ask_llm
| Crates.io | ask_llm |
| lib.rs | ask_llm |
| version | 0.1.4 |
| created_at | 2025-03-14 19:14:01.741681+00 |
| updated_at | 2025-06-29 23:20:52.702105+00 |
| description | make a request to whatever llm is the best these days, without hardcoding model/provider |
| homepage | https://github.com/valeratrades/ask_llm |
| repository | https://github.com/valeratrades/ask_llm |
| max_upload_size | |
| id | 1592623 |
| size | 105,399 |
Valera (valeratrades)
documentation
README
ask_llm
Layer for llm requests, generic over models and providers
Usage
Lib
Provides 2 simple primitives:
oneshot and conversation functions, which follow standard logic for llm interactions, that most providers share.
Then the model is automatically chosen based on whether we care about cost/speed/quality. Currently this is expressed by choosing Model::{Fast/Medium/Slow}, from which we pick a model as hardcoded in current implementation.
When used as a lib, import with
ask_llm = { version = "*", default-features = false }
as clap would be brought otherwise, as it is necessary for cli part to function.
Cli
Wraps the lib with clap. Uses oneshot by default, if needing conversation - read/write it from/to json files.
Semver
Note that due to specifics of implementation, minor version bumps can change effective behavior by changing what model processes the request. Only boundary API changes will be marked with major versions.
This repository follows my best practices and Tiger Style (except "proper capitalization for acronyms": (VsrState, not VSRState) and formatting).
License
Licensed under Blue Oak 1.0.0Unless you explicitly state otherwise, any contribution intentionally submitted for inclusion in this crate by you, as defined in the Apache-2.0 license, shall be licensed as above, without any additional terms or conditions.