kungfu-eric

Update langchain imports

1

Langchain has moved their components around

Server hang after ~400 long context requests mixtral or llama3 ollama 0.1.32

2

### What is the issue? Hangs after about 400 long context requests on mixtral and same with llama3 ``` ollama --version ollama version is 0.1.32 ``` This is on AMD...

### What is the issue? Using mixtral default 2048 ctx splits memory across 2x GPUs ~12 GBs each. When extending context to 12k, it dumps all mem on one GPU...