github/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-04-19 00:27:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs(markdownlint): enable autofixable rules and normalize links

Browse Source
This commit is contained in:
Sebastian
2026-02-06 09:55:12 -05:00
parent 1bf9f237f7
commit c7aec0660e
84 changed files with 261 additions and 198 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
docs/concepts/memory.md
View File

@@ -302,8 +302,8 @@ Why OpenAI batch is fast + cheap:
- For large backfills, OpenAI is typically the fastest option we support because we can submit many embedding requests in a single batch job and let OpenAI process them asynchronously.
- OpenAI offers discounted pricing for Batch API workloads, so large indexing runs are usually cheaper than sending the same requests synchronously.
- See the OpenAI Batch API docs and pricing for details:
- https://platform.openai.com/docs/api-reference/batch
- https://platform.openai.com/pricing
- [https://platform.openai.com/docs/api-reference/batch](https://platform.openai.com/docs/api-reference/batch)
- [https://platform.openai.com/pricing](https://platform.openai.com/pricing)
Config example:
@@ -382,11 +382,11 @@ Implementation sketch:
- **Vector**: top `maxResults * candidateMultiplier` by cosine similarity.
- **BM25**: top `maxResults * candidateMultiplier` by FTS5 BM25 rank (lower is better).
2. Convert BM25 rank into a 0..1-ish score:
1. Convert BM25 rank into a 0..1-ish score:
- `textScore = 1 / (1 + max(0, bm25Rank))`
3. Union candidates by chunk id and compute a weighted score:
1. Union candidates by chunk id and compute a weighted score:
- `finalScore = vectorWeight * vectorScore + textWeight * textScore`