-
I encountered some obstacles in actual development, such as wanting to notify users of the information about function call execution to let them know the data source, or wanting to notify users of the…
-
### Motivation.
Speculative Decoding is a crucial feature for reducing latency, currently supported by vLLM (credit to @cadedaniel !). However, when deploying Speculative Decoding in real online LL…
-
To enhance our project and the next diagram artifact version we added for v1.1, I think we should include information about traditional REST API and websocket architecture into the diagram and how thi…
-
**Describe the bug**
Using GPT4 model version 2024-05-13 on Azure (Sweden) with Semantic Kernel, Python.
I have noticed that sometimes it seems that GPT4o (os is it in SK?) gets the toolname wrong, …
-
I run 01-local demo for server and rtvi-web-demo for client
2024-08-26 17:13:11.097 | INFO | pipecat.transports.services.daily:on_participant_joined:468 - Participant joined a3b53542-cc5e-4…
-
### Ticket Contents
## Goal
Create a bot capable of answering user questions based on RAG framework using government data extracted from PDFs.
## Description
The project aims to develop a chatbo…
-
Subscribe to this issue and stay notified about new [daily trending repos in Python](https://github.com/trending/python?since=daily)!
-
Torchtune is a great project that explaining such a complex fine-tuning process in such an elegant way.
I would think having a simple benchmark againt other popular LLM fine-tuning approach is valu…
-
Hello friends!🌎
We're excited to host an Unconference at this year's Kubernetes Contributor Summit in Salt Lake City, Utah! Your input is crucial in making this event a success, so we'd love to hea…
-
[ ] I checked the [documentation](https://docs.ragas.io/) and related resources and couldn't find an answer to my question.
**Your Question**
I wrote this code and I get the error:
The api_key …