* refactor(storage): delete agfs http mode client
* refactor(storage): refactor protocol to support diff return type
* refactor(storage): refactor code format from lint
* docs: fix code-doc inconsistencies in English documentation
- Fix default server host: docs claimed 0.0.0.0 but code defaults to 127.0.0.1
- Fix GLOBAL_SEARCH_TOPK: docs said 3 but code uses 10
- Fix VLM model name: docs had doubao-seed-2-0-code-preview-260215, code uses doubao-seed-2-0-pro-260215
- Fix metrics file reference: pointed to nonexistent .vscode/.workdir/metric/METRIC_res.md
- Fix build prerequisite: Go replaced by Rust/Cargo (no .go files remain in repo)
- Fix embedding provider list: README listed 7 providers, code supports 13
- Fix CLI command inconsistency: two ov commands in sessions doc should be openviking
- Add missing session archive endpoint to API overview table
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs: revert ov→openviking CLI rename in sessions doc
Both `ov` and `openviking` are registered entry points for the same
Rust CLI binary (pyproject.toml). The short `ov` alias is intentional
and valid — reverting the previous rename.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs: sync same fixes to Chinese docs, README_CN, and README_JA
Apply the same consistency fixes from the English docs to:
- docs/zh/ (Chinese documentation)
- README_CN.md (Chinese README)
- README_JA.md (Japanese README)
Changes mirror the English fixes: server host default, GLOBAL_SEARCH_TOPK,
VLM model name, build prerequisites (Go→Rust), embedding provider list,
metrics file reference, and missing session archive endpoint.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Align docs, examples, the setup wizard, and telemetry tests with the
current Doubao multimodal embedding model so generated configs keep
referencing the supported default consistently.
- Add 'ollama' as a supported embedding provider
- Ollama runs locally via OpenAI-compatible API, no API key required
- Allow OpenAI provider to work without api_key when api_base is set
(supports local OpenAI-compatible servers like vLLM, LocalAI)
- Add configuration example and tests for Ollama provider
This enables fully local embedding deployment without cloud API keys.
* feat: define a system path for future deployment
* feat: define a system path for future deployment
* fix: golang downgrade to 1.19
* fix: golang downgrade to 1.19, and change doc
* docs: change model recommendation
* fix: golang downgrade to 1.19, and change doc
* fix: mv test files
* fix: loguru
---------
Co-authored-by: openviking <openviking@example.com>
* feat: add code parser, not tested
* feat: rename CodeParser to CodeRepositoryParser
* fix: code parser data uploading
* fix: code parser data uploading
* fix: code parsing
* feat: protect binary files to summary and vectorize
* Update viking_fs.py
* feat: use a default dir ~/.openviking to store configuration
Qin Haojie