eyurtsev/kor

• highabout#1

  Update the repository description to be more informative

  原因：

  当前

  LLM(😽)

  复制粘贴的修复

  复制

  Extract structured data from text using LLMs, especially those without native function calling or tool APIs.

  待办完成忽略
• highreadme#2

  Reposition the README's opening statement to highlight Kor's specific niche

  原因：

  当前

  # Kor
  
  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: Structured Data Extraction for LLMs (especially those without native tool calling)
  
  Kor is a Python library designed to help you reliably extract structured data from text using Large Language Models (LLMs). It is particularly well-suited for "old style" LLMs that do not have a chat interface or native tool calling APIs. Specify your desired output schema, provide examples, and Kor will generate prompts, interact with the LLM, and parse the output into structured data.

  待办完成忽略
• mediumtopics#3

  Enhance repository topics with more specific keywords

  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, structured-output, legacy-llm, no-function-calling, prompt-engineering

  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 can I extract structured data from unstructured text using large language models?

  你：未被推荐
  AI 推荐顺序：

  1. OpenAI GPT-4 / GPT-3.5 Turbo
  2. Anthropic Claude 3
  3. LlamaIndex (run-llama/llama_index)
  4. LangChain (langchain-ai/langchain)
  5. Mistral Large / Mixtral 8x7B
  6. Instructor (jxnl/instructor)
  7. Llama 3
  8. Falcon
  9. Zephyr

  AI 推荐了 9 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 tools provide structured output from LLMs lacking native function calling capabilities?

  你：未被推荐
  AI 推荐顺序：

  1. Guidance
  2. Instructor
  3. JSONFormer
  4. LMQL
  5. Outlines
  6. LiteLLM
  7. LangChain

  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？