mirror of
https://github.com/mii443/rust-genai.git
synced 2025-08-22 16:25:27 +00:00
. minor update and start prep for v0.1.13
This commit is contained in:
@ -1,10 +1,16 @@
|
||||
`.` minor | `-` Fix | `+` Addition | `^` improvement | `!` Change | `*` Refactor
|
||||
|
||||
> **IMPORTANT:** `0.1.x` will still have some breaking changes in patches.
|
||||
> - Make sure to **lock** your version, e.g., `genai = "=0.1.12"`.
|
||||
> - Make sure to **lock** your version, e.g., `genai = "=0.1.13"`.
|
||||
> - Version `0.2.x` will follow semver more strictly.
|
||||
> - API changes will be denoted as "`!` - **API CHANGE** ...."
|
||||
|
||||
## 2024-12-07 - `0.1.13`
|
||||
|
||||
- `+` add stop_sequences support cohere -
|
||||
- `+` stop_sequences - for openai, ollama, groq, gemini, cochere
|
||||
- `+` stop_sequences - for anthropic (thanks [@semtexzv](https://github.com/semtexzv))
|
||||
|
||||
## 2024-11-18 - `0.1.12`
|
||||
|
||||
- `.` minor update on llms model names
|
||||
|
@ -12,17 +12,19 @@ Currently supports natively: **Ollama**, **OpenAI**, **Anthropic**, **groq**, **
|
||||
|
||||
```toml
|
||||
# cargo.toml
|
||||
genai = "=0.1.12" # Version lock for `0.1.x`
|
||||
genai = "=0.1.13" # Version lock for `0.1.x`
|
||||
```
|
||||
|
||||
<br />
|
||||
|
||||
The goal of this library is to provide a common and ergonomic single API to many generative AI Providers, such as OpenAI, Anthropic, Cohere, Ollama.
|
||||
|
||||
- **IMPORTANT 1** `0.1.x` will still have some breaking changes in patches, so make sure to **lock** your version, e.g., `genai = "=0.1.12"`. In short, `0.1.x` can be considered "beta releases." Version `0.2.x` will follow semver more strictly.
|
||||
- **IMPORTANT 1** `0.1.x` will still have some breaking changes in patches, so make sure to **lock** your version, e.g., `genai = "=0.1.13"`. In short, `0.1.x` can be considered "beta releases." Version `0.2.x` will follow semver more strictly.
|
||||
|
||||
- **IMPORTANT 2** `genai` is focused on normalizing chat completion APIs across AI providers and is not intended to be a full representation of a given AI provider. For this, there are excellent libraries such as [async-openai](https://crates.io/search?q=async-openai) for OpenAI and [ollama-rs](https://crates.io/crates/ollama-rs) for Ollama.
|
||||
|
||||
Check out [devai.run](https://devai.run), the **Iterate to Automate** command-line application that leverages **GenAI** for multi-AI capabilities.
|
||||
|
||||
[Examples](#examples) | [Thanks](#thanks) | [Library Focus](#library-focus) | [Changelog](CHANGELOG.md) | Provider Mapping: [ChatOptions](#chatoptions) | [MetaUsage](#metausage)
|
||||
|
||||
## Examples
|
||||
@ -132,6 +134,7 @@ async fn main() -> Result<(), Box<dyn std::error::Error>> {
|
||||
|
||||
## Thanks
|
||||
|
||||
- Thanks to [@semtexzv](https://github.com/semtexzv) for `stop_sequences` Anthropic support [PR #34](https://github.com/jeremychone/rust-genai/pull/34)
|
||||
- Thanks to [@omarshehab221](https://github.com/omarshehab221) for de/serialize on structs [PR #19](https://github.com/jeremychone/rust-genai/pull/19)
|
||||
- Thanks to [@tusharmath](https://github.com/tusharmath) for make webc::Error [PR #12](https://github.com/jeremychone/rust-genai/pull/12)
|
||||
- Thanks to [@giangndm](https://github.com/giangndm) for make stream is send [PR #10](https://github.com/jeremychone/rust-genai/pull/10)
|
||||
|
@ -84,12 +84,15 @@ impl Adapter for CohereAdapter {
|
||||
if let Some(temperature) = options_set.temperature() {
|
||||
payload.x_insert("temperature", temperature)?;
|
||||
}
|
||||
|
||||
if !options_set.stop_sequences().is_empty() {
|
||||
payload.x_insert("stop_sequences", options_set.stop_sequences())?;
|
||||
}
|
||||
|
||||
if let Some(max_tokens) = options_set.max_tokens() {
|
||||
payload.x_insert("max_tokens", max_tokens)?;
|
||||
}
|
||||
|
||||
if let Some(top_p) = options_set.top_p() {
|
||||
payload.x_insert("p", top_p)?;
|
||||
}
|
||||
|
Reference in New Issue
Block a user