", "crewai"]
 
 [tool.poetry]
 name = "PraisonAI"
-version = "2.0.60"
+version = "2.0.61"
 description = "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."
 authors = ["Mervin Praison"]
 license = ""
@@ -102,7 +102,7 @@ python = ">=3.10,<3.13"
 rich = ">=13.7"
 markdown = ">=3.5"
 pyparsing = ">=3.0.0"
-praisonaiagents = ">=0.0.60"
+praisonaiagents = ">=0.0.61"
 python-dotenv = ">=0.19.0"
 instructor = ">=1.3.3"
 PyYAML = ">=6.0"

src/praisonai-agents/image-agent-async.py

@@ -0,0 +1,15 @@
+import asyncio
+from praisonaiagents import ImageAgent
+
+async def main():
+    agent = ImageAgent(
+        name="ImageCreator",
+        llm="dall-e-3",
+        style="natural"
+    )
+
+    result = await agent.achat("A cute baby sea otter playing with a laptop")
+    print(f"Image generation result: {result}")
+
+if __name__ == "__main__":
+    asyncio.run(main())

src/praisonai-agents/image-agent.py

@@ -1,47 +1,8 @@
-from praisonaiagents import Agent, Tools
-from praisonaiagents.tools import duckduckgo
+from praisonaiagents.agent.image_agent import ImageAgent
 
-agent = Agent(instructions="You are a Image Analysis Agent", tools=[duckduckgo])
-agent.start("I want to go London next week, find me a good hotel and flight")
+# Create an image agent with normal mode
+agent = ImageAgent(llm="dall-e-3")
 
-from praisonaiagents import Agent, Task, PraisonAIAgents
-
-# Create Image Analysis Agent
-image_agent = Agent(
-    name="ImageAnalyst",
-    role="Image Analysis Specialist",
-    goal="Analyze images and videos to extract meaningful information",
-    backstory="""You are an expert in computer vision and image analysis.
-    You excel at describing images, detecting objects, and understanding visual content.""",
-    llm="gpt-4o-mini",
-    self_reflect=False
-)
-
-# 1. Task with Image URL
-task1 = Task(
-    name="analyze_landmark",
-    description="Describe this famous landmark and its architectural features.",
-    expected_output="Detailed description of the landmark's architecture and significance",
-    agent=image_agent,
-    images=["https://upload.wikimedia.org/wikipedia/commons/b/bf/Krakow_-_Kosciol_Mariacki.jpg"]
-)
-
-# 2. Task with Local Image File
-task2 = Task(
-    name="analyze_local_image",
-    description="What objects can you see in this image? Describe their arrangement.",
-    expected_output="Detailed description of objects and their spatial relationships",
-    agent=image_agent,
-    images=["image.jpg"] 
-)
-
-# Create PraisonAIAgents instance
-agents = PraisonAIAgents(
-    agents=[image_agent],
-    tasks=[task1, task2],
-    process="sequential",
-    verbose=1
-)
-
-# Run all tasks
-agents.start()
+# Generate an image
+result = agent.chat("A cute baby sea otter playing with a laptop")
+print("Image generation result:", result)

src/praisonai-agents/image-understanding-agent.py

@@ -0,0 +1,47 @@
+from praisonaiagents import Agent, Tools
+from praisonaiagents.tools import duckduckgo
+
+agent = Agent(instructions="You are a Image Analysis Agent", tools=[duckduckgo])
+agent.start("I want to go London next week, find me a good hotel and flight")
+
+from praisonaiagents import Agent, Task, PraisonAIAgents
+
+# Create Image Analysis Agent
+image_agent = Agent(
+    name="ImageAnalyst",
+    role="Image Analysis Specialist",
+    goal="Analyze images and videos to extract meaningful information",
+    backstory="""You are an expert in computer vision and image analysis.
+    You excel at describing images, detecting objects, and understanding visual content.""",
+    llm="gpt-4o-mini",
+    self_reflect=False
+)
+
+# 1. Task with Image URL
+task1 = Task(
+    name="analyze_landmark",
+    description="Describe this famous landmark and its architectural features.",
+    expected_output="Detailed description of the landmark's architecture and significance",
+    agent=image_agent,
+    images=["https://upload.wikimedia.org/wikipedia/commons/b/bf/Krakow_-_Kosciol_Mariacki.jpg"]
+)
+
+# 2. Task with Local Image File
+task2 = Task(
+    name="analyze_local_image",
+    description="What objects can you see in this image? Describe their arrangement.",
+    expected_output="Detailed description of objects and their spatial relationships",
+    agent=image_agent,
+    images=["image.jpg"] 
+)
+
+# Create PraisonAIAgents instance
+agents = PraisonAIAgents(
+    agents=[image_agent],
+    tasks=[task1, task2],
+    process="sequential",
+    verbose=1
+)
+
+# Run all tasks
+agents.start()

src/praisonai-agents/praisonaiagents/__init__.py

@@ -3,6 +3,7 @@
 """
 
 from .agent.agent import Agent
+from .agent.image_agent import ImageAgent
 from .agents.agents import PraisonAIAgents
 from .task.task import Task
 from .tools.tools import Tools
@@ -30,6 +31,7 @@
 
 __all__ = [
     'Agent',
+    'ImageAgent',
     'PraisonAIAgents',
     'Agents',
     'Tools',

src/praisonai-agents/praisonaiagents/agent/__init__.py

@@ -1,4 +1,5 @@
 """Agent module for AI agents"""
 from .agent import Agent
+from .image_agent import ImageAgent
 
-__all__ = ['Agent'] 
+__all__ = ['Agent', 'ImageAgent']

src/praisonai-agents/praisonaiagents/agent/agent.py

@@ -16,7 +16,6 @@
     display_self_reflection,
     ReflectionOutput,
     client,
-    error_logs,
     adisplay_instruction
 )
 import inspect