Skip to content

docs: correct reranker timeout default from 12s to 30s #59

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
detail-app wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

docs: correct reranker timeout default from 12s to 30s #59

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docs/configuration.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,4 +156,4 @@ Common variables (see `app.rag.*` defaults in `application.properties`):
- `RAG_TOP_K`
- `RAG_RETURN_K`
- `RAG_CITATIONS_K`
- `RAG_RERANKER_TIMEOUT` (default `12s`) — timeout budget for LLM reranking calls
- `RAG_RERANKER_TIMEOUT` (default `30s`) — timeout budget for LLM reranking calls
4 changes: 2 additions & 2 deletions docs/retrieval-pipeline.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -172,7 +172,7 @@ Each document is presented as `[index] title | url` followed by the first 500 ch

- Model: same provider as chat (OpenAI/GitHub Models)
- Temperature: `0.0` (deterministic)
- Timeout: configurable via `app.rag.reranker-timeout` (default 12s)
- Timeout: configurable via `app.rag.reranker-timeout` (default 30s)
- Response format: `{"order": [0, 3, 1, 2, ...]}` (0-based indices)

### Response parsing
Expand Down Expand Up @@ -292,7 +292,7 @@ All four must be non-blank and distinct (validated on startup).
|---|---|---|---|
| `app.rag.search-top-k` | `12` | Must be > 0 | Candidates fetched from hybrid search before reranking |
| `app.rag.search-return-k` | `6` | Must be > 0, must be <= `search-top-k` | Results returned to the LLM after reranking |
| `app.rag.reranker-timeout` | `12s` | Must be positive | Timeout for LLM reranking call |
| `app.rag.reranker-timeout` | `30s` | Must be positive | Timeout for LLM reranking call |
| `app.rag.search-citations` | `3` | Must be >= 0 | Citation references included in the response |
| `app.rag.search-mmr-lambda` | `0.5` | Must be in [0.0, 1.0] | MMR lambda (higher = relevance, lower = diversity) |
| `app.rag.chunk-max-tokens` | `900` | Must be > 0 | Max tokens per ingested chunk (see [ingestion.md](ingestion.md)) |
Expand Down