xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-05 05:10:38 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs: clarify open-source models usage scope in model selection guide

Browse Source
This commit is contained in:
mrT23
2025-02-11 10:24:16 +02:00
parent 43fb8ff433
commit 77204faa51
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/docs/usage-guide/changing_a_model.md
View File

@ -51,7 +51,7 @@ api_base = "http://localhost:11434" # or whatever port you're running Ollama on
Commercial models such as GPT-4, Claude Sonnet, and Gemini have demonstrated robust capabilities in generating structured output for code analysis tasks with large input. In contrast, most open-source models currently available (as of January 2025) face challenges with these complex tasks.
Based on our testing, local open-source models are suitable for experimentation and learning purposes, but they are not suitable for production-level code analysis tasks.
Based on our testing, local open-source models are suitable for experimentation and learning purposes (mainly for the `ask` command), but they are not suitable for production-level code analysis tasks.
Hence, for production workflows and real-world usage, we recommend using commercial models.