Compare commits

...
Author SHA1 Message Date
Nicolò Boschi a274942d16 docs: add RERANKER_ZEROENTROPY_BASE_URL to configuration page
Document the new configurable base URL for the ZeroEntropy reranker
provider added in #766. Also fix a type error where RERANK_URL was
renamed to rerank_url but one usage was missed.
2026-03-30 17:45:22 +02:00
2 changed files with 3 additions and 1 deletions
@@ -704,7 +704,7 @@ class ZeroEntropyCrossEncoder(CrossEncoderModel):
indices = [idx for idx, _ in indexed_texts]
response = await self._async_client.post(
self.RERANK_URL,
self.rerank_url,
json={
"model": self.model,
"query": query,
@@ -464,6 +464,7 @@ Supported OpenAI embedding dimensions:
| `HINDSIGHT_API_RERANKER_LITELLM_MAX_TOKENS_PER_DOC` | Truncate documents to this many tokens before sending to the reranker (applies to both `litellm` and `litellm-sdk`). Use for models with small context windows (e.g. set to `900` for a 1024-token limit model). Unset by default (no truncation). | - |
| `HINDSIGHT_API_RERANKER_ZEROENTROPY_API_KEY` | ZeroEntropy API key for reranking | - |
| `HINDSIGHT_API_RERANKER_ZEROENTROPY_MODEL` | ZeroEntropy rerank model (`zerank-2`, `zerank-2-small`) | `zerank-2` |
| `HINDSIGHT_API_RERANKER_ZEROENTROPY_BASE_URL` | Custom base URL for ZeroEntropy-compatible API (e.g., mock server, proxy, or self-hosted deployment) | `https://api.zeroentropy.dev` |
| `HINDSIGHT_API_RERANKER_FLASHRANK_MODEL` | FlashRank model for fast CPU-based reranking | `ms-marco-MiniLM-L-12-v2` |
| `HINDSIGHT_API_RERANKER_FLASHRANK_CACHE_DIR` | Cache directory for FlashRank models | System default |
| `HINDSIGHT_API_RERANKER_JINA_MLX_MODEL_PATH` | Local path to downloaded `jina-reranker-v3-mlx` model (auto-downloads from HuggingFace if unset) | - |
@@ -498,6 +499,7 @@ export HINDSIGHT_API_RERANKER_COHERE_BASE_URL=https://your-azure-cohere-endpoint
export HINDSIGHT_API_RERANKER_PROVIDER=zeroentropy
export HINDSIGHT_API_RERANKER_ZEROENTROPY_API_KEY=your-api-key
export HINDSIGHT_API_RERANKER_ZEROENTROPY_MODEL=zerank-2 # or zerank-2-small
# export HINDSIGHT_API_RERANKER_ZEROENTROPY_BASE_URL=https://your-custom-endpoint.com # optional
# LiteLLM proxy - unified gateway for multiple reranking providers (requires running LiteLLM proxy server)
export HINDSIGHT_API_RERANKER_PROVIDER=litellm