llm
llm copied to clipboard
simonw
Access large language models from the command-line
This PR fixes the easier issues with #409, but does not completely resolve it. The `\n` vs `\r\n` is likely a red herring, as Python does a lot of newline...
> I'd like to fix those test failures, but I also want to ship a 0.13.1 release quickly. So I'm going to mark a bunch of tests as expected to...
This trick: https://til.simonwillison.net/pypi/pypi-releases-from-github
https://www.perplexity.ai/ https://api.perplexity.ai/chat/completions Perplexity is a popular AI service with its LLMs. Having it with llm as a plugin will add much value to the project. I tried to API into...
> I'm going with `llm collections show xxx` for consistency with `llm templates show xxx`. _Originally posted by @simonw in https://github.com/simonw/llm/issues/229#issuecomment-1712940173_
https://github.com/simonw/openai-to-sqlite/blob/361d98a7f260a1420e6e698481f298848b922253/README.md#saving-similarity-calculations-to-the-database This is the feature that can be used to save calculated similarity scores to the database. I use it to serve related TILs on my TILs site: https://til.simonwillison.net/llms/openai-embeddings-related-content ```bash...
Calling `llm embed` with the same content but different --store settings does not update the table
Just noticed this: ```bash paginate-json 'https://api.github.com/repos/simonw/llm/issues?state=all&filter=all' > issues.json cat issues.json | jq '[.[] | {id, title, body}]' | llm embed-multi llm-issues - ``` That worked and populated my `llm-issues` collection...
Ollama makes it easy to run models such as llama2 locally on macOS easily: https://ollama.ai/ The user runs a server on localhost, so the architecture of the plugin could likely...
Hi, I'm seeing the following error when using the default model, 3.5: `Error: This model's maximum context length is 4097 tokens. However, your messages resulted in 8285 tokens. Please reduce...
Streaming response doesn't work with Azure models. This can be fixed by handling the JSON chunks differently. There is an issue with AzureChatOpenAI Streaming first response chunk response["choices"][0] is causing...
