​
Prerequisites

​
1. Prepare Your Query and Codebase

Define your user request and collect the files from your codebase that need to be ranked for relevance.

user_query = "Add a user profile component with avatar and edit functionality"
codebase_files = [
    {"filename": "src/components/UserProfile.tsx", "code": "..."},
    {"filename": "src/types/user.ts", "code": "..."},
    {"filename": "src/components/Header.tsx", "code": "..."},
    # ... more files
]

​
2. Call the Code Reranker API

Send your query and codebase to the reranker to get relevance scores for each file.

import requests

url = "https://ranker.endpoint.relace.run/v2/code/rank"
api_key = "[YOUR_API_KEY]"

headers = {
    "Authorization": f"Bearer {api_key}",
    "Content-Type": "application/json"
}

data = {
    "query": user_query,
    "codebase": codebase_files,
    "token_limit": 150000,  # Set to your model's context limit with buffer room for system prompt
}

response = requests.post(url, headers=headers, json=data)
ranked_files = response.json()

​
3. Parse Ranked Results from Response

The API returns files ranked by relevance with scores between 0 and 1 up to the token limit you set.

[
  {
    "filename": "src/components/UserProfile.tsx",
    "score": 0.9598
  },
  {
    "filename": "src/types/user.ts",
    "score": 0.0321
  },
  {
    "filename": "src/components/Header.tsx",
    "score": 0.0014
  }
]

We recommend additionally filtering out results with relevance score ≤ 0.08. See the model overview section for more details.