# WeKnora

> LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.

- **URL**: https://www.freshcrate.ai/projects/WeKnora
- **Author**: Tencent
- **Category**: Databases
- **Latest version**: `v0.6.1` (2026-06-05)
- **License**: NOASSERTION
- **Source**: https://github.com/Tencent/WeKnora
- **Homepage**: https://weknora.weixin.qq.com
- **Language**: Go
- **GitHub**: 13,971 stars, 1,669 forks
- **Registry**: github
- **Tags**: `agent`, `agentic`, `ai`, `chatbot`, `chatbots`, `embeddings`, `evaluation`, `generative-ai`, `go`

## Description

LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v0.6.1` | 2026-06-05 | High | ## What's Changed * perf(repository): exclude embedding field from Elasticsearch search r… by @majinding in https://github.com/Tencent/WeKnora/pull/1433 * fix(swagger): Fix some Swagger API endpoints returning 404 errors and regenerate the Swagger documentation by @ChenRussell in https://github.com/Tencent/WeKnora/pull/1436 * fix(repository): qualify tenant_id with table name to resolve ambiguous column reference by @ChenRussell in https://github.com/Tencent/WeKnora/pull/1435 * fix(frontend) |
| `v0.6.0` | 2026-05-21 | High | ## What's Changed * fix(compose): stop publishing docreader gRPC port to the host by @lyingbug in https://github.com/Tencent/WeKnora/pull/1308 * feat(frontend): show UI build version on system info page by @lyingbug in https://github.com/Tencent/WeKnora/pull/1313 * fix(org): searchable join bypasses invite code expiry by @tsukiga-kirei in https://github.com/Tencent/WeKnora/pull/1324 * fix(frontend): make rerank model optional in agent editor save by @guangyang1206 in https://github.com/Tence |
| `v0.5.2` | 2026-05-13 | High | ## What's Changed * chore: release v0.5.1 by @lyingbug in https://github.com/Tencent/WeKnora/pull/1104 * docs(readme): add Chrome Extension and ClawHub Skill badges by @lyingbug in https://github.com/Tencent/WeKnora/pull/1105 * fix(embedding): OpenAIEmbedder.doRequestWithRetry shadows err · retur… by @toy0116 in https://github.com/Tencent/WeKnora/pull/1116 * fix(chat): include history in model fallback by @Aphroq in https://github.com/Tencent/WeKnora/pull/1112 * fix(memory): dedupe episode |
| `v0.5.1` | 2026-04-30 | High | ## What's Changed * docs(readme): enhance layout for Agent Mode and Observability sections across multiple languages by @lyingbug in https://github.com/Tencent/WeKnora/pull/1047 * docs(readme): update tracing references from Jaeger to Langfuse across multiple languages by @lyingbug in https://github.com/Tencent/WeKnora/pull/1048 * feat(frontend): add LLM call timeout for agents by @lyingbug in https://github.com/Tencent/WeKnora/pull/1059 * fix(wiki): queue JSON handling and failed ingest ope |
| `v0.5.0` | 2026-04-27 | High | ## What's Changed * feat(repository): update keyword retrieval logic to use ParadeDB's matching operator by @lyingbug in https://github.com/Tencent/WeKnora/pull/977 * Fix system prompt not being used when flag is false by @utafrali in https://github.com/Tencent/WeKnora/pull/969 * fix: missing deep copy entity by @shanghai-Jerry in https://github.com/Tencent/WeKnora/pull/975 * fix: SQLite/Lite mode compatibility for FAQ import and chunk operations by @swim2sun in https://github.com/Tencent/We |
| `v0.4.0` | 2026-04-15 | High | ## What's Changed * fix: allow MINIO_ENDPOINT to be configured via environment variable by @voidkey in https://github.com/Tencent/WeKnora/pull/911 * fix: resolve tool name duplication in streaming tool calls by @tsukiga-kirei in https://github.com/Tencent/WeKnora/pull/914 * feat(agent): support customizable LLM call timeout by @tsukiga-kirei in https://github.com/Tencent/WeKnora/pull/916 * feat/connector notion by @voidkey in https://github.com/Tencent/WeKnora/pull/923 * feat: add VectorSto |
| `0.3.6-test` | 2026-04-11 | High | ## WeKnora Lite 0.3.6-test  ### Web CLI 版（命令行 / 服务器部署）  单二进制部署，零外部依赖（无需 Docker / PostgreSQL / Redis）。  ```bash # 1. 解压 tar xzf WeKnora-lite_0.3.6-test_<os>_<arch>.tar.gz cd WeKnora-lite_0.3.6-test_<os>_<arch>  # 2. 配置 cp .env.lite.example .env.lite # 编辑 .env.lite，至少确认 OLLAMA_BASE_URL 正确  # 3. 启动 Ollama（如尚未运行） ollama serve & ollama pull qwen2.5:7b ollama pull nomic-embed-text  # 4. 运行 set -a && source .env.lite && set +a ./WeKnora-lite # 访问 http://localhost:8080 ```  \| 文件 \| 平台 \| \|------\|------\| \| |
| `v0.3.6` | 2026-04-03 | High | ## What's Changed * perf(frontend): optimize login page rendering performance by @aahowe in https://github.com/Tencent/WeKnora/pull/824 * fix: update doc-content.vue renderer to marked v5+ token API by @ochanism in https://github.com/Tencent/WeKnora/pull/829 * refactor: use unified NVIDIA API for both chat and VLM by @manx98 in https://github.com/Tencent/WeKnora/pull/838 * feat: support parallel tool calling by @renezander030 in https://github.com/Tencent/WeKnora/pull/835 * feat: fix enable |
| `v0.3.6` | 2026-04-03 | Medium | ## What's Changed * perf(frontend): optimize login page rendering performance by @aahowe in https://github.com/Tencent/WeKnora/pull/824 * fix: update doc-content.vue renderer to marked v5+ token API by @ochanism in https://github.com/Tencent/WeKnora/pull/829 * refactor: use unified NVIDIA API for both chat and VLM by @manx98 in https://github.com/Tencent/WeKnora/pull/838 * feat: support parallel tool calling by @renezander030 in https://github.com/Tencent/WeKnora/pull/835 * feat: fix enable |
| `v0.3.6` | 2026-04-03 | Medium | ## What's Changed * perf(frontend): optimize login page rendering performance by @aahowe in https://github.com/Tencent/WeKnora/pull/824 * fix: update doc-content.vue renderer to marked v5+ token API by @ochanism in https://github.com/Tencent/WeKnora/pull/829 * refactor: use unified NVIDIA API for both chat and VLM by @manx98 in https://github.com/Tencent/WeKnora/pull/838 * feat: support parallel tool calling by @renezander030 in https://github.com/Tencent/WeKnora/pull/835 * feat: fix enable |

## Dependency audit

- **Score**: 0/100
- **Total deps**: 79
- **Resolved**: 0
- **Unresolved**: 79
- **License conflicts**: 0
- **Warnings**: 80
- **Scanned**: 2026-05-11

## Citation

- HTML: https://www.freshcrate.ai/projects/WeKnora
- Markdown: https://www.freshcrate.ai/projects/WeKnora.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/WeKnora/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._