Files
OmniRoute/open-sse/handlers/rerank.ts
diegosouzapw 71d14209a4 feat: OmniRoute v1.0.0 — Intelligent AI Gateway & Universal LLM Proxy
OmniRoute is an intelligent API gateway that unifies 20+ AI providers behind a single
OpenAI-compatible endpoint. Features include intelligent routing with 6 strategies,
multi-format translation (OpenAI/Claude/Gemini/Responses API), circuit breakers,
semantic caching, combo fallback chains, real-time health monitoring, and a full
dashboard with provider management, analytics, and CLI tool integration.

Key highlights:
- 20+ providers (Claude Code, Codex, Gemini CLI, GitHub Copilot, iFlow, Qwen, Kiro, etc.)
- 6 routing strategies (Fill First, Round Robin, P2C, Random, Least Used, Cost Optimized)
- Export/Import database backup with full archive support
- Translator Playground with 4 modes (Playground, Chat Tester, Test Bench, Live Monitor)
- 100% TypeScript across src/ and open-sse/
- Docker support with multi-stage builds
- Comprehensive documentation and 9 dashboard screenshots
2026-02-18 00:02:15 -03:00

138 lines
4.0 KiB
TypeScript

/**
* Rerank Handler
*
* Handles /v1/rerank requests following the Cohere rerank API format.
* Routes to the appropriate provider based on the model prefix or lookup.
*/
import { getRerankProvider, parseRerankModel } from "../config/rerankRegistry.ts";
import { errorResponse } from "../utils/error.ts";
/**
* Build authorization header for a rerank provider
*/
function buildAuthHeader(providerConfig, token) {
if (providerConfig.authHeader === "bearer") {
return { Authorization: `Bearer ${token}` };
}
return {};
}
/**
* Transform request body for provider-specific formats (e.g. NVIDIA ranking API)
*/
function transformRequestForProvider(providerConfig, body) {
if (providerConfig.format === "nvidia") {
return {
model: body.model,
query: { text: body.query },
passages: (body.documents || []).map((doc) => ({
text: typeof doc === "string" ? doc : doc.text || "",
})),
top_n: body.top_n,
};
}
// Default: Cohere-compatible format (used by Together, Fireworks, Cohere)
return body;
}
/**
* Transform response from provider-specific formats back to Cohere format
*/
function transformResponseFromProvider(providerConfig, data) {
if (providerConfig.format === "nvidia") {
return {
id: data.id || `rerank-${Date.now()}`,
results: (data.rankings || []).map((r) => ({
index: r.index,
relevance_score: r.logit || r.score || 0,
document: { text: r.text || "" },
})),
meta: {
api_version: { version: "2" },
billed_units: { search_units: 1 },
},
};
}
return data;
}
/**
* Handle a rerank request
*
* @param {Object} options
* @param {string} options.model - Model ID (e.g. "rerank-v3.5" or "cohere/rerank-v3.5")
* @param {string} options.query - Query to rank documents against
* @param {string[]|Object[]} options.documents - Documents to rerank
* @param {number} [options.top_n] - Number of top results to return
* @param {boolean} [options.return_documents] - Whether to include document text in results
* @param {Object} options.credentials - Provider credentials { apiKey, accessToken }
* @returns {Response}
*/
/** @returns {Promise<any>} */
export async function handleRerank({
model,
query,
documents,
top_n,
return_documents,
credentials,
}) {
if (!model) return errorResponse(400, "model is required");
if (!query) return errorResponse(400, "query is required");
if (!documents || !Array.isArray(documents) || documents.length === 0) {
return errorResponse(400, "documents must be a non-empty array");
}
const { provider: providerId, model: modelId } = parseRerankModel(model);
const providerConfig = providerId ? getRerankProvider(providerId) : null;
if (!providerConfig) {
return errorResponse(
400,
`No rerank provider found for model "${model}". Available: cohere, together, nvidia, fireworks`
);
}
const token = credentials?.apiKey || credentials?.accessToken;
if (!token) {
return errorResponse(401, `No credentials for rerank provider: ${providerId}`);
}
const requestBody = transformRequestForProvider(providerConfig, {
model: modelId,
query,
documents,
top_n: top_n || documents.length,
return_documents: return_documents !== false,
});
try {
const res = await fetch(providerConfig.baseUrl, {
method: "POST",
headers: {
"Content-Type": "application/json",
...buildAuthHeader(providerConfig, token),
},
body: JSON.stringify(requestBody),
});
if (!res.ok) {
const errData = await res.json().catch(() => ({}));
return errorResponse(
res.status,
errData.message || errData.error?.message || `Provider returned HTTP ${res.status}`
);
}
const data = await res.json();
const result = transformResponseFromProvider(providerConfig, data);
return Response.json(result, {
headers: { "Access-Control-Allow-Origin": "*" },
});
} catch (err) {
return errorResponse(500, `Rerank request failed: ${err.message}`);
}
}