mirror of
https://github.com/volcengine/OpenViking.git
synced 2026-09-30 09:17:51 +08:00
python-sdk@0.1.9
5
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
|
9eac8a6d3d |
feat(sdk): sync go/ts/python SDKs with server find/search, recall, an… (#3737)
* feat(sdk): sync go/ts/python SDKs with server find/search, recall, and admin changes Server-side changes recently landed that the language SDKs had drifted from: - find/search results now return `tags` and no longer return `category`/`match_reason`/`relations`/`overview` (#3730). Go's strict struct was the only one broken; update MatchedContext accordingly. - new admin endpoints for agent-evolution and per-account settings (#3695). - public `search/recall` endpoint was missing from all SDKs. Changes: - python: add `level`/`since`/`until`/`time_field` to find/search; add an `extra` escape hatch to find/search/add_resource/write/batch_write so new server fields can be passed without an SDK bump (only forwarded when set, preserving `level=0`); add `recall` and the four admin methods. - go: fix MatchedContext (add Tags, drop removed fields), add Recall and the four admin methods. - typescript: type MatchedContext/FindResult, add RecallOptions, add `recall` and the four admin methods. Co-authored-by: TRAE CLI <noreply@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> feat(sdk): unify options APIs and sync latest server interfaces - migrate complex Python SDK calls to typed options dictionaries - add dedicated context search and consistent extra-field handling - align Go and TypeScript options with omission-aware serialization - support session config, event tags, Agent Evolution date filters, OpenViking Assets, batch write, downloads, and create_parent - refresh SDK tests and examples across all three languages Co-authored-by: TRAE CLI <noreply@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> fix(sdk): address options API review findings - fix Go session extra merging and Python message precedence - adapt LangChain calls to the Python options API - migrate repository examples, tests, and documentation Co-authored-by: TRAE CLI <noreply@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> fix(sdk): complete options migration and message parity - migrate remaining Python SDK benchmarks to options dictionaries - normalize empty parts consistently for single and batch messages - add regression guards for repository SDK call sites Co-authored-by: TRAE CLI <noreply@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> fix(sdk): align reindex options after main rebase - preserve reindex tags in Python typed options - add reindex extra support for Go and TypeScript - reject official fields passed through extra across SDKs Co-authored-by: TRAE CLI <noreply@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> feat(sdk): support legacy keyword options Co-authored-by: TRAE CLI <noreply@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> docs(sdk): use explicit Python SDK arguments Co-authored-by: TRAE CLI <noreply@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> fix(sdk): support set tags extra options Co-authored-by: TRAE CLI <noreply@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> fix(sdk): expose Go add resource options Expose AddType and ProcessingMode through Go AddResourceOptions and serialize them to the resources API. Add a regression test covering the resulting request payload. Co-authored-by: TRAE CLI <noreply@bytedance.com> Co-authored-by: TRAE CLI <traecli@bytedance.com> feat(sdk): flatten core Python client options Co-authored-by: TRAE CLI <traecli@bytedance.com> docs(sdk): align Python examples with flattened options Co-authored-by: TRAE CLI <traecli@bytedance.com> fix(sdk): preserve core API compatibility Co-authored-by: TRAE CLI <traecli@bytedance.com> refactor(python-sdk): move resource hints to options Co-authored-by: TRAE CLI <traecli@bytedance.com> fix(sdk): align resource option callers Co-authored-by: TRAE CLI <traecli@bytedance.com> test(sdk): cover recursive reindex forwarding Co-authored-by: TRAE CLI <traecli@bytedance.com> fix(sdk): preserve Go options compatibility Co-authored-by: TRAE CLI <traecli@bytedance.com> feat(python-sdk): expose message peer id Co-authored-by: TRAE CLI <traecli@bytedance.com> test(python-sdk): consolidate options coverage Co-authored-by: TRAE CLI <traecli@bytedance.com> feat(python-sdk): add parts and flatten image search Co-authored-by: TRAE CLI <traecli@bytedance.com> * docs(sdk): align Python call examples Co-authored-by: TRAE CLI <traecli@bytedance.com> --------- Co-authored-by: TRAE CLI <traecli@bytedance.com> Co-authored-by: Qin Haojie <qinhaojie.exe@bytedance.com> |
||
|
Qin Haojie
|
7abd6ab249 |
refactor(client): remove Python embedded mode (#3712)
* refactor(client): remove Python embedded mode Consolidate Python consumers on the HTTP SDK while keeping shared server and storage capabilities unchanged. * refactor(client): remove obsolete embedded leftovers |
||
|
MaojiaSheng
|
db7319f4a2 |
refactor: to accelerate cli launch speed, refactor openviking_cli dir (#150)
* fix: remove await asyncio and call agfs directly * feat: mv cli out of openviking * refactor: mv cli out of openviking * refactor: mv cli out of openviking |
||
|
Zayn Jarvis
|
a5cf17b646 |
feat: in chatmem example, add /time and /add_resource command (#77)
* docs: add design for /time and /add_resource commands Design document for two new chatmem features: - /time command: display performance timing breakdown - /add_resource command: add documents during chat sessions Includes architecture, detailed implementation plan, and UX examples. * feat: add resource manager shared module - create_client(): initialize OpenViking client - add_resource(): add files/URLs to database with progress - Extracted from add.py for reusability * refactor: simplify add.py using resource manager - Use shared create_client() and add_resource() - Reduces duplication, maintains same CLI behavior - ~80 lines reduced to ~40 lines * test: document manual testing results * docs: document /time and /add_resource commands in README * docs: add implementation plan for /time and /add_resource * feat: add timing instrumentation to Recipe.query() - Track search_time, llm_time, total_time with perf_counter - Return timing data in result dict under 'timings' key - No breaking changes to existing API * feat: add /time command handler - Parse /time <question> syntax - Extract question and call ask_question with show_timing=True - Show usage help if no question provided * feat: add timing display to ask_question - Accept show_timing parameter (default False) - Display timing panel with search/LLM/total times - Format times as seconds with 3 decimal places * docs: update help text with /time and /add_resource commands * feat: add /add_resource command handler - Parse /add_resource <path> syntax - Expand user paths (~/ notation) - Use shared resource_manager module - Show spinner during processing - Immediate feedback when complete * docs: implementation complete summary * feat: support add resource and time command * roll: some unexpected changes * roll: some unexpected changes * chore: remove chat since dups * chore: help msg update * feat: update README for chatmem * feat: update diff lint * fix: use original changed files * fix: filter py files * fix: remove deleted file |
||
|
Liu Zhiheng
|
74ea0f95f6 |
feat: chat & chat w/ mem examples (#39)
* docs(chat): add OpenViking chat application design - REPL-style chat interface with rich terminal UI - Client-server architecture (port 8391) - Automatic RAG for context-aware responses - Auto-commit sessions on exit - Modular structure for multi-agent development chore: add .worktrees to gitignore docs: add chat examples design document - Phase 1: Multi-turn chat interface (no persistence) - Phase 2: Chat with session memory using OpenViking Session API - Detailed architecture, implementation plan, and testing strategy * docs(chat): add detailed implementation plan for Phase 1 - 9 bite-sized tasks with exact code - TDD approach with manual testing - Frequent commits after each task - Complete REPL implementation - Handoff document for Phase 2 * feat(chat): create directory structure with symlinks to query example * fix(chat): remove broken data symlink - data directory is runtime artifact * feat(chat): implement ChatSession for in-memory history * docs: add agent handoff document for continuing implementation - Complete task specifications for Tasks 3-9 - Subagent-driven development instructions - Current status summary (Tasks 1-2 complete) - Code examples and test procedures - Entry point for next agent * feat(chat): add ChatREPL class skeleton with signal handling * feat(chat): implement welcome banner, help, and command handling * feat(chat): implement question/answer display with sources * feat(chat): implement main REPL loop with readline support * fix(chat): chat func declaration * feat(chat): support multi-run chat and tested * fix(chat): interupt, remove debug log, move doc * docs(chatmem): add Phase 2 implementation plan - 11 detailed tasks with exact code - Session API integration steps - Message recording and commit procedures - Testing and verification checklist - Comprehensive documentation plan - Success criteria for completion * feat(chatmem): create Phase 2 directory from chat example - Copy examples/chat/ to examples/chatmem/ - Update pyproject.toml name to chatmem - Base for Session API integration * refactor(chatmem): remove ChatSession, add Session API imports - Remove in-memory ChatSession class - Add OpenViking Session API imports - Prepare for Session integration * feat(chatmem): initialize OpenViking client and Session - Add session_id parameter to ChatREPL.__init - Initialize SyncOpenViking client in run() - Create/load Session with session_id - Display session info if continuing from previous - Keep Recipe initialization * feat(chatmem): record user and assistant messages to Session - Add user message before query - Add assistant message after response - Remove old in-memory add_turn() call - Messages now persist in Session * feat(chatmem): commit session on exit with memory extraction - Update _signal_handler to commit on Ctrl-C - Update run() finally block to commit on normal exit - Display memory extraction count - Handle commit errors gracefully - Session persists to data/session/ * feat(chatmem): add --session-id command line argument - Add --session-id flag to specify session - Default: chat-interactive - Update help text to mention persistent memory - Pass session_id to ChatREPL * docs(chatmem): add comprehensive README with memory features - Document session persistence behavior - Explain memory extraction process - Show session management examples - Compare with examples/chat/ - Add troubleshooting section - Include architecture diagrams * docs(chatmem): add detailed comparison with chat example - Side-by-side feature comparison - Use case recommendations - Code differences - Storage structure comparison - Performance considerations - Migration path examples * test(chatmem): add comprehensive test results - Session creation/loading verified - Message recording tested - Memory extraction confirmed - Multiple sessions working - Error handling tested - All commands functional * feat(chatmem): Phase 2 complete - persistent memory implementation Complete Features: - Session persistence using OpenViking Session API - Automatic message recording (user + assistant) - Session commit on exit with memory extraction - Previous session loading on startup - Multiple independent sessions (--session-id) - Comprehensive documentation and testing Architecture: - OpenViking SyncClient for storage - Session API for message management - Memory extraction on commit - Session storage in data/session/ Testing: - All functionality verified - Multiple sessions tested - Error handling confirmed - Memory extraction working Ready for production use. * fix(chatmem): session API * fix(chatmem): retrieve memory from FindResult * feat(chatmem): aggregate chatmem docs * refactor: replace symlink with common pkg |