Replaced hardcoded date values with environment variables for flexibility and added a new filter for newspapers. Enhanced response parsing by including facets for related persons and organizations.
Introduced performance tracking in the smd_detail_article function by adding execution time logging. This helps in monitoring and optimizing the function’s runtime during API requests and processing.
Replace raw response text retrieval with JSON parsing to extract specific content. This ensures more precise data handling and aligns with expected response structure.
The "Bearer" prefix was mistakenly included in the API key header. This change removes it to align with the expected format required by the external service.
Replaced curly brackets with direct reference to the environment variable in the payload model value. This ensures the correct model is passed dynamically from environment configurations.
Modified the response handling to return raw text instead of JSON in one case and updated another to include summarized content with article ID. These changes ensure consistency and enhance the response structure for better client integration.
Replaced the summarized content processing with direct data return. This improves efficiency by skipping the summarization step and ensures the full response data is available to the caller for further use.
Updated the `summarize_to_words` function to take `text` and `title` as separate parameters instead of a single `article` dictionary. Adjusted payload and function calls accordingly for better clarity and flexibility.
Introduced a new `summarize_to_words` function to summarize articles using an external API. Integrated it into `smd_detail_article` to return summarized article content instead of the full text. Updated header key capitalization for consistency.
Clarified that the SMD search query should be written in German and enriched with relevant contextual keywords. This ensures better alignment with language requirements and improves search accuracy.
Replaced the hardcoded page size with a value fetched from the `SWISSDOX_PAGESIZE` environment variable, defaulting to 10 if not set. This allows greater flexibility and configurability for pagination settings.
Updated the SMD server client to use POST instead of GET for sending requests. This change ensures the payload is sent as JSON in compliance with the server's expected input format.
Replaced synchronous requests with aiohttp to enable non-blocking, async HTTP requests. Updated `smd_detail_article` and `smd_research` to utilize asyncio for parallel execution, significantly improving efficiency for handling multiple API calls. Added aiohttp and asyncio dependencies to requirements.txt.
Removed the unused `smd_detail_article` decorator and expanded the response structure to include detailed article data in nested JSON. Adjusted the pagination default `pageSize` from 10 to 25 to handle larger datasets effectively.
Revised the API endpoint URL from smd.ch to swissdox.ch for accuracy and updated the function docstring to clarify the purpose of the article_id parameter. These changes improve clarity and ensure API requests are routed correctly.
Clarify the usage instructions and context for the smd_detail_article function. This ensures better understanding of its relationship with the smd_research tool.
The `onlyResults` parameter was changed from `True` to `False` in the API request configuration. This ensures more comprehensive data retrieval by including additional metadata in the API response.
Remove unnecessary SMD utilities and shift query creation logic directly into `smd_research` for simplicity. This eliminates duplicate functionality and reduces reliance on external utility files, consolidating responsibilities within server implementation.
Added the `timeout_keep_alive` parameter to FastMCP initialization in both GPT Researcher and SMD Researcher servers. This ensures connections remain active for longer, improving server reliability for long-lived client interactions.
The `host` and `port` parameters were added to FastMCP initialization for both GPT Researcher and SMD servers. This ensures the servers are accessible on all network interfaces at port 8000.
Implemented the SMD MCP Server with functionality for AI-driven research and article retrieval via the MCP protocol. Added utilities for prompt creation and enhanced dependency configuration. This serves as a foundation for handling SMD-related queries and data processing.
