self-hosted-ai

Search the Sovereign AI Blog for articles matching a natural language query, optionally filtered by tag and sorted by relevance or date. Behaviour matrix: - query='', sort=* -> list newest-first, optionally tag-filtered - query!='', sort=relevance -> TF-IDF ranked, optionally tag-filtered - query!='', sort=date_desc -> TF-IDF filtered (score > 0.001), then sorted by date Pure read-only, deterministic for a given KB snapshot.

{
  "type": "object",
  "properties": {
    "query": {
      "default": "",
      "description": "Natural language search query (e.g. 'flashinfer OOM on GB10'). Multi-word queries are tokenized and TF-IDF ranked. Pass empty string to list articles without ranking by relevance.",
      "title": "Query",
      "type": "string"
    },
    "tag": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional tag filter (e.g. 'setup', 'fixes', 'strategy'). Only articles with this tag are considered. Use list_tags to discover available tags.",
      "title": "Tag"
    },
    "sort": {
      "default": "relevance",
      "description": "Result ordering. 'relevance' uses TF-IDF score (default for non-empty query). 'date_desc' sorts newest first (default behaviour when query is empty). When query is empty, 'relevance' is treated as 'date_desc'.",
      "enum": [
        "relevance",
        "date_desc"
      ],
      "title": "Sort",
      "type": "string"
    },
    "n": {
      "default": 5,
      "description": "Maximum number of results to return",
      "maximum": 20,
      "minimum": 1,
      "title": "N",
      "type": "integer"
    }
  },
  "title": "search_blogArguments"
}

{
  "type": "object",
  "properties": {
    "result": {
      "items": {
        "$ref": "#/$defs/SearchResult"
      },
      "title": "Result",
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "$defs": {
    "SearchResult": {
      "description": "One ranked article result from search_blog.",
      "properties": {
        "slug": {
          "description": "Article slug, use as input to get_article",
          "title": "Slug",
          "type": "string"
        },
        "title": {
          "description": "Article title",
          "title": "Title",
          "type": "string"
        },
        "url": {
          "description": "Public URL of the article",
          "title": "Url",
          "type": "string"
        },
        "description": {
          "description": "Article description or summary",
          "title": "Description",
          "type": "string"
        },
        "tags": {
          "description": "Topic tags assigned to the article",
          "items": {
            "type": "string"
          },
          "title": "Tags",
          "type": "array"
        },
        "date": {
          "default": "",
          "description": "Publication date (ISO 8601)",
          "title": "Date",
          "type": "string"
        },
        "relevance_score": {
          "description": "TF-IDF cosine similarity score, 0.0 to 1.0 (1.0 = direct date-sorted hit when query is empty)",
          "title": "Relevance Score",
          "type": "number"
        },
        "quality_score": {
          "description": "Build-time editorial quality score",
          "title": "Quality Score",
          "type": "number"
        },
        "quality_style": {
          "default": "",
          "description": "Editorial style category",
          "title": "Quality Style",
          "type": "string"
        }
      },
      "required": [
        "slug",
        "title",
        "url",
        "description",
        "tags",
        "relevance_score",
        "quality_score"
      ],
      "title": "SearchResult",
      "type": "object"
    }
  },
  "title": "search_blogOutput"
}

List all blog articles. No TF-IDF computation — pure database listing. Use to browse the full corpus, paginate through articles, or filter by tag. For full-text semantic search use search_blog instead.

{
  "type": "object",
  "properties": {
    "tag": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional tag filter (e.g. 'setup', 'fixes', 'strategy'). Only articles with this tag are considered. Use list_tags to discover available tags.",
      "title": "Tag"
    },
    "sort": {
      "default": "date_desc",
      "description": "Result ordering. 'date_desc' newest first (default). 'date_asc' oldest first. 'title_asc' alphabetical. 'quality_desc' best quality first.",
      "enum": [
        "date_desc",
        "date_asc",
        "title_asc",
        "quality_desc"
      ],
      "title": "Sort",
      "type": "string"
    },
    "limit": {
      "default": 20,
      "description": "Number of results (1-50)",
      "maximum": 50,
      "minimum": 1,
      "title": "Limit",
      "type": "integer"
    },
    "offset": {
      "default": 0,
      "description": "Pagination offset (0-based)",
      "minimum": 0,
      "title": "Offset",
      "type": "integer"
    }
  },
  "title": "list_articlesArguments"
}

{
  "type": "object",
  "properties": {
    "result": {
      "items": {
        "$ref": "#/$defs/ArticleSummary"
      },
      "title": "Result",
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "$defs": {
    "ArticleSummary": {
      "description": "A single article entry returned by list_articles.",
      "properties": {
        "slug": {
          "description": "Article slug, use as input to get_article",
          "title": "Slug",
          "type": "string"
        },
        "title": {
          "description": "Article title",
          "title": "Title",
          "type": "string"
        },
        "url": {
          "description": "Public URL of the article",
          "title": "Url",
          "type": "string"
        },
        "date": {
          "default": "",
          "description": "Publication date (ISO 8601)",
          "title": "Date",
          "type": "string"
        },
        "tags": {
          "description": "Topic tags assigned to the article",
          "items": {
            "type": "string"
          },
          "title": "Tags",
          "type": "array"
        },
        "description": {
          "default": "",
          "description": "Article description or summary",
          "title": "Description",
          "type": "string"
        },
        "quality_score": {
          "description": "Editorial quality score",
          "title": "Quality Score",
          "type": "number"
        },
        "quality_style": {
          "default": "",
          "description": "Editorial style category",
          "title": "Quality Style",
          "type": "string"
        },
        "quality_class": {
          "default": "",
          "description": "Editorial quality class",
          "title": "Quality Class",
          "type": "string"
        }
      },
      "required": [
        "slug",
        "title",
        "url",
        "tags",
        "quality_score"
      ],
      "title": "ArticleSummary",
      "type": "object"
    }
  },
  "title": "list_articlesOutput"
}

Retrieve the full content of a blog article by its slug. Returns the article body (Markdown) plus metadata. If the slug does not match any article, returns an Article with `error='article_not_found'` and other fields at their defaults.

{
  "type": "object",
  "properties": {
    "slug": {
      "description": "Article slug as returned by search_blog (e.g. 'setup-llm-inference-setup'). Lower-case, hyphenated.",
      "title": "Slug",
      "type": "string"
    }
  },
  "required": [
    "slug"
  ],
  "title": "get_articleArguments"
}

{
  "type": "object",
  "properties": {
    "slug": {
      "description": "Article slug",
      "title": "Slug",
      "type": "string"
    },
    "title": {
      "default": "",
      "description": "Article title",
      "title": "Title",
      "type": "string"
    },
    "url": {
      "default": "",
      "description": "Public URL of the article",
      "title": "Url",
      "type": "string"
    },
    "date": {
      "default": "",
      "description": "Publication date (ISO 8601)",
      "title": "Date",
      "type": "string"
    },
    "tags": {
      "description": "Topic tags assigned to the article",
      "items": {
        "type": "string"
      },
      "title": "Tags",
      "type": "array"
    },
    "description": {
      "default": "",
      "description": "Short article description",
      "title": "Description",
      "type": "string"
    },
    "body": {
      "default": "",
      "description": "Full article body in Markdown",
      "title": "Body",
      "type": "string"
    },
    "quality_score": {
      "default": 0,
      "description": "Build-time quality score from the editorial pipeline (unbounded weighted composite across 13 signals, higher is better; thresholds depend on style)",
      "title": "Quality Score",
      "type": "number"
    },
    "quality_style": {
      "default": "",
      "description": "Editorial style category (e.g. 'best_practice_learnings', 'werthaltige_code_beispiele'). Empty if not categorised.",
      "title": "Quality Style",
      "type": "string"
    },
    "quality_class": {
      "default": "",
      "description": "Editorial content class (e.g. 'Ephemeral', 'Evergreen'). Empty if not classified.",
      "title": "Quality Class",
      "type": "string"
    },
    "word_count": {
      "default": 0,
      "description": "Word count of the article body",
      "title": "Word Count",
      "type": "integer"
    },
    "error": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Set to 'article_not_found' if no article matches the slug",
      "title": "Error"
    }
  },
  "required": [
    "slug"
  ],
  "description": "Full content of a single blog article.",
  "title": "Article"
}

Validate an SGLang configuration for NVIDIA DGX Spark (GB10/SM121A). Pure pattern-matching against known failure modes documented in the Sovereign AI Blog. No inference, no external calls. Returns critical issues, non-fatal warnings, and a recommended baseline config. All parameters are optional; supply only what you have. With no inputs you get the recommended config and a 'unknown' verdict.

{
  "type": "object",
  "properties": {
    "attention_backend": {
      "default": "",
      "description": "SGLang --attention-backend value (e.g. 'flashinfer', 'triton'). Empty string = skip this check.",
      "title": "Attention Backend",
      "type": "string"
    },
    "mem_fraction": {
      "default": 0,
      "description": "SGLang --mem-fraction-static value (e.g. 0.88). 0.0 = skip this check.",
      "maximum": 1,
      "minimum": 0,
      "title": "Mem Fraction",
      "type": "number"
    },
    "cuda_graph_max_bs": {
      "default": 0,
      "description": "SGLang --cuda-graph-max-bs value. 0 = skip this check.",
      "minimum": 0,
      "title": "Cuda Graph Max Bs",
      "type": "integer"
    },
    "image_tag": {
      "default": "",
      "description": "Docker image tag in use (e.g. 'lmsysorg/sglang:latest', 'lmsysorg/sglang:v0.4.0'). Empty = skip.",
      "title": "Image Tag",
      "type": "string"
    },
    "hardware": {
      "default": "",
      "description": "Hardware description (e.g. 'GB10', 'DGX Spark', 'SM121A'). Empty = skip GB10-specific rules.",
      "title": "Hardware",
      "type": "string"
    },
    "error_message": {
      "default": "",
      "description": "Paste error log output here for pattern matching against known failure modes.",
      "title": "Error Message",
      "type": "string"
    }
  },
  "title": "diagnose_sglangArguments"
}

{
  "type": "object",
  "properties": {
    "issues": {
      "description": "Critical issues that will prevent SGLang from running correctly",
      "items": {
        "$ref": "#/$defs/DiagnosticIssue"
      },
      "title": "Issues",
      "type": "array"
    },
    "warnings": {
      "description": "Non-fatal warnings (suboptimal but non-blocking)",
      "items": {
        "$ref": "#/$defs/DiagnosticIssue"
      },
      "title": "Warnings",
      "type": "array"
    },
    "recommended_config": {
      "$ref": "#/$defs/RecommendedConfig",
      "description": "Verified-good baseline config for GB10/SM121A"
    },
    "verdict": {
      "description": "Overall verdict. 'unknown' = no inputs provided.",
      "enum": [
        "valid",
        "valid_with_warnings",
        "invalid",
        "unknown"
      ],
      "title": "Verdict",
      "type": "string"
    }
  },
  "required": [
    "issues",
    "warnings",
    "recommended_config",
    "verdict"
  ],
  "$defs": {
    "DiagnosticIssue": {
      "description": "A single rule violation found in the SGLang config.",
      "properties": {
        "severity": {
          "description": "critical = config will fail, warning = will run but suboptimal",
          "enum": [
            "critical",
            "warning"
          ],
          "title": "Severity",
          "type": "string"
        },
        "param": {
          "description": "The config parameter or input field that triggered the rule",
          "title": "Param",
          "type": "string"
        },
        "value": {
          "description": "The offending value (stringified)",
          "title": "Value",
          "type": "string"
        },
        "problem": {
          "description": "Plain-English explanation of the failure mode",
          "title": "Problem",
          "type": "string"
        },
        "fix": {
          "description": "Concrete fix to apply",
          "title": "Fix",
          "type": "string"
        },
        "source": {
          "description": "URL of the blog article documenting this issue",
          "title": "Source",
          "type": "string"
        }
      },
      "required": [
        "severity",
        "param",
        "value",
        "problem",
        "fix",
        "source"
      ],
      "title": "DiagnosticIssue",
      "type": "object"
    },
    "RecommendedConfig": {
      "description": "A known-good SGLang config baseline for GB10/SM121A hardware.",
      "properties": {
        "attention_backend": {
          "description": "SGLang attention backend (triton is the verified default for GB10)",
          "title": "Attention Backend",
          "type": "string"
        },
        "mem_fraction": {
          "description": "--mem-fraction-static value (0.75 is the upper safe bound for GB10)",
          "title": "Mem Fraction",
          "type": "number"
        },
        "cuda_graph_max_bs": {
          "description": "--cuda-graph-max-bs (32 is the optimum for GB10)",
          "title": "Cuda Graph Max Bs",
          "type": "integer"
        },
        "image_tag": {
          "description": "Docker image tag with SM121A support",
          "title": "Image Tag",
          "type": "string"
        },
        "env": {
          "additionalProperties": true,
          "description": "Environment variables required for stable operation",
          "title": "Env",
          "type": "object"
        },
        "max_running_requests": {
          "description": "Concurrent request cap, calibrated for GB10 memory budget",
          "title": "Max Running Requests",
          "type": "integer"
        }
      },
      "required": [
        "attention_backend",
        "mem_fraction",
        "cuda_graph_max_bs",
        "image_tag",
        "env",
        "max_running_requests"
      ],
      "title": "RecommendedConfig",
      "type": "object"
    }
  },
  "description": "Outcome of a diagnose_sglang call.",
  "title": "DiagnoseResult"
}

List all topic tags used across the Sovereign AI Blog corpus, with article counts. Use this to browse the topic space before calling search_blog with a tag filter.

{
  "type": "object",
  "properties": {
    "sort": {
      "default": "count_desc",
      "description": "Result ordering. 'count_desc' lists most-used tags first (default). 'alpha' sorts alphabetically.",
      "enum": [
        "count_desc",
        "alpha"
      ],
      "title": "Sort",
      "type": "string"
    }
  },
  "title": "list_tagsArguments"
}

{
  "type": "object",
  "properties": {
    "result": {
      "items": {
        "$ref": "#/$defs/TagInfo"
      },
      "title": "Result",
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "$defs": {
    "TagInfo": {
      "description": "A topic tag with the number of articles using it.",
      "properties": {
        "tag": {
          "description": "The tag name (lower-case, snake_case)",
          "title": "Tag",
          "type": "string"
        },
        "article_count": {
          "description": "Number of articles tagged with this tag",
          "title": "Article Count",
          "type": "integer"
        }
      },
      "required": [
        "tag",
        "article_count"
      ],
      "title": "TagInfo",
      "type": "object"
    }
  },
  "title": "list_tagsOutput"
}