eyurtsev/kor

• highabout#1

  Update repository description for clarity

  原因：

  当前

  LLM(😽)

  复制粘贴的修复

  复制

  Extract structured, type-safe data from unstructured text using LLMs, especially for models without native tool-calling APIs. Uses Pydantic for schema definition.

  待办完成忽略
• highreadme#2

  Reposition README's core value proposition

  原因：

  当前

  This is a half-baked prototype that 'helps' you extract structured data from text using LLMs 🧩. Specify the schema of what should be extracted and provide some examples. Kor will generate a prompt, send it to the specified LLM and parse out the output. You might even get results back. So yes – it’s just another wrapper on top of LLMs with its own flavor of abstractions. 😸

  复制粘贴的修复

  复制

  Kor is a robust library for **structured, type-safe data extraction from unstructured text using LLMs**, particularly effective for models that do not support native tool-calling APIs. Define your desired output schema using Pydantic, provide examples, and Kor handles prompt generation, LLM interaction, and output parsing, including re-asking for malformed responses. Integrated with LangChain, Kor excels in prompt-based/parsing extraction.

  待办完成忽略
• mediumtopics#3

  Add more specific topics

  原因：

  当前

  information-extraction, llm, natural-language, natural-language-processing, natural-language-understanding

  复制粘贴的修复

  复制

  information-extraction, llm, natural-language, natural-language-processing, natural-language-understanding, pydantic, structured-data, schema-extraction

  待办完成忽略

本次扫描解析到的品类 GEO 通道：google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• 品类问题

  How to extract structured information from unstructured text using large language models?

  你：未被推荐
  AI 推荐顺序：

  1. OpenAI API
  2. Anthropic Claude
  3. LlamaIndex (llamaindex/llamaindex)
  4. LangChain (langchain-ai/langchain)
  5. Hugging Face Transformers (huggingface/transformers)
  6. Google Cloud Vertex AI
  7. Amazon Bedrock

  AI 推荐了 7 个替代方案，却始终没点名 eyurtsev/kor。这就是要补上的差距。

  查看 AI 完整回答
• 品类问题

  What's a good library for schema-guided information extraction with LLMs?

  你：未被推荐
  AI 推荐顺序：

  1. Instructor
  2. LangChain
  3. LlamaIndex
  4. Guidance
  5. Marvin
  6. OpenAI Functions/Tools
  7. jsonformer

  AI 推荐了 7 个替代方案，却始终没点名 eyurtsev/kor。这就是要补上的差距。

  查看 AI 完整回答

• Metadata completeness

  pass

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of eyurtsev/kor?

  pass
  ✓AI 明确点名了 eyurtsev/kor

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

• If a team adopts eyurtsev/kor in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI 明确点名了 eyurtsev/kor

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

• In one sentence, what problem does the repo eyurtsev/kor solve, and who is the primary audience?

  pass
  ✓AI 明确点名了 eyurtsev/kor

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？