feat: add mcp_playwright_example #128
Closed
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ample Fix NameError in streamlit_mcp_rag_agent example
Add MCP agent server example
…llow API reference (lastmile-ai#117)
…ai#120) * fix/agent-functions * Remove redundant __aenter__ and initialize
- Modified `execute_tool_call` method in OpenAIAugmentedLLM to convert content list to string - Used "\n".join() to concatenate list items into a single string - This addresses issue lastmile-ai#25 where OpenAI API rejects list-type content - Follows OpenAI API specification requiring content to be string or null - Prevents errors with LLMs like deepseek that strictly validate input format The change ensures compatibility with OpenAI's API requirements which specify: "content can only be a string or null. It cannot be a list, object, or any other type." Co-authored-by: ask <ask@m01n.net>
…i#122) * Update mcp_agent.config.yaml * Updating README for new Github MCP Server
… proper message handling (lastmile-ai#130)
…age_param issues (lastmile-ai#131) * fix: update content handling in AzureAugmentedLLM to ensure proper list formatting * fix: update error message to clarify supported roles in AzureAugmentedLLM * fix: update response handling in AzureAugmentedLLM to parse JSON data correctly * fix: simplify JSON argument parsing in AzureAugmentedLLM and improve content handling
* feat: add GoogleAugmentedLLM and GoogleSettings * feat: add example for MCP Google Agent with configuration and usage instructions * feat: update GoogleSettings to allow optional API key and enhance tool schema transformation for compatibility with Gemini * feat: add google-genai dependency * refactor: rename project_id to project in MCP agent config schema * feat: enhance transform_mcp_tool_schema to track unsupported keywords in description and improve any_of handling * feat: demonstrate generate_structured in mcp_basic_google_agent example * fix: correct structured output generation in GoogleAugmentedLLM * chore: update instructor dependency to version 1.7.9 and remove instructor[anthropic] from anthropic's optional dependencies * fix: improve error handling and response processing in GoogleAugmentedLLM * fix: remove redundant error handling for missing function call name or ID in GoogleAugmentedLLM
saqadri
requested changes
Apr 16, 2025
Comment on lines
67
to
73
| result = await llm.generate_str(prompt) | ||
|
|
||
| # Write the result (CSV data) to a file. | ||
| csv_filename = "candidate_summary.csv" | ||
| absolute_path = os.path.abspath(csv_filename) | ||
| with open(csv_filename, "w", newline="") as csv_file: | ||
| csv_file.write(result) |
Collaborator
There was a problem hiding this comment.
why not use the "filesystem" mcp server to let the llm write the result to disk instead of doing this manually?
| async with app.run() as agent_app: | ||
| context = agent_app.context | ||
|
|
||
| async with MCPConnectionManager(context.server_registry): |
Collaborator
There was a problem hiding this comment.
Suggested change
| async with MCPConnectionManager(context.server_registry): |
| ) | ||
|
|
||
| try: | ||
| llm = await linkedin_scraper_agent.attach_llm(OpenAIAugmentedLLM) |
Collaborator
There was a problem hiding this comment.
Hmm, curious if this should be an Orchestrator workflow. Lots of steps. Does it work well?
| @@ -0,0 +1,66 @@ | |||
| # mcp_playwright_Linkedin_example | |||
Collaborator
There was a problem hiding this comment.
Please add a demo video URL to this readme. If you upload the video on GitHub (e.g. into a comment) and copy the url into the readme, it'll automatically render.
… websockets and SSE connections (lastmile-ai#116) * Add support for websockets and an example * Fix readme * Add support for passing HTTP headers to SSE and websocket connections and add an example * Fix tests --------- Co-authored-by: Sarmad Qadri <sarmad@lastmileai.dev>
…ai#143) - Co-authored-by: Roberto Anić Banić <git@roberto.banic.hr> * Add configurable headers to SSE connection * Fix * Update pyproject.toml * Add websocket transport to ServerRegistry * Remove duplicate headers config * lint and format * Update SSE example --------- Co-authored-by: Roberto Anić Banić <git@roberto.banic.hr>
* fx: _reasoning flag used to set api params * fx: add all new oai reasoning models * chore: replace deprecated api field * ch: cleanup startswith * ch: leave commented code as before
Haniehz1
force-pushed
the
add-playwright-linkedin-example
branch
from
0c46232 to
13a7698
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
20 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.