docs: improve .env.example.full reranker and embedding provider documentation - #1073
Merged
lightzt99 merged 1 commit intoJun 23, 2026
Conversation
…entation - Document the `generic` reranker provider for standard rerank APIs (SiliconFlow, Xinference, vLLM, etc.) with usage examples - Add all supported embedding providers (azure_openai, gemini, vertexai, together, aws_bedrock, zai) to the EMBEDDING_PROVIDER list - Add model examples for siliconflow, azure_openai, gemini, zai embeddings - Fix RERANKER_MODEL defaults to match code (jina-reranker-v3, rerank) - Expand RERANKER_API_BASE_URL comments with per-provider defaults - Add concrete configuration examples for SiliconFlow and Xinference rerank
Collaborator
|
LGTM |
222twotwotwo
pushed a commit
to 222twotwotwo/powercontext
that referenced
this pull request
Aug 23, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
While configuring PowerMem I wanted to integrate SiliconFlow and other third-party services as a reranker, but found no guidance in
.env.example.fullon how to do so. The code already supports agenericreranker provider and many more embedding providers than documented. This PR improves the configuration reference to match what the code actually supports.Changes
genericreranker provider for standard rerank APIs (SiliconFlow, Xinference, vLLM, or any OpenAI-compatible rerank endpoint)azure_openai,gemini,vertexai,together,aws_bedrock,zai) to theEMBEDDING_PROVIDERlistsiliconflow,azure_openai,gemini,zaiembedding providersRERANKER_MODELcomment defaults to match actual code:jina-reranker-v3(wasjina-reranker-v2-base-multilingual),rerankfor zai (wasrerank-3-base, rerank-3-large)RERANKER_API_BASE_URLcomments with per-provider default URLsWhy
genericprovider is a powerful universal adapter but is completely invisible in the docsCloses #1072
Validation
src/powermem/integrations/rerank/config/providers.pyandsrc/powermem/integrations/embeddings/config/providers.pyjina-reranker-v3,rerank(zai),qwen3-rerankhttps://api.jina.ai/v1/rerank,https://open.bigmodel.cn/api/paas/v4/rerankGenericRerankimplementation (standard{model, query, documents}→{results: [{index, relevance_score}]})git diff --checkpasses