Conversation
… blocking parameters, update version to 0.0.79 in `pyproject.toml` and `uv.lock`, and enhance server startup logic in `agent.py` with healthcheck endpoint and improved thread management.
✅ Deploy Preview for praisonai ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
|
Caution Review failedThe pull request is closed. WalkthroughThis update introduces new deployment documentation for AWS and Google Cloud, reorganizes documentation navigation, and adds example scripts for multi-agent and simple API deployments. The version of the Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant Script
participant Agent
participant FastAPI Server
User->>Script: Runs agent script
Script->>Agent: agent.launch(path, port, host, debug)
Agent->>FastAPI Server: Register endpoint (if not already running)
FastAPI Server-->>Agent: Confirms registration
Agent->>Script: If last launch in script, block main thread
User->>FastAPI Server: Sends request to /agent-endpoint
FastAPI Server->>Agent: Forwards request
Agent->>FastAPI Server: Returns response
FastAPI Server->>User: Sends agent response
Possibly related PRs
Suggested labels
Poem
Tip ⚡️ Faster reviews with caching
Enjoy the performance boost—your workflow just got faster. 📜 Recent review detailsConfiguration used: CodeRabbit UI ⛔ Files ignored due to path filters (2)
📒 Files selected for processing (20)
✨ Finishing Touches
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Hello @MervinPraison, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!
Summary of Changes
This pull request updates the version of the PraisonAI package to 2.1.4. This involves changes to the docker/Dockerfile files, docs/api/praisonai/deploy.html, docs/developers/local-development.mdx, docs/ui/chat.mdx, docs/ui/code.mdx, praisonai/deploy.py, and pyproject.toml to reflect the new version. Additionally, it introduces new documentation files for deploying to AWS and Google Cloud, and provides examples for multi-agent APIs. The changes also include updates to dependencies and minor modifications to the agent's launch function.
Highlights
- Version Update: The core change is updating the
PraisonAIpackage version to2.1.4across all relevant files. - Deployment Documentation: New documentation files (
docs/deploy/aws.mdx,docs/deploy/deploy.mdx,docs/deploy/googlecloud.mdx) have been added to guide users on deploying PraisonAI agents to AWS and Google Cloud. - API Examples: New examples (
examples/api/multi-agent-api.py,examples/api/simple-api-mcp.py,examples/api/simple-api.py) are added to demonstrate how to create multi-agent APIs. - Agent Launch Function: The
launchfunction insrc/praisonai-agents/praisonaiagents/agent/agent.pyhas been modified to remove theautostartandblockingparameters, and to improve the server startup and endpoint registration process.
Changelog
Click here to see the changelog
- docker/Dockerfile
- Updated
praisonaiversion from2.1.1to2.1.4in theDockerfile.
- Updated
- docker/Dockerfile.chat
- Updated
praisonaiversion from2.0.18to2.1.4in theDockerfile.chat.
- Updated
- docker/Dockerfile.dev
- Updated
praisonaiversion from2.0.18to2.1.4in theDockerfile.dev.
- Updated
- docker/Dockerfile.ui
- Updated
praisonaiversion from2.0.18to2.1.4in theDockerfile.ui.
- Updated
- docs/api/praisonai/deploy.html
- Updated
praisonaiversion from2.1.1to2.1.4in the documentation.
- Updated
- docs/deploy/aws.mdx
- Added new documentation file for deploying to AWS, including instructions for EC2, ECS/Fargate, and Lambda deployments.
- docs/deploy/deploy.mdx
- Added new documentation file for deploying PraisonAI agents as APIs, including quick start, multi-agent deployment, and production deployment options.
- docs/deploy/googlecloud.mdx
- Added new documentation file for deploying to Google Cloud using Cloud Run, including scaling, continuous deployment, and security best practices.
- docs/developers/local-development.mdx
- Updated
praisonaiversion from2.0.18to2.1.4in the local development documentation.
- Updated
- docs/mint.json
- Reordered tabs and added a Deploy group with links to deployment documentation pages.
- docs/ui/chat.mdx
- Updated
praisonaiversion from2.0.18to2.1.4in the chat UI documentation.
- Updated
- docs/ui/code.mdx
- Updated
praisonaiversion from2.0.18to2.1.4in the code UI documentation.
- Updated
- examples/api/multi-agent-api.py
- Added new example file demonstrating how to create a multi-agent API with weather, stock, and travel agents.
- examples/api/simple-api-mcp.py
- Added new example file demonstrating a simple API with MCP (Multi-Channel Platform) integration.
- examples/api/simple-api.py
- Added new example file demonstrating a simple API with a helpful assistant agent.
- praisonai/deploy.py
- Updated
praisonaiversion from2.1.1to2.1.4in thecreate_dockerfilefunction.
- Updated
- pyproject.toml
- Updated
praisonaiversion from2.1.1to2.1.4. - Updated
praisonaiagentsversion from0.0.71to0.0.79. - Updated
chainlitversion from2.0.3to2.5.5. - Updated
langchain-google-genaiversion from1.0.4to2.1.0. - Updated
langchain-openaiversion from0.1.7to>=0.2.1,<0.3.0. - Updated
langchain-anthropicversion from0.1.13to0.3.0. - Updated
langchain-cohereversion from0.1.4to>=0.3.0,<0.4.0. - Updated
crawl4aiversion from0.3.4to>=0.6.0. - Added
fastapianduvicornas dependencies for theapiextra.
- Updated
- src/praisonai-agents/multi-agent-api.py
- Removed
blockingparameter fromlaunchcalls. - Removed comments related to blocking execution.
- Removed
- src/praisonai-agents/praisonaiagents/agent/agent.py
- Removed
autostartandblockingparameters from thelaunchfunction. - Added healthcheck endpoint to the FastAPI app.
- Improved server startup and endpoint registration process using threading and stack inspection to determine if the server should block.
- Added more logging and error handling for server startup.
- Removed
- src/praisonai-agents/pyproject.toml
- Updated
praisonaiagentsversion from0.0.78to0.0.79.
- Updated
- src/praisonai-agents/uv.lock
- Updated
praisonaiagentsversion from0.0.78to0.0.79.
- Updated
Using Gemini Code Assist
The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.
Invoking Gemini
You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.
| Feature | Command | Description |
|---|---|---|
| Code Review | /gemini review |
Performs a code review for the current pull request in its current state. |
| Pull Request Summary | /gemini summary |
Provides a summary of the current pull request in its current state. |
| Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in issue comments and review comments. |
| Help | /gemini help |
Displays a list of available commands. |
Customization
To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.
Limitations & Feedback
Gemini Code Assist is currently in preview and may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments to provide feedback.
You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.
A version ascends,
New docs guide cloud journeys,
Agents find their place.
Footnotes
-
Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩
There was a problem hiding this comment.
Code Review
The pull request updates the praisonai version across multiple Dockerfiles and documentation files. It also introduces new documentation for deploying PraisonAI agents to AWS and Google Cloud, and deploying PraisonAI agents as APIs. The changes seem straightforward and necessary for keeping the project up-to-date and providing deployment guidance. However, there are a few areas that could be improved, particularly in the new documentation files.
Summary of Findings
- Dependency Updates: The pull request updates the
praisonaiversion in multiple files. It's crucial to ensure that these updates are thoroughly tested and compatible with the rest of the project's dependencies. - API Launch Parameters: The removal of
autostartandblockingparameters from thelaunchmethod could affect existing users. Providing a clear migration path and documentation is essential. - Agent Launch Detection: The automatic detection of the last
launchcall might not be reliable in all scenarios. A more explicit control mechanism for blocking the main thread could improve the code's robustness.
Merge Readiness
The pull request introduces necessary updates and valuable deployment documentation. However, the potential impact of removing the autostart and blocking parameters, and the reliability of the agent launch detection, should be carefully considered. At a minimum, the high severity issues should be addressed before merging. I am unable to directly approve this pull request, and I recommend that other reviewers also examine the code before merging.
| COPY . . | ||
|
|
||
| RUN pip install flask praisonai==2.0.18 watchdog | ||
| RUN pip install flask praisonai==2.1.4 watchdog |
There was a problem hiding this comment.
This line updates the praisonai version in the documentation. Ensure that this version is thoroughly tested and compatible with the rest of the dependencies. It would be useful to add a comment indicating why this update is being made.
RUN pip install flask praisonai==2.1.4 watchdog # Updated to version 2.1.4 for [reason]
| COPY . . | ||
|
|
||
| RUN pip install flask praisonai==2.0.18 watchdog | ||
| RUN pip install flask praisonai==2.1.4 watchdog |
There was a problem hiding this comment.
This line updates the praisonai version in the documentation. Ensure that this version is thoroughly tested and compatible with the rest of the dependencies. It would be useful to add a comment indicating why this update is being made.
RUN pip install flask praisonai==2.1.4 watchdog # Updated to version 2.1.4 for [reason]
| COPY . . | ||
|
|
||
| RUN pip install flask praisonai==2.0.18 watchdog | ||
| RUN pip install flask praisonai==2.1.4 watchdog |
There was a problem hiding this comment.
This line updates the praisonai version in the documentation. Ensure that this version is thoroughly tested and compatible with the rest of the dependencies. It would be useful to add a comment indicating why this update is being made.
RUN pip install flask praisonai==2.1.4 watchdog # Updated to version 2.1.4 for [reason]
| def launch(self, path: str = '/', port: int = 8000, host: str = '0.0.0.0', debug: bool = False): | ||
| """ | ||
| Launch the agent as an HTTP API endpoint. | ||
|
|
||
| Args: | ||
| path: API endpoint path (default: '/') | ||
| port: Server port (default: 8000) | ||
| host: Server host (default: '0.0.0.0') | ||
| autostart: Whether to start the server automatically (default: True) | ||
| debug: Enable debug mode for uvicorn (default: False) | ||
| blocking: If True, blocks the main thread to keep the server running (default: True) | ||
|
|
There was a problem hiding this comment.
The autostart and blocking parameters have been removed from the launch method. This could affect existing users who rely on these parameters. Consider adding a note in the documentation about this change and how users can achieve the same behavior without these parameters.
def launch(self, path: str = '/', port: int = 8000, host: str = '0.0.0.0', debug: bool = False):
"""
Launch the agent as an HTTP API endpoint.
Args:
path: API endpoint path (default: '/')
port: Server port (default: 8000)
host: Server host (default: '0.0.0.0')
debug: Enable debug mode for uvicorn (default: False)
Returns:
None
"""| # Get the stack frame to check if this is the last launch() call in the script | ||
| import inspect | ||
| stack = inspect.stack() | ||
|
|
||
| # If this is called from a Python script (not interactive), try to detect if it's the last launch call | ||
| if len(stack) > 1 and stack[1].filename.endswith('.py'): | ||
| caller_frame = stack[1] | ||
| caller_line = caller_frame.lineno | ||
|
|
||
| print(f"✅ FastAPI server started at http://{host}:{port}") | ||
| print(f"📚 API documentation available at http://{host}:{port}/docs") | ||
|
|
||
| # If blocking is True, keep the main thread alive | ||
| if blocking: | ||
| print("\nServer is running in blocking mode. Press Ctrl+C to stop...") | ||
| try: | ||
| # Read the file to check if there are more launch calls after this one | ||
| with open(caller_frame.filename, 'r') as f: | ||
| lines = f.readlines() | ||
|
|
||
| # Check if there are more launch() calls after the current line | ||
| has_more_launches = False | ||
| for line in lines[caller_line:]: | ||
| if '.launch(' in line and not line.strip().startswith('#'): | ||
| has_more_launches = True | ||
| break | ||
|
|
||
| # If this is the last launch call, block the main thread | ||
| if not has_more_launches: | ||
| try: | ||
| print("\nAll agents registered. Press Ctrl+C to stop the server.") | ||
| while True: | ||
| time.sleep(1) | ||
| except KeyboardInterrupt: | ||
| print("\nServer stopped") | ||
| except Exception as e: | ||
| # If something goes wrong with detection, block anyway to be safe | ||
| logging.error(f"Error in launch detection: {e}") | ||
| try: | ||
| while True: | ||
| time.sleep(1) | ||
| except KeyboardInterrupt: | ||
| print("\nServer stopped") | ||
| else: | ||
| # Note for non-blocking mode | ||
| print("\nNote: Server is running in a background thread. To keep it alive, either:") | ||
| print("1. Set blocking=True when calling launch()") | ||
| print("2. Keep your main application running") | ||
| print("3. Use a loop in your code to prevent the program from exiting") | ||
|
|
||
|
|
There was a problem hiding this comment.
This section attempts to detect if the launch call is the last one in a script and blocks the main thread accordingly. While this is a clever approach, it might not be reliable in all cases. Consider providing a more explicit way for users to control whether the server blocks the main thread or not, perhaps through a separate function call or a global setting.
1 participant
Summary by CodeRabbit
New Features
Improvements
Dependency Updates
Bug Fixes