What embedding models are there with separation between different modes of content? I know E5-Large-V2 has that ("passage" vs "query"), and @nomic_ai have "search_query", "search_document", "clustering", "classification" https://
docs.nomic.ai/reference/endp
oints/nomic-embed-text
… Any other good examples?
CODE
-
Embedding Models with Content Mode Separation
By
–
-
Improving documentation and examples for function calling and JSON mode
By
–
Thanks everyone for the super valuable inputs! We’ll improve docs and add more examples for function calling and JSON mode. Please keep the feedback coming!
-
XLA Compiler and JAX Integration for Optimal Performance
By
–
The XLA compiler — and the fact that JAX was designed for XLA, making the two work really well together.
-
Discussion on LLM Code Execution Capabilities
By
–
Still waiting for code execution Quite easy to ask GPT to run and test its own creation. Even though Claude is slightly better, this is a big missing feature.
-
Challenges extracting table data from screenshot images
By
–
Definitely founded – I've had particular trouble getting table data out of screenshots of tables, but I don't trust it very much at all yet
-
Computer Science Short Memory: Historical Context in AI Research
By
–
Define 'we'. Also, I knew that CS types had short memories, but really? https://
dl.acm.org/doi/10.1145/34
42188.3445922
… -
Documentation Token Limit Testing and Performance Analysis
By
–
The documentation says it should cut off at 4096 tokens of output, but I haven't stress tested it myself yet
-
Text extraction challenges with token output limitations
By
–
The HTML thing was really just an illustrative example – the general challenge is that there are plenty of text extraction tasks where the output is > 8196 tokens so the more output tokens we can have the easier these things are to put into practice
-
Free OCR tool for PDFs and images with practical limitations
By
–
Yeah, I wrote about those limitations in my post https://
simonwillison.net/2024/Mar/30/oc
r-pdfs-images/
… It's not state-of-the-art, but it's aiming to be the most convenient possible (free) option for people who don't have anything better