Skip to content

Document the 5.1 AI & Models feature set#523

Merged
heskew merged 7 commits into
mainfrom
docs/models-5.1
Jun 11, 2026
Merged

Document the 5.1 AI & Models feature set#523
heskew merged 7 commits into
mainfrom
docs/models-5.1

Conversation

@heskew

@heskew heskew commented Jun 10, 2026

Copy link
Copy Markdown
Member

Summary

First documentation for the models/AI surface shipping in 5.1 — the docs currently have zero coverage of it. Everything is tagged <VersionBadge version="v5.1.0" /> (all feature commits are first contained in core's v5.1.0-beta.1).

  • New reference/models/ section (sidebar: "AI & Models"): overview + models configuration block, embed()/generate()/generateStream() API, tool calling incl. the toolMode: 'auto' agent loop (budgets, parallelism, error modes, trace, conversation hook), the four bundled backends (Ollama, OpenAI incl. OpenAI-compatible endpoints via baseUrl, Anthropic, Bedrock), and hdb_model_calls / aggregate analytics.
  • Schema reference: new @embed directive section (write semantics, validation, auto-HNSW); vector-indexing additions — int8 quantization with full-precision rerank, per-query ef, auto-scaled search ef (type="changed"), dotProduct distance.
  • Correction: the HNSW parameter table documented efSearchConstruction; the option Harper reads is efConstructionSearch. Fixed with a note.
  • Release notes: deliberately not included — the 5.1 release notes are authored separately (the earlier draft was removed in 44bfe49).

Deliberately not documented

  • openaiStream() SSE formatter — unmerged (branch pinned).
  • The built-in agent component (agent: config, agent_* operations) — merged as scaffold, operations-API-only, maxCostUsd advertised but unenforced; holding docs until #839 lands.
  • Reserved GenerateOpts (toolArgValidation strict/lenient, maxCostUsd, conversationId) — called out in a short "Reserved options" note as non-functional in 5.1 so TypeScript autocomplete doesn't mislead.

Where to look

  • Facts were verified against the implementation (signatures from resources/models/types.ts, defaults from agentLoop.ts/analyticsTable.ts/backend components, HNSW behavior from resources/indexes/HierarchicalNavigableSmallWorld.ts). A follow-up docs-accuracy audit is planned; flagging two spots reviewers should sanity-check: the per-query ef example (plumbed through the sort descriptor; no existing unit test exercises it end-to-end) and the Azure/Gemini OpenAI-compatibility claims (bearer-auth-only constraint stated).
  • npm run build passes (links/MDX verified); format:write applied.

Generated by Claude (Fable 5).


🤖 Generated with Claude Code

New reference section (models/): overview + configuration, embed/generate/
generateStream API, tool calling and the toolMode 'auto' agent loop,
the four bundled backends (ollama, openai, anthropic, bedrock), and
model-call analytics. Adds the @embed directive and 5.1 vector-indexing
additions (int8 quantization, per-query ef, auto-scaled search ef,
dotProduct distance) to the schema reference, corrects the HNSW search
parameter name (efConstructionSearch, previously documented as
efSearchConstruction), and starts the 5.1 release notes.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
@gemini-code-assist

Copy link
Copy Markdown

Warning

You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!

heskew and others added 4 commits June 9, 2026 17:48
error_code can also be pending_unsupported (Models.ts pending-status
path is reachable); Bedrock family dispatch also handles mistral.,
and unknown prefixes are rejected.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Config-file (Joi) validation of the models block is boot-blocking for
structurally invalid entries; only registration-time errors are
warn-and-skip. Also note ${VAR} indirection is string-fields-only.
Surfaced by the models-subsystem deep review.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Only credential fields reject unresolved ${VAR} placeholders at
startup; host/model/region carry them into requests literally.
Surfaced by the models-subsystem deep review.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Current reference docs are served at /reference/v5/ (versions config
maps current -> path 'v5'); the PR preview's broken-link check caught
the unversioned /reference/ links.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
@github-actions

Copy link
Copy Markdown

🚀 Preview Deployment

Your preview deployment is ready!

🔗 Preview URL: https://preview.harper-documentation.harperfabric.com/pr-523

This preview will update automatically when you push new commits.

@github-actions github-actions Bot temporarily deployed to pr-523 June 10, 2026 03:34 Inactive
VersionBadge tagging for minor-version availability (new vs changed),
version derivation from the core release, release-notes-per-minor
placement, versioned /reference/v5/ link paths from other content
trees, and feature/docs PR cross-linking. Gives the engineering
guidelines a single place to point at for docs mechanics.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
@github-actions github-actions Bot temporarily deployed to pr-523 June 10, 2026 03:53 Inactive
@github-actions

Copy link
Copy Markdown

🚀 Preview Deployment

Your preview deployment is ready!

🔗 Preview URL: https://preview.harper-documentation.harperfabric.com/pr-523

This preview will update automatically when you push new commits.

@heskew heskew requested review from Ethan-Arrowood and kriszyp June 10, 2026 20:12
@heskew heskew marked this pull request as ready for review June 10, 2026 20:12
@heskew heskew requested a review from a team as a code owner June 10, 2026 20:12
@gemini-code-assist

Copy link
Copy Markdown

Warning

You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!

type Document @table {
id: Long @primaryKey
text: String
embedding: [Float] @embed(source: "text", model: "default")

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is there an equivalent to automatically embed on the search side of the equation? When we Document.search({. I'm not seeing an equivalent in the docs, but maybe I missed it.

Copy link
Copy Markdown
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sorry Dawson. Missed this before merging. No, there's not but the need is now tracked at HarperFast/harper#1277. Great callout.

Release notes will be authored separately (Kris owns them); this PR
stays scoped to the reference documentation.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
@github-actions github-actions Bot temporarily deployed to pr-523 June 11, 2026 21:39 Inactive
@github-actions

Copy link
Copy Markdown

🚀 Preview Deployment

Your preview deployment is ready!

🔗 Preview URL: https://preview.harper-documentation.harperfabric.com/pr-523

This preview will update automatically when you push new commits.

@heskew heskew merged commit dcd5dc2 into main Jun 11, 2026
7 checks passed
@heskew heskew deleted the docs/models-5.1 branch June 11, 2026 22:36
@github-actions

Copy link
Copy Markdown

🧹 Preview Cleanup

The preview deployment for this PR has been removed.

kriszyp added a commit that referenced this pull request Jun 13, 2026
* docs(v5.1): release notes, deployment tracking ops, deploy_component updates

- Add 5.1.md release notes covering: models/AI, @embed directive, MCP server,
  deployment tracking, HNSW int8 quantization, and replication improvements
- Update deploy_component docs: urlPath, install_allow_scripts params, deployment_id response
- Document new deployment operations: list_deployments, get_deployment,
  get_deployment_payload, delete_deployment_payload
- Document hdb_deployment record schema (fields, phases, peer_results)

Note: models/AI detail, MCP reference, and HNSW quantization have separate PRs
(#523, #507/#516, #508) — this PR adds the release notes overview and the
deployment tracking operations which had no coverage.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* style: run prettier on changed files

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix: remove cross-plugin MCP link that breaks Docusaurus build

The release-notes and reference doc plugins are separate; relative .md
links between them resolve incorrectly. Removing until PR #507 (MCP
reference section) merges and can be linked with an absolute path.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* docs(5.1): expand release notes — middleware/routing, caching, LOCAL_ONLY, HARPER_CONFIG, RocksDB, migrateOnStart, upgrade improvements

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants