alt_text
Generate descriptive alt text for images from URLs or local files to improve accessibility and SEO using computer vision models.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | No | ||
| image_url | No | ||
| max_words | No |
Input Schema (JSON Schema)
{
"properties": {
"file_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "File Path"
},
"image_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Image Url"
},
"max_words": {
"default": 20,
"title": "Max Words",
"type": "integer"
}
},
"title": "alt_textArguments",
"type": "object"
}
Implementation Reference
- src/cv_mcp/mcp_server.py:80-92 (handler)MCP tool handler for 'alt_text'. Validates input (image_url or file_path), constructs image_ref, and delegates to run_alt_text from metadata.runner.@mcp.tool() def alt_text( image_url: Optional[str] = None, file_path: Optional[str] = None, max_words: int = 20, ) -> str: if not image_url and not file_path: raise ValueError("Provide either image_url or file_path") if image_url and file_path: raise ValueError("Provide only one of image_url or file_path, not both") image_ref = image_url or file_path # type: ignore return run_alt_text(image_ref, max_words=max_words)
- Core implementation of alt_text generation. Supports local, Ollama, and OpenRouter backends using specific system and user prompts from prompts.py.def run_alt_text(image_ref: str, *, model: Optional[str] = None, max_words: int = 20) -> str: if _use_local_for("caption"): prompt = f"{prompts.ALT_SYSTEM}\n\n{prompts.alt_user_prompt(max_words)}" return _local_gen(image_ref, prompt) if _use_ollama_for("caption"): from cv_mcp.captioning.ollama_client import OllamaClient client = OllamaClient(host=str(_cfg_value("ollama_host", "http://localhost:11434"))) res = client.analyze_single_image( image_ref, prompts.alt_user_prompt(max_words), model=_cfg_value("caption_model"), system=prompts.ALT_SYSTEM, ) if not res.get("success"): raise RuntimeError(str(res.get("error", "Alt text generation failed (ollama)"))) return str(res.get("content", "")).strip() client = OpenRouterClient() res = client.analyze_single_image( image_ref, prompts.alt_user_prompt(max_words), model=model or _cfg_value("caption_model"), system=prompts.ALT_SYSTEM, ) if not res.get("success"): raise RuntimeError(str(res.get("error", "Alt text generation failed"))) return str(res.get("content", "")).strip()
- src/cv_mcp/metadata/prompts.py:1-13 (helper)System prompt and user prompt template used by run_alt_text for generating factual alt text descriptions.from __future__ import annotations ALT_SYSTEM = ( "You describe images for accessibility. Be concise and strictly factual. Do not infer unseen details." ) def alt_user_prompt(max_words: int = 20) -> str: return ( f"Describe this image in <= {max_words} words. Neutral tone. " "No brand/species/location guesses. Return one sentence only. If unknown, omit." )