Conversation
|
CLA Assistant Lite bot All contributors have signed the CLA ✍️ ✅ |
Author
|
I have read the Arakoo CLA Document and I hereby sign the CLA |
Author
|
recheck |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds Qdrant support to the JavaScript SDK through the existing
@arakoodev/edgechains.js/vector-dbexport. Callers can store and query vectors using Qdrant's REST API through aQdrantclass, without installing a Qdrant client package.Fixes #273
/claim #273
Changes
JS/edgechains/examples/qdrant-search, which imports the public SDK export and removes its uniquely named collection after execution.The SDK now lives under
JS/edgechains/arakoodev; this change uses that current package location rather than the olderlibpath linked in the issue.Validation
Verified locally with Node 22.23.2, npm 10.9.8, Vitest 2.1.9 and Qdrant 1.15.5:
npm run buildinJS/edgechains/arakoodev: passed.node_modules/.bin/vitest run src/vector-db/src/tests/qdrant --reporter=verbosewithQDRANT_URLpointing to the local server: 64 unit tests and two live integration tests passed.npm startinJS/edgechains/examples/qdrant-search: passed using the public package export; the database document ranked above the music document.d924dd4fec3f310cd7fef88dbf1390ee4b29f4a5, using identical dependencies, reproduced all 15 failures. These include Jest globals under Vitest, stale OpenAI import paths, missing browser/runtime prerequisites and an external HTTP 403. The full upstream suite is not passing.Focused coverage includes ID zero, UUIDs, Unicode, dense/named vectors, filters, thresholds, pagination, payload/vector flags, empty results, writes and deletions, dimension errors, invalid numeric values, HTTP errors, malformed responses, deadlines and timer cleanup.
Demo
The 30-second
qdrant-demo.mp4is a rendered playback of captured output from the actual local tests and example. It is not a screen recording.Scope and limitations
Sparse vectors, multivectors, hybrid queries, automatic retries and a Supabase compatibility facade are outside this change. Qdrant validates UUID syntax and collection dimensions. A timed-out write may already have applied; the documentation advises callers to reconcile its outcome before retrying.
AI assistance
The implementation, tests, documentation and this description were prepared with OpenAI Codex assistance. The validation results above come from local automated runs; an independent AI code review also found no blocking defect.
qdrant-demo.mp4