docs(vectordbs/opensearch): correct collection_name default, document user and password - #7392
Open
OfficialAbhinavSingh wants to merge 1 commit into
Conversation
… user and password The Python config table listed `collection_name` as required. OpenSearchConfig gives it a default of `mem0` (mem0/configs/vector_stores/opensearch.py:7) and no validator enforces it, unlike `host`, which validate_auth does reject when missing (:30-35) and which the table correctly marks required. `user` and `password` were absent from the Python table although the store consumes both: when `http_auth` is unset and both are given, they are passed to the client as an auth tuple (mem0/vector_stores/opensearch.py:68-70). That precedence is now stated on all three rows, since supplying `http_auth` silently wins over them. The TypeScript table already documents `user` and `password`; this brings the Python table in line with it.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Linked Issue
None — docs-only, so this is exempt from the accepted-issue gate (
pr-gate.yml). Happy to file an issue first if you would prefer one.Description
Two corrections to the Python tab of the OpenSearch config table, both checked against the code on
main.collection_namewas listed asrequired.OpenSearchConfiggives it a default ofmem0and nothing enforces it:hostis genuinely required —validate_authraises"Host must be provided for OpenSearch"(:30-35) — so that row is correct and is left as-is.userandpasswordwere missing from the Python tab, though the store consumes both. Whenhttp_authis unset and both are supplied, they are passed to the client as an auth tuple:Because
http_authsilently wins when present, that precedence is now stated on all three rows. The TypeScript tab already documentsuserandpassword, so this brings the Python tab in line.Type of Change
AI Assistance
Written with Claude Code. Each claim was read off the code rather than inferred: the
collection_namedefault, thevalidate_authhost check that makeshostgenuinely required, and the auth-tuple fallback in the client constructor.Worth flagging separately, since it is a code issue rather than a docs one and is deliberately not part of this PR:
api_key,connection_class, andpool_maxsizeare declared onOpenSearchConfigbut never read byOpenSearchDB— the client hardcodesconnection_class=RequestsHttpConnectionandpool_maxsize=20(vector_stores/opensearch.py:73-74), andapi_keyis not referenced anywhere in that file. Setting any of the three is silently inert, so I left them out of the table rather than document options that do nothing. Happy to open an issue for that if it is useful.Breaking Changes
N/A
Test Coverage
Docs-only, no code paths touched.
python3 scripts/check-llms-txt-coverage.pyreportsdocs/llms.txt is in sync— no page added or removed, so nollms.txtupdate is needed.Checklist