Juan Jose Alban Ortiz

Results 15 comments of Juan Jose Alban Ortiz

When called from a development installation (pip install -e ~/jaydebeapi) the error stops happening and it's no longer reproducible.

using the GPT-4 API, it seems the projects relies on CPU usage to make vectorization ![image](https://github.com/reorproject/reor/assets/5524219/362e5f73-3b05-45e4-b31d-2f783850eda7) while ignores entirely the GPU for the analysis and vectorization. IDK if there is...

Indeed I don't have cuss installed. Do you think there is a way to make easier to final users this installation? El 26 feb 2024 8:24 a. m., Daniel Houston...

https://github.com/run-llama/llama_parse/blob/main/examples/demo_advanced_astradb.ipynb

https://blog.llamaindex.ai/introducing-llamacloud-and-llamaparse-af8cedf9006b

Yes El 24 feb 2024 7:07 a. m., samlhuillier ***@***.***> escribió: Thank you for opening this @ElCuboNegro Yes I agree that this is definitely something that would be super good...

Do you have any documentation about how are you doing the RAG? With the aim of implementing something like this https://ai.plainenglish.io/unlocking-whole-dataset-reasoning-why-knowledge-graphs-are-the-future-of-ai-systems-fc8726367808

perhaps you can use two instances of the AI_FN functions: the first one should take the user request and transform it into the function signature and docstring (in my experience,...

True, but you can safeward through non-ai static analysis