-
The value of the history reducer plugin is to reduce the tokens required for the LLM to use extremely large chat histories. This implies we don't want to load the entire chat history into memory. Ther…
-
### Describe the bug
When using `bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0`, the interpreter crashes if two consecutive user messages are sent.
### Reproduce
▌ Model set to bedrock/anthro…
-
Aider version: 0.61.0
Python version: 3.10.12
Platform: Linux-6.8.0-47-generic-x86_64-with-glibc2.35
Python implementation: CPython
Virtual environment: No
OS: Linux 6.8.0-47-generic (64bit)
Git…
-
Hi, I really love your tool—I'm using it, and I think it's great. However, when I try to wrap it in Python, it's not as easy as I expected. While the documentation shows how to use coder.run() for sim…
-
Currently, OpenAI provides the functionality to return token usage through their Streaming Chat Completion API. However, this feature has not yet been incorporated into Azure OpenAI. Upon ex…
-
1. open a notebook and press ctrl+i to open the copilot inline chat
2. ask for a code change and then run `inlineChat.viewInChat` on the response (ctrl+down)
:bug: pylance crashes with bad request
…
-
### Issue
(summary provided by aider)
I would summarize the issue like this:
There appears to be a bug in the AI assistant's file visibility system. Even when explicitly asked multiple times wh…
-
### What is the issue?
~~ python test.py
import ollama
res=ollama.chat(model="qwen2.5:0.5b",stream=False,messages=[{"role": "user","content": "who are you"}],options={"temperature":0})
print(res)
…
-
Hi,
I am running some accuracy tests with quantized models. I run the following commands but it takes a long time to run a small test and apparently NVIDIA GPU is not utilized while its available:
…
-
### Search before asking
- [X] I had searched in the [issues](https://github.com/eosphoros-ai/DB-GPT/issues?q=is%3Aissue) and found no similar issues.
### Operating system information
Windows
###…