Vijaylaxmi Lendale

Hello @illusion77, Thank you for highlighting the availability of the streaming feature in the OpenAI Assistants API. This is a valuable addition and could enhance real-time interactions significantly. To proceed,...

Hi @lambda7xx The similar timings between async and sync methods are expected in CPU-bound tasks like yours, where async doesn't inherently speed up the process but allows for concurrent IO...

Hi @singerbj, this integration sounds very interesting! I'd be keen to help explore the feasibility and contribute to adding web-llm as an LLM option. Here's my initial approach: * **Compatibility...

can I work on this too?

Hi @homanp, I'm interested in taking a look at implementing email and phone numbers for calling agents. Here are some initial questions and thoughts: **Functionality** * **Email and Phone Generation:**...

Hi @liferadioat, I'd be interested in taking on this issue. I have experience working with .env files and making adjustments for API configurations. Do you have a specific structure in...

Hi @homanp, I'm interested in working on adding support for the PRO RAG Pipeline. Before starting, I'd like to gather more details: * **Specifics of the PRO RAG Pipeline:** Could...