docs: refresh LightRAG model setup examples#17
Merged
Conversation
Replaces the stale LightRAG model guidance from #1 with current endpoints and slugs: - Kimi K2.6 via the international Moonshot API at https://api.moonshot.ai/v1 for the quality-oriented setup. - Cerebras gpt-oss-120b for the speed-oriented setup, replacing the deprecated qwen-3-32b example. - Fireworks Qwen3-Embedding-8B remains the high-quality embedding default. - Local Ollama example now includes both LLM_BINDING_HOST and EMBEDDING_BINDING_HOST. Also keeps README.md and part3-lightrag-setup.md in sync and updates the slow-ingestion recommendation. Supersedes #1.
4 tasks
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Replaces #1 with a current-main-safe LightRAG setup refresh. The original PR had the right idea (show multiple LightRAG model options), but the exact examples are now stale:
kimi-2.5is no longer the recommended current Kimi slug; Kimi's public docs now showkimi-k2.6.https://api.moonshot.cn/v1is the China-region endpoint; the international Kimi API docs usehttps://api.moonshot.ai/v1.qwen-3-32bis deprecated; the current production speed default isgpt-oss-120b.Changes
part3-lightrag-setup.mdand the combinedREADME.md..envoptions:nomic-embed-textembeddings (free/private)LLM_BINDING_HOST/EMBEDDING_BINDING_HOSTenv vars.Verification
git diff --checkclean.LLM_BINDING_HOSTis the correct env var for OpenAI-compatible and Ollama endpoints.https://api.moonshot.ai/v1andkimi-k2.6.qwen-3-32bdeprecated and listgpt-oss-120bas a current production model.Supersedes #1.