codegen

Code reranking/semantic search

Uses Relace's code reranking model to find the most relevant files for a given query. This is useful as a first pass in agentic exploration to narrow down the search space.

Based on: https://docs.relace.ai/docs/code-reranker/agent

Query Construction: The query can be a short question or a more detailed conversation with the user request included. For a first pass, use the full conversation; for subsequent calls, use more targeted questions.

Token Limit and Score Threshold: For 200k token context models like Claude 4 Sonnet, recommended defaults are scoreThreshold=0.5 and tokenLimit=30000.

The response will be a list of file paths and contents ordered from most relevant to least relevant.

get/codegen/reranking/{path}

Request

Base URL
https://api.blaxel.ai/v0
Auth
- OAuth 2
  Authorization code/oauth/authorize
  Client credentials
  Token URL/oauth/token
  Scopesadmin
- or HTTP bearer
TypeScript
https://skmtc.dev/blaxel/apis/blaxel-control-plane/docs/codegen/reranking/:path/get.ts
A function with typed inputs. Its response is checked against the schema.

Path parameters

pathstring required

Path to search in (relative to workspace)

Query parameters

querystring required

Natural language query to search for

scoreThresholdnumber

Minimum relevance score (default: 0.5)

tokenLimitinteger

Maximum tokens to return (default: 30000)

filePatternstring

Regex pattern to filter files (e.g., .*\.ts$ for TypeScript files)

Response

Relevant files found

messagestring

successboolean

Example response

{
  "message": "Found 5 relevant files",
  "success": true
}

Changes

No recorded changes to this operation across all 1 revision of this API.