Sergio Moreno
Sergio Moreno
This should be the correct UI. The current quote differs a lot from other quotes from Medium, Linkedin or similar websites.
We're seeing this error too, running Redis in normal mode (Not cluster) and executing `await queue.close()` before returning our api request value. We connect to Redis with the connection object:...
Yes, will prepare a repro and ping you back
On 8.0.0@beta^3 still not fixed guys, just to add more information :) I know that is an issue of Prisma side, I put a +1 on their issue.
It's just a fastapi server, implement it as usual like you do on FastAPI.
No, we have it done and operative in production already. Even the reranker embedding for LlamaIndex too, using Infinity as backend; we've been lately a bit busy to reach a...
This our code guys, sorry I couldn't find time yet to publish a package on LlamaIndex but I share the code that we've been using already for 4 months and...
To use it, in our case we directly do: ```python from rag.embeddings.infinity import InfinityEmbeddings EMBED_MODEL = InfinityEmbeddings( model="jinaai/jina-embeddings-v2-base-es", ) ``` LlamaIndex service context: ```python def get_service_context( config: BaseConfig, prompt_schema: BasePromptSchema,...
> @semoal thx for sharing the code. Would you share the reranker class? Thanks again~ ```python import requests from typing import List, Optional from llama_index.core.callbacks import CBEventType, EventPayload from llama_index.core.postprocessor.types...
Changes looks quite good! Really impressed, is there any estimated ETA?