* 介紹頁 https://www.langchain.com/langsmith * 後台 https://smith.langchain.com/ * 文件 * https://python.langchain.com/docs/guides/langsmith/ * https://docs.smith.langchain.com/ * Langsmith 系列影片 https://www.youtube.com/playlist?list=PLfaIDFEXuae2CjNiTeqXG5r8n9rld9qQu * LangSmith in 10 Minutes https://www.youtube.com/watch?v=jx7xuHlfsEQ&list=PLfaIDFEXuae2CjNiTeqXG5r8n9rld9qQu&index=2&t=411s * Projects > Monitor * 任何 LLM calll 上面有個 Playground 可以帶入過去快速實驗 * Dataset 跑實驗看結果，可以 Compare 不同實驗結果 * 多選 Traces 可以加到 Annotation Queue 進行人工標注 * Hub * LangSmith Production Monitoring & Automations 影片系列 https://www.youtube.com/playlist?list=PLfaIDFEXuae0bYV1_60f0aiM0qI7e1zSf * [[LangSmith Evaluations 影片系列]] * cookbook * [ ] https://github.com/langchain-ai/langsmith-cookbook - [ ] OpenAI Fine-Tuning https://github.com/langchain-ai/langsmith-cookbook/blob/main/fine-tuning-examples/export-to-openai/fine-tuning-on-chat-runs.ipynb - [ ] hub https://blog.langchain.dev/langchain-prompt-hub/ * 微調 * https://blog.langchain.dev/testing-fine-tuned-open-source-models-in-langsmith/ * colab 範例 https://github.com/chatopensource/ai-cookbooks/blob/main/openai-fine-tuning-langsmith-cookbook.ipynb?ref=blog.langchain.dev