The third PR, submitted on 0910, primarily focuses on enabling interaction with language models via Langchain to deliver intelligent analysis results. It also addresses issues present in the previous PR.
Use the Ollama library to call the local large language model (Qwen2:7b) for analysis, send prompts containing Pod information, receive the analysis results, and display the results in Markdown format.
This PR resolves issues from the previous PR. To prevent multiple loads of the same data on a single page, the project utilizes React's Context to manage shared state. This approach allows multiple components to access and update the same data without the need for repeated requests.
The third PR, submitted on 0910, primarily focuses on enabling interaction with language models via Langchain to deliver intelligent analysis results. It also addresses issues present in the previous PR.
Ollamalibrary to call the local large language model (Qwen2:7b) for analysis, send prompts containing Pod information, receive the analysis results, and display the results in Markdown format.https://github.com/user-attachments/assets/bdbc20a4-0737-4141-81de-9eeb100aea41