Implemented Ollama as an embeddings provider

Initial prototype of Ollama embeddings actually working, error handlign / retries still missing.

Allow model to be any String and require dimensions parameter

Fixed rustfmt formatting issues

There were some formatting issues in the initial PR and this should not make the changes comply with the Rust style guidelines

Because I accidentally didn't follow the style guide for commits in my commit messages I squashed them into one to comply
This commit is contained in:
Jakob Klemm 2024-03-03 01:11:25 +01:00
parent 938149f814
commit d3004d8040
No known key found for this signature in database
GPG key ID: D91BAB52F26F2A75
7 changed files with 350 additions and 15 deletions

View file

@ -2,6 +2,7 @@ use std::path::PathBuf;
use hf_hub::api::sync::ApiError;
use super::ollama::OllamaError;
use crate::error::FaultSource;
use crate::vector::openai::OpenAiError;
@ -71,6 +72,15 @@ pub enum EmbedErrorKind {
OpenAiRuntimeInit(std::io::Error),
#[error("initializing web client for sending embedding requests failed: {0}")]
InitWebClient(reqwest::Error),
// Dedicated Ollama error kinds, might have to merge them into one cohesive error type for all backends.
#[error("unexpected response from Ollama: {0}")]
OllamaUnexpected(reqwest::Error),
#[error("sent too many requests to Ollama: {0}")]
OllamaTooManyRequests(OllamaError),
#[error("received internal error from Ollama: {0}")]
OllamaInternalServerError(OllamaError),
#[error("received unhandled HTTP status code {0} from Ollama")]
OllamaUnhandledStatusCode(u16),
}
impl EmbedError {
@ -129,6 +139,22 @@ impl EmbedError {
pub fn openai_initialize_web_client(inner: reqwest::Error) -> Self {
Self { kind: EmbedErrorKind::InitWebClient(inner), fault: FaultSource::Runtime }
}
pub fn ollama_unexpected(inner: reqwest::Error) -> EmbedError {
Self { kind: EmbedErrorKind::OllamaUnexpected(inner), fault: FaultSource::Bug }
}
pub(crate) fn ollama_too_many_requests(inner: OllamaError) -> EmbedError {
Self { kind: EmbedErrorKind::OllamaTooManyRequests(inner), fault: FaultSource::Runtime }
}
pub(crate) fn ollama_internal_server_error(inner: OllamaError) -> EmbedError {
Self { kind: EmbedErrorKind::OllamaInternalServerError(inner), fault: FaultSource::Runtime }
}
pub(crate) fn ollama_unhandled_status_code(code: u16) -> EmbedError {
Self { kind: EmbedErrorKind::OllamaUnhandledStatusCode(code), fault: FaultSource::Bug }
}
}
#[derive(Debug, thiserror::Error)]