Add Langchain external search tool examples for PraisonAI agents #407
Conversation
MervinPraison
commented
Mar 10, 2025
MervinPraison
commented
- Introduced example scripts for Brave Search, Google Trends, and SerpAPI
- Demonstrated multi-agent workflows using external search tools
- Added API key configuration instructions for each search tool
- Included examples of research and content generation agents using search capabilities
- Introduced example scripts for Brave Search, Google Trends, and SerpAPI - Demonstrated multi-agent workflows using external search tools - Added API key configuration instructions for each search tool - Included examples of research and content generation agents using search capabilities
![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 introduces example scripts for integrating PraisonAI agents with external search tools from Langchain. It demonstrates how to use Brave Search, Google Trends, and SerpAPI within multi-agent workflows. The examples include instructions for configuring API keys and showcase research and content generation agents leveraging search capabilities.
Highlights
- New Examples: Added example scripts for Brave Search, Google Trends, and SerpAPI integrations with PraisonAI agents.
- Multi-Agent Workflows: Demonstrated multi-agent workflows utilizing external search tools for research and content generation.
- API Key Configuration: Included instructions for configuring API keys for each search tool to enable the examples.
Changelog
Click here to see the changelog
- examples/tools/langchain/brave-search.py
- Created a new script demonstrating Brave Search integration.
- Implemented a
search_bravefunction to query Brave Search with a specified API key. - Configured a data agent to search for AI job trends and an editor agent to write a blog article.
- Lines 1-3: Added installation and environment variable setup instructions.
- Lines 5-7: Imported necessary modules from
praisonaiagentsandlangchain_community. - Lines 9-13: Defined the
search_bravefunction to perform the search. - Lines 15-18: Created data and editor agents and started the PraisonAIAgents workflow.
- examples/tools/langchain/google-trends.py
- Created a new script demonstrating Google Trends integration.
- Utilized
GoogleTrendsAPIWrapperfromlangchain_communityto research trending AI topics. - Configured a research agent to find trending topics and a summarise agent to summarise the findings.
- Lines 1-3: Added installation and environment variable setup instructions.
- Lines 5-6: Imported necessary modules from
langchain_communityandpraisonaiagents. - Lines 8-11: Created a research agent with instructions to research trending AI topics.
- Lines 13-15: Created a summarise agent with instructions to summarise the research findings.
- Lines 17-18: Started the PraisonAIAgents workflow with the research and summarise agents.
- examples/tools/langchain/serp-api.py
- Created a new script demonstrating SerpAPI integration.
- Utilized
SerpAPIWrapperfromlangchain_communityto search for AI job trends. - Configured a data agent to search for AI job trends and an editor agent to write a blog article.
- Lines 1-3: Added installation and environment variable setup instructions.
- Lines 5-6: Imported necessary modules from
praisonaiagentsandlangchain_community. - Lines 8-9: Created data and editor agents.
- Lines 11-12: Started the PraisonAIAgents workflow with the data and editor agents.
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.
Did you know?
The term 'API' was first used in the context of computing in the 1960s, long before the internet became widespread.
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
This pull request introduces example scripts for integrating Langchain external search tools (Brave Search, Google Trends, and SerpAPI) with PraisonAI agents. The examples demonstrate multi-agent workflows using these tools and provide instructions for API key configuration. Overall, this is a valuable addition to the project, providing users with practical examples of how to leverage external search capabilities within PraisonAI agents.
Summary of Findings
- Missing Error Handling: The
search_bravefunction inbrave-search.pylacks error handling for theos.environ['BRAVE_SEARCH_API']call. If the environment variable is not set, the program will crash. This should be addressed to improve the robustness of the example. - Inconsistent Tool Usage: In
google-trends.py,GoogleTrendsAPIWrapperis passed directly as a tool, while inbrave-search.pyandserp-api.py, a function wrapping the tool is used. This inconsistency should be addressed for clarity and maintainability. - Missing API Key Instructions: The
google-trends.pyexample is missing instructions on how to obtain theSERPAPI_API_KEY, which is necessary for the script to function correctly. This should be added to ensure users can easily run the example.
Merge Readiness
The pull request introduces valuable examples for integrating Langchain external search tools with PraisonAI agents. However, there are a few issues that need to be addressed before merging. Specifically, the missing error handling in brave-search.py and the inconsistent tool usage across the examples should be fixed. Additionally, the missing API key instructions in google-trends.py should be added. I am unable to approve this pull request, and recommend that it not be merged until these issues are addressed (at a minimum), and that others review and approve this code before merging.
| api_key = os.environ['BRAVE_SEARCH_API'] | ||
| tool = BraveSearch.from_api_key(api_key=api_key, search_kwargs={"count": 3}) | ||
| return tool.run(query) |
There was a problem hiding this comment.
Consider adding error handling to check if the BRAVE_SEARCH_API environment variable is set. If it's not set, the program will crash. You can use os.getenv with a default value or raise an exception with a helpful message.
| api_key = os.environ['BRAVE_SEARCH_API'] | |
| tool = BraveSearch.from_api_key(api_key=api_key, search_kwargs={"count": 3}) | |
| return tool.run(query) | |
| api_key = os.getenv('BRAVE_SEARCH_API') | |
| if not api_key: | |
| raise ValueError("BRAVE_SEARCH_API environment variable not set.") | |
| tool = BraveSearch.from_api_key(api_key=api_key, search_kwargs={"count": 3}) |
| # pip install langchain-community google-search-results | ||
| # export SERPAPI_API_KEY=your_api_key_here | ||
| # export OPENAI_API_KEY=your_api_key_here |
There was a problem hiding this comment.
It's good to include the installation and environment variable setup instructions, but it's missing instructions on how to obtain the SERPAPI_API_KEY.
| # pip install langchain-community google-search-results | |
| # export SERPAPI_API_KEY=your_api_key_here | |
| # export OPENAI_API_KEY=your_api_key_here | |
| # pip install langchain-community google-search-results | |
| # export SERPAPI_API_KEY=your_api_key_here # Get your API key from https://serpapi.com/ | |
| # export OPENAI_API_KEY=your_api_key_here |
| research_agent = Agent( | ||
| instructions="Research trending topics related to AI", | ||
| tools=[GoogleTrendsAPIWrapper] |
There was a problem hiding this comment.
For consistency with the other examples (brave-search.py and serp-api.py), consider wrapping GoogleTrendsAPIWrapper in a function.
| research_agent = Agent( | |
| instructions="Research trending topics related to AI", | |
| tools=[GoogleTrendsAPIWrapper] | |
| def google_trends_search(query: str): | |
| """Searches Google Trends and returns results.""" | |
| tool = GoogleTrendsAPIWrapper() | |
| return tool.run(query) | |
| research_agent = Agent( | |
| instructions="Research trending topics related to AI", | |
| tools=[google_trends_search] | |
| ) |
✅ Deploy Preview for praisonai canceled.
|
