4456: Add Ollama as an embeddings provider r=dureuill a=jakobklemm

# Pull Request

## Related issue
[Related Discord Thread](https://discord.com/channels/1006923006964154428/1211977150316683305)

## What does this PR do?
- Adds Ollama as a provider of Embeddings besides HuggingFace and OpenAI under the name `ollama`
- Adds the environment variable `MEILI_OLLAMA_URL` to set the embeddings URL of an Ollama instance with a default value of `http://localhost:11434/api/embeddings` if no variable is set
- Changes some of the structs and functions in `openai.rs` to be public so that they can be shared.
- Added more error variants for Ollama specific errors
- It uses the model `nomic-embed-text` as default, but any string value is allowed, however it won't automatically check if the model actually exists or is an embedding model

Tested against Ollama version `v0.1.27` and the `nomic-embed-text` model.

## PR checklist
Please check if your PR fulfills the following requirements:
- [x] Does this PR fix an existing issue, or have you listed the changes applied in the PR description (and why they are needed)?
- [x] Have you read the contributing guidelines?
- [x] Have you made sure that the title is accurate and descriptive of the changes?

Co-authored-by: Jakob Klemm <jakob@jeykey.net>
Co-authored-by: Louis Dureuil <louis.dureuil@gmail.com>
This commit is contained in:
meili-bors[bot] 2024-03-13 08:48:47 +00:00 committed by GitHub
commit 5ed7b6a0b2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 409 additions and 14 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 +72,17 @@ 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("model not found. Meilisearch will not automatically download models from the Ollama library, please pull the model manually: {0}")]
OllamaModelNotFoundError(OllamaError),
#[error("received unhandled HTTP status code {0} from Ollama")]
OllamaUnhandledStatusCode(u16),
}
impl EmbedError {
@ -129,6 +141,26 @@ impl EmbedError {
pub fn openai_initialize_web_client(inner: reqwest::Error) -> Self {
Self { kind: EmbedErrorKind::InitWebClient(inner), fault: FaultSource::Runtime }
}
pub(crate) fn ollama_unexpected(inner: reqwest::Error) -> EmbedError {
Self { kind: EmbedErrorKind::OllamaUnexpected(inner), fault: FaultSource::Bug }
}
pub(crate) fn ollama_model_not_found(inner: OllamaError) -> EmbedError {
Self { kind: EmbedErrorKind::OllamaModelNotFoundError(inner), fault: FaultSource::User }
}
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)]
@ -195,6 +227,13 @@ impl NewEmbedderError {
}
}
pub fn ollama_could_not_determine_dimension(inner: EmbedError) -> NewEmbedderError {
Self {
kind: NewEmbedderErrorKind::CouldNotDetermineDimension(inner),
fault: FaultSource::User,
}
}
pub fn openai_invalid_api_key_format(inner: reqwest::header::InvalidHeaderValue) -> Self {
Self { kind: NewEmbedderErrorKind::InvalidApiKeyFormat(inner), fault: FaultSource::User }
}