Expand description
Comindly LLM enrichment — per-symbol summaries, symbol-aware query generation, and a
repo style guide, via Rig (provider-agnostic: OpenAI by default; any OpenAI-compatible
endpoint via COMINDLY_LLM_BASE_URL; Bedrock/Vertex/others can be added behind cargo features).
Opt-in / data egress: these functions send code (signatures, snippets) to the configured
LLM provider. They run only when the caller explicitly enables enrichment
(comindly link --enrich), never as part of plain indexing. Requires OPENAI_API_KEY (or a
provider key + COMINDLY_LLM_BASE_URL).
Structs§
- Enrichment
- LLM-generated enrichment for one symbol.
- LlmClient
Constants§
- DEFAULT_
BASE_ URL - Where requests go without an endpoint setting: OpenAI.
- DEFAULT_
MODEL - Default model — cheap and fast, suitable for bulk symbol summaries.