Commit graph

16 commits

Author SHA1 Message Date
elpresidank
b6759e75df refactor(ts): make port effect native 2026-06-06 10:33:10 -05:00
elpresidank
9eaa1a2c1e Use Effect fn for FalkorDB helpers 2026-06-04 06:44:34 -05:00
elpresidank
09d34fb4d4 Normalize term translation with Effect Match 2026-06-02 09:11:33 -05:00
elpresidank
d38ce475fd Scope FalkorDB triples clients 2026-06-02 03:55:39 -05:00
elpresidank
44110c5bb4 Add typed flow spec accessors 2026-06-02 03:23:23 -05:00
elpresidank
74955d6041 Use native runtimes for flow entrypoints 2026-06-02 02:34:03 -05:00
elpresidank
f6878d4dd7 Enforce strict Effect tsgo migrations 2026-06-01 23:19:54 -05:00
elpresidank
dca2786828 Remove native classes from TS runtime 2026-06-01 20:26:47 -05:00
elpresidank
3515106670 Advance TS port Effect workbench 2026-06-01 16:22:25 -05:00
elpresidank
ffd97375a8 saving 2026-05-12 08:06:58 -05:00
elpresidank
f2b376abef fix: FalkorDB result parsing, embeddings routing, triples query response, graph visualization
- Fix FalkorDB triples query: client v5 returns objects not arrays, use named field access
- Fix embeddings service: align spec names to "embeddings-request"/"embeddings-response"
- Fix client triplesQuery: read `triples` field instead of `response` from backend
- Fix graph page crash: guard against non-array triples, accept literals as entity nodes
- Add seed:demo script for AI industry knowledge graph (254 triples, 64 entities)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-10 04:59:36 -05:00
elpresidank
5e3929a883 fix: comprehensive QA audit — light mode, accessibility, error handling, code quality
- Fix light mode: theme-aware graph node labels, remove prose-invert for
  theme-safe markdown, add brand/semantic color overrides for light backgrounds
- Add 404 catch-all route redirecting unknown paths to /chat
- FalkorDB: add .catch() to connectPromise, add ensureConnected() to all
  store methods (createLiteral, relateNode, relateLiteral, deleteCollection)
- Accessibility: dialog role/aria-modal, toast aria-live, dismiss/zoom/search
  button aria-labels, close panel aria-label
- Lazy-load ForceGraph2D (splits 189KB into separate chunk, main bundle -26%)
- Cap conversation localStorage at 200 messages to prevent quota overflow
- Fix pnpm test: add --passWithNoTests to cli/mcp packages
- Add upload error notification instead of silent catch
- Remove unused class-variance-authority dep and dead tabs.tsx component
- Add @types/node to flow package devDependencies
- Remove stale FIXME comment in messages.ts

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-07 09:15:59 -05:00
elpresidank
3a80872482 fix: comprehensive QA — resolve 13 bugs, add UX improvements across all services
Client SDK: add .catch() to graphRagStreaming/documentRagStreaming (silent timeout),
null-guard JSON.parse in getPrompts/getSystemPrompt/getPrompt.

Backend: implement "getvalues" config operation for token costs, null-check
createTerm() in FalkorDB triples query, add knowledge-cores service entrypoint
and Docker entry, return proper HTTP 400/404 for gateway error responses.

Workbench: cancel button + elapsed timer for chat, clear agent spinner on error,
flow dialog inline validation, responsive header wrapping, knowledge cores
loading timeout, sidebar/page naming consistency, theme toggle indicator.

Infrastructure: enable Grafana Explore for viewers, add gateway Prometheus
scrape target, fix RAG pipeline dashboard layout (6 panels visible),
filter Service Health to configured targets only.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-07 05:20:10 -05:00
elpresidank
50fb311d2d feat: real PDF pipeline test — end-to-end knowledge extraction working
Add full pipeline test that generates a real PDF, processes it through
the entire pipeline, and verifies knowledge lands in FalkorDB:

- Create test PDF generator using pdf-lib (2-page doc about Acme Corp)
- Add testFullPipeline() to integration tests with store verification
- Fix FalkorDB client connect() — createClient returns unconnected client
  in both TriplesStore and TriplesQuery classes

Results: PDF decoded (2 pages) → chunked (2 chunks) → extracted
(4 relationships) → 16 triples stored in FalkorDB including:
  alice-johnson → is-a-senior-engineer → acme-corporation
  cloudsync → uses-aws-for-hosting → amazon-web-services
  provenance: pages → prov:wasDerivedFrom → source document

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-07 02:19:12 -05:00
elpresidank
c545213224 feat: add query/retrieval FlowProcessor services and missing runner scripts
Wire up the query and retrieval side of the pipeline so the agent can
answer questions from stored knowledge:

- Triples query service (FalkorDB) — all SPO pattern queries via NATS
- Graph embeddings query service (Qdrant) — entity vector similarity
- Document embeddings query service (Qdrant) — chunk vector similarity
- Graph RAG service — full concept→entity→traverse→score→synthesize pipeline
- Document RAG service — embed→find chunks→synthesize pipeline
- Runner scripts for chunker, extractor, embeddings (missing from Phase 5)
- Add DocumentEmbeddingsRequest/Response schema types
- Add RAG prompt templates (extract-concepts, edge-scoring, synthesize)
- Add graph/doc embeddings query topics to seed config + flow manager
- Add all pipeline/query/retrieval services to docker-compose
- 8 new runner scripts, 8 new pnpm script aliases

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-07 01:05:54 -05:00
elpresidank
b6536eca38 init 2026-04-05 22:44:45 -05:00