gptme
gptme copied to clipboard
ErikBjare
A CLI and web UI to interact with LLMs in a Chat-style interface, with code execution capabilities and other tools.
Source files could be: - your projects folder (with code) - your notes (in plaintext) - previously web-retrieved documents Adding this feature would return gptme to its roots: an agent...
The package currently seems to depend on `readline`, which is unavailable for Windows.
Not sure what causes this. Seems to happen kind of randomly. Maybe this is what caused sudden exits before? But we handle the exceptions since https://github.com/ErikBjare/gptme/commit/becab4d69a85f2c769f610f6200de44c7fabdcaf Seems to happen after...
When working on gpt-engineer I notice one benefit which is that the context per request is a lot smaller, because we don't keep sending past conversation history. This also saves...
gptme sometimes outputs code blocks that are just examples, and thus may not be runnable. It would be nice if we could distinguish between the two, avoiding issues like in...
Hi @ErikBjare, Noticed you're calling GPT-4 + local models via llama cpp. Wanted to see if we could help with LiteLLM (https://github.com/BerriAI/litellm). Replaced the openai chatcompletions call with litellm.completion. This...
Since I'm working on both projects, it would be interesting to benchmark them on the same suite and compare results. Then potentially integrating gpt-engineer as a tool in gptme to...
I did some smaller benchmarks (more like tests, really) and would like to continue with this endeavor to evaluate capabilities and weak spots. Would also be interesting to test on...
User: /rename devopsx Renaming conversation (enter empty name to auto-generate) Traceback (most recent call last): File "/home/noah/.local/bin/gptme", line 8, in sys.exit(main()) ^^^^^^ File "/usr/lib/python3/dist-packages/click/core.py", line 1130, in __call__ return self.main(*args,...
- Include logs in PR message (as ``) - Logs are stored in `~/.local/share/gptme/logs//conversation.jsonl`