feat: add v2 API#907
Closed
Teingi wants to merge 16 commits into
Closed
Conversation
Introduce /api/v2 endpoints that accept SDK configuration (database, LLM, embedding, etc.) in the request body instead of requiring server-side .env setup. v1 and v2 coexist - v1 routes are unchanged. Key design: business logic is extracted into shared _do_xxx() functions; v1 and v2 handlers are thin wrappers that differ only in how they obtain the MemoryService (singleton from app.state vs per-request construction from body.config). All v2 endpoints use POST so config can be carried in the JSON body.
…ules Extract shared business logic into api/shared/, move v2 handlers into api/v2/, and split v2 request models into models/request_v2.py so that each API version lives in its own directory with clear boundaries. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Downshift m0 from a fat app to a thin API layer by moving all intelligence algorithms into the powermem library: - SearchQueryOptimizer: pronoun resolution, compound query splitting, keyword extraction for semantic search (sync + async) - ExperienceManager: distill reusable task-solving experiences from conversations and merge similar experiences (sync + async) - ContentReviewer: dual-layer safety review with keyword blocklist (66 keywords) and LLM-based contextual review (sync + async) - ExperienceQueryRewriter: title-style query rewriting for experience search (sync + async) - strip_think_tags utility for reasoning model compatibility - Enhanced FACT_RETRIEVAL_PROMPT and UPDATE_MEMORY_PROMPT with sensitive content filtering rules and language preservation - Integrated search_with_rewrite() with parallel sub-query fan-out and deduplication in both Memory and AsyncMemory - All new modules exposed via public API on Memory/AsyncMemory classes Source: seekdb-m0 (always-merge experience logic, no skip) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
feat: port intelligence capabilities from m0 into powermem core See merge request oceanbase-ce-publish/powermem!62
…nal vector index - Enrich SEARCH_QUERY_REWRITE_PROMPT with complex query decomposition rules (parallel intents, comparisons, conditionals, time spans), synonym expansion, and more examples - Add "memory" field alongside "content" in StorageAdapter.get_memory() for API compatibility with m0 - Add create_vector_index parameter to OceanBase vector store to allow skipping vector index creation when not needed Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
feat: enhance search query prompt, add memory field to get, and optional vector index See merge request oceanbase-ce-publish/powermem!63
feat: complete v2 API parity See merge request oceanbase-ce-publish/powermem!64
|
rongfeng.frf seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account. You have signed the CLA already but the status is still pending? Let us recheck 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
2 participants
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.
No description provided.