Add web finding to live corpus
add_findingAdd a web-found mathematics result to the live Mathlas corpus for immediate retrieval via search. Optionally include a dense vector for full dense+BM25 search.
Instructions
Ingest a web-found result into the live mathlas corpus so search_existing_math returns it immediately (provenance 'web_added'; BM25 always — no model load; full dense retrieval too if you pass dense_vec embedded in the served index's space). Use after web-searching per search_directive. Args: statement, slogan, source, optional name, optional dense_vec.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| statement | Yes | the web-found result's statement (the real text) | |
| slogan | Yes | a short natural-language denotation of it (what it says) | |
| source | Yes | where it came from: a URL / arXiv id / citation | |
| name | No | optional name/title of the result | |
| dense_vec | No | OPTIONAL dense embedding of the slogan, computed BY YOU (the AI) with the SAME model the served index uses, length == the served index dim. Storing it gives the finding full dense+BM25 retrieval (found even when wording differs from the query). NO model is loaded by mathlas. Omit for BM25-only. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| ok | Yes | ||
| statement | No | ||
| name | No | ||
| slogan | No | ||
| source | No | ||
| provenance | No | ||
| dense_added | No | ||
| n_findings | No | ||
| note | Yes | on failure (e.g. dense_vec dim mismatch) says exactly what to fix; the finding is NOT added |