docs: fix drift in Data Stores - #292
Open
jack-arturo wants to merge 1 commit into
Open
Conversation
Reattribute the memory MERGE, _graph_keyword_search, and _vector_search source links to the modules that actually define them, and document the QDRANT_HOST/QDRANT_PORT fallback used to construct QDRANT_URL. Verified against verygoodplugins/automem@8ff266e Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01BKgtjSkSUjSo7W8VSXs2Q1
Deploying automem-website with
|
| Latest commit: |
fe97e9a
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://c459179d.automem-website.pages.dev |
| Branch Preview URL: | https://docs-audit-architecture-data-1p8y.automem-website.pages.dev |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Automated docs-accuracy audit of
docs/architecture/data-stores. All findings verified against the localautomemcheckout at the SHA below.The theme here: three "Core Operations" / "Vector Search Implementation" notes point at
automem/stores/*.pyas if those modules held the logic. They do not —graph_store.pyis 37 lines containing only_build_graph_tag_predicate(), andvector_store.pyis 61 lines containing only_build_qdrant_tag_filter(). Both are small predicate builders; the search functions and the memory-write Cypher live elsewhere. (This is the follow-up left open by PR #169: "_graph_keyword_searchand_vector_searchmissing".)MERGE… (automem/stores/graph_store.py)"graph_store.pycontains no Cypher write. TheMERGE (m:Memory {id: $id})statement is in the memory API blueprint.automem/api/memory.py#L615._graph_keyword_search… (automem/stores/graph_store.py)"runtime_wiring.py;graph_store.pyonly builds the tag predicate it uses.automem/search/runtime_recall_helpers.py#L595, with a clause preservinggraph_store.py's real role._vector_search… (automem/stores/vector_store.py)"vector_store.pyonly builds the Qdrant tag filter.automem/search/runtime_recall_helpers.py#L940, with a clause preservingvector_store.py's real role.QDRANT_URL(default "none")QDRANT_URLis unset,config.pyconstructs it fromQDRANT_HOST+QDRANT_PORT(default6333) — the Railway-internal setup the deployment docs rely on. Neither variable appeared on this page.QDRANT_HOSTandQDRANT_PORTrows and noted the precedence onQDRANT_URL.Verified against: verygoodplugins/automem@8ff266e
Verified as correct, no change made: all four FalkorDB config rows (
FALKORDB_HOSTdoes fall through tolocalhost, after the Railway domain env vars);QDRANT_COLLECTION/VECTOR_SIZEdefaults; the whole embedding config table includingEMBEDDING_BATCH_SIZE=20andEMBEDDING_BATCH_TIMEOUT_SECONDS=2.0(real env vars atapp.py#L217-L218, not hardcoded); the auto-mode provider ladder Voyage → OpenAI → Ollama → FastEmbed → Placeholder and the Ollama defaults; theVECTOR_SIZE_AUTODETECTdimension-validation paragraph;/healthreportingconnected/disconnectedfor both stores; theruntime_clients.pysource note (init_falkordb,init_qdrant,ensure_qdrant_collectionall present); 14 relationship types in the Mermaid diagram.Questions
None — every fix above is a direct file/name/value correction.
Unverified
Follow-ups
28eb916e, several releases behind current8ff266e. They carry no line anchors and still resolve, so I left them rather than churn the header; the three links I did touch are now pinned to8ff266e, so the page is temporarily mixed-SHA.automem/stores/graph_store.pyandvector_store.pyare described in the source-note block as "FalkorDB abstraction" and "Qdrant abstraction". Given both are ~40-60 line predicate builders, those labels oversell them, but rewriting the header block is a bigger edit than this audit's scope.Generated by Claude Code