-
### Bug Description
I was using LlamaIndex with the OpenAI API for a while and question answering worked great. Since I switched to Azure, I'm seeing all kinds of prompt template fragments and rela…
-
-
Compared to GPTQ, [AWQ](https://github.com/mit-han-lab/llm-awq) is more accurate and has much better inference performance.
Benchmark: https://github.com/lm-sys/FastChat/blob/main/docs/awq.md#bench…
-
I am running LangChain with Next.js 13 in a Docker container.
While I am able to ingest PDFs from the project root outside Docker but into ChromaDB running in another Docker container, the whole proc…
-
Hello,
https://github.com/JayZeeDesign/microsoft-autogen-experiments/blob/main/content_agent.py
I got a few instances of infinite loops running the above with gpt4.
- An agent, if I recall co…
-
### System Info
(h2ogpt) jon@pseudotensor:~/h2ogpt$ pip freeze | grep langchain
langchain==0.0.235
langchainplus-sdk==0.0.20
Python 3.10
(h2ogpt) jon@pseudotensor:~/h2ogpt$ lsb_release -a
No…
-
**Is your feature request related to a problem? Please describe.**
Currently it is hard to utilize the APIs for many AI services (e.g. Bard, Bing, Claude) in developed projects, especially via their …
-
# Bug report
- [ X] I confirm this is a bug with Supabase, not with my own application.
- [ X] I confirm I have searched the [Docs](https://docs.supabase.com), GitHub [Discussions](https://gi…
-
version: 0.0.106
OpenAI seems to no longer support max_retries.
https://platform.openai.com/docs/api-reference/completions/create?lang=python
-
Target date: end november 2023
wanted:
- packages:
- [x] Torch-2.1.1
- [x] numpy-1.26.2, with Array API v2022.12 support
- infrastructure :
- [x] a beta and partial Python-3.12 (mi…