simonw llm issues - Githubissues

simonw / llm

Access large language models from the command-line

https://llm.datasette.io

Apache License 2.0

4.8k stars 266 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Fix windows bug where llm doesn't run <<llm chat>> on Windows issue #495

#646 sukhbinder opened 1 hour ago
1
Add support for Duckduckgo AI chat models (llama3, claude3, gpt4o, mixtral)?

#645 zoobab opened 1 day ago
0
Utility method for getting usage details from Response

#644 simonw closed 2 days ago
2
Python API documentation for Response objects

#643 simonw opened 2 days ago
0
Log input tokens, output tokens and token details

#642 simonw closed 2 days ago
4
Log async responses to the database when run using llm --async

#641 simonw closed 2 days ago
1
llm.get_models() and .get_async_models() documented functions

#640 simonw closed 1 day ago
1
Feature request: Copilot Chat support

#639 Uninen opened 3 days ago
0
WIP: Fragments

#638 simonw opened 4 days ago
2
Add `editor` command (and make it the default when no args provided)

#637 oeo opened 4 days ago
0
llm install llm-sentence-transformers results in error

#636 axel-at-drom opened 5 days ago
0
llm chat -m mistral-7b-instruct-v0 led to OSError: [Errno 9] Bad file descriptor

#635 raybellwaves opened 5 days ago
0
Enhancement Proposal: Track Head (for backtracking)

#634 FergusFettes opened 5 days ago
1
chat - coloring tokens by logprob

#633 mlaugharn opened 6 days ago
0
Replying to an async conversation does not work

#632 simonw closed 1 week ago
5
Add logprobs for openai chat models

#631 irthomasthomas closed 2 days ago
0
Add command-name settings for --help

#630 web-sst opened 1 week ago
4
docs: add llm-grok

#629 Hiepler closed 1 week ago
1
async support for embeddings

#628 simonw opened 1 week ago
0
register_embedding_models() missing from plugin-hooks docs page

#627 simonw opened 1 week ago
0
Plugins incorrectly loaded during test runs

#626 simonw closed 5 days ago
2
Report estimated cost / token usage in the end of response

#625 Joilence opened 1 week ago
1
Add guidance supports customized openai url and the key

#624 MonolithFoundation opened 1 week ago
0
`llm keys get name` command

#623 simonw closed 1 week ago
2
Update default model information to 4o-mini

#622 tnorthcutt closed 1 week ago
1
tiny typo on README.md

#621 jpita closed 1 week ago
1
Supporting composable prompts and templates

#620 mhalle opened 1 week ago
0
Should LLM be tightly coupled to SQLite?

#619 simonw opened 1 week ago
0
Keys in environment should precede static configuration

#618 kfet opened 2 weeks ago
0
Option for passing in longer context fragments, stored in a deduped table

#617 simonw opened 2 weeks ago
45
Run cog -r in PRs, use that to update logging.md with new tables

#616 simonw closed 2 weeks ago
0
Add attachments tables to schema documentation

#615 simonw closed 2 weeks ago
1
OpenAI token usage stored incorrectly

#614 simonw closed 2 weeks ago
1
llm.get_async_model(), llm.AsyncModel base class and OpenAI async models

#613 simonw closed 1 week ago
14
`llm models --options` should show supported attachment types, too

#612 simonw closed 2 weeks ago
2
Make it possible to send one or more attachments with no accompanying prompt

#611 simonw closed 2 weeks ago
5
Abstract out token usage numbers

#610 simonw closed 2 days ago
12
[FR] `--json`: Save metadata as JSON

#609 NightMachinery opened 2 weeks ago
0
Support `gpt-4o-audio-preview` for input (not output)

#608 NightMachinery closed 2 weeks ago
8
Tool usage research

#607 simonw opened 2 weeks ago
15
Chaining `llm chat` with stdin

#606 aud opened 2 weeks ago
3
Error: Completions.create() got an unexpected keyword argument 'stream_options'

#605 xezpeleta closed 2 weeks ago
0
Added comments and improved code readability

#604 AyhamJo7 opened 2 weeks ago
0
`audio/wave` `.wav` files not supported

#603 NightMachinery closed 2 weeks ago
11
Ability to configure attachment support for models in extra-openai-models.yaml

#602 NightMachinery opened 2 weeks ago
1
Allow passing of can_stream in openai_models.py

#600 cmungall closed 2 weeks ago
1
Allow setting can_stream in extra-openai-models.yaml to allow for o1 over proxy

#599 cmungall closed 2 weeks ago
1
`llm chat` errors on followup since 0.6

#601 yorickvP closed 2 weeks ago
5
Installation borked after trying to uninstall gpt4all

#598 ianconsolata opened 3 weeks ago
0
`llm chat` works fine for one followup prompt, then crashes accessing `Response.attachments` (with or without attachments present)

#597 maxwelljoslyn closed 2 weeks ago
4