pretext: spec POST /pipelines/{id}/encode#155
Open
beckyconning wants to merge 1 commit into
Open
Conversation
Documents the new tenant-authed query-embedding route added in precog/services#3504. Body is `{"text": "..."}` and the response is the verbatim encoder envelope (`{"vec":[...],"dim":768,"model_id":"..."}`). Slotted next to the vectorize PUT — same auth model, same family. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Documents the new tenant-authed query-embedding route added in precog/services#3504.
{ \"text\": \"...\" }{ \"vec\": [...], \"dim\": 768, \"model_id\": \"...\" }200on success,400on empty text,401if unauthed,404if the caller can't see the pipeline,502if the encoder is unreachableSlotted next to the existing
vectorizePUT — same auth model, same family.Why
External clients (notably the MCP server's
semantic_searchtool) need to embed user queries against the same sentence-transformers/all-mpnet-base-v2 model the corpus was vectorized with. Running the embedder in-process required@xenova/transformers+onnxruntime-nodein a Vercel serverless function, which has been the failure mode behind recent "Failed to embed the query" errors. Exposing the encoder behind the public API gets us tenant auth + a single dedicated model pod instead.Test plan
/pipelines/{id}/encodeonce precog/services#3504 lands🤖 Generated with Claude Code