v0.3.0 - Claude, Obsidian, MCP & Clean

What's New

Features

• Anthropic Claude Provider (#38): Native support for Claude models (claude-opus-4-8, claude-sonnet-4-6, claude-haiku-4-5). Use create_client("anthropic", ...) or llm="anthropic". Requires pip install 'hyperextract[anthropic]' and an OpenAI-compatible embedder.
• Obsidian Vault Export (#37): Turn any knowledge graph into an Obsidian vault with Markdown notes linked by [[wikilinks]]. CLI: he export obsidian <ka_path> -o <vault>.
• MCP Server (#40): Expose knowledge abstracts to MCP-capable assistants (Claude Desktop, IDE agents) via he-mcp. Tools: list_templates, info, search, ask (RAG), export_obsidian. Requires pip install 'hyperextract[mcp]'.
• he clean Command (#39): Remove a KA's vector index or the entire knowledge abstract with confirmation guards.
• README Refresh: New Trendshift trending badge, centered for-the-badge shields, and a "What's New / 最新动态" section.

Fixes

• Multi-chunk Embedding Mean (#36): Use true mean when averaging multi-chunk embeddings for better long-document quality.
• Embedding Batch Size Cap (#35): Cap embedding batch size for OpenAI-compatible providers to avoid provider limits.
• LLM Merge Strategies (#41): Fix silent None resolution for multi-word llm_* merge strategies (llm_prefer_incoming, llm_prefer_existing, llm_custom_rule).
• Batch None Handling (#30): Gracefully handle None results from batch() when LLM extraction fails.

Dependencies

• langchain-anthropic>=0.3.0 (optional extra hyperextract[anthropic])
• mcp>=1.2.0 (optional extra hyperextract[mcp])

Resolved Issues

• #38 Anthropic provider support
• #37 Obsidian export
• #40 MCP server
• #39 he clean command
• #36 / #35 Embedding reliability improvements
• #41 Template merge strategy fix
• #30 / #25 / #27 Batch None handling

Notes

• All new LLM/transport integrations are optional extras; the core package remains lightweight.
• Existing OpenAI, Bailian, and vLLM provider paths are unchanged.

v0.2.0 - Unified Provider System

What's New

Features

• Unified Provider System (#26): 统一 `create_client()` 接口，支持字符串简写
  • OpenAI (`create_client("openai", api_key=...)`)
  • 阿里云百炼 (`create_client("bailian", api_key=...)`)
  • 本地 vLLM (`create_client(llm="vllm:Qwen3.5-9B@http://localhost:8000/v1\", ...)`)
• Debug Logging: LLM chunk 输入/结果日志，知识提取管道日志
• CLI Logging: 通过 `HYPER_EXTRACT_LOG_LEVEL` 环境变量控制日志级别

Fixes

• OpenAI-compatible Embeddings (#22): 修复 Ollama 等本地模型的 embeddings 支持
• CLI Log Order: 修复 ontosight 覆盖日志级别的问题
• CI Tests: 修复无 OPENAI_API_KEY 环境下的测试失败

Dependencies

• `ontosight` >=0.1.8 (可视化引擎升级)
• `semhash` >=0.4.1
• `structlog` >=25.5.0

Resolved Issues

• #26 Provider 系统统一
• #22 Ollama embedding 修复
• #21 国内模型支持（百炼、vLLM）
• #24 Qwen 模型使用指南（百炼渠道）

v0.1.2 - CLI Bug Fix Release

What's Changed

🐛 Bug Fixes

• Fixed CLI command error caused by incorrect function reference (load_kb_metadata → load_ka_metadata) in get_template_from_ka

📦 Maintenance

• Updated version to 0.1.2
• Updated documentation version references

📋 Dependencies

• Bump actions/checkout from 4 to 6
• Bump actions/setup-python from 5 to 6
• Bump astral-sh/setup-uv from 5 to 7
• Bump actions/upload-artifact from 4 to 7

Bump version to 0.1.1

What's Changed

• add cog_rag and hypergraph_rag by @haoohu in #1
• update cog-rag by @haoohu in #2
• feat: implement 22 finance domain templates. SEC Filings / Equity Research Reports / Prospectuses IPO Filings / Earnings Call Transcripts / Financial News & Market Commentary by @yuxizhe in #4
• feat(tests): add finance test documents matching all 24 finance templates by @yuxizhe in #5
• feat(industry): 新增工业领域知识图谱模板及测试样例 by @Rizrock in #6
• undate cog_rag and graph_rag by @haoohu in #8
• 精简、修改general模版，添加测试文本 by @Rizrock in #10

New Contributors

• @haoohu made their first contribution in #1
• @yuxizhe made their first contribution in #4
• @Rizrock made their first contribution in #6

Full Changelog: https://github.com/yifanfeng97/Hyper-Extract/commits/v0.1.1