Commit Graph

49 Commits

Author SHA1 Message Date
Louis Dureuil
00c4ed3bc2
milli: refactor getting embedder and embedder name 2024-04-04 15:57:29 +02:00
Louis Dureuil
572fb3a51d
Finer granularity for embedder needs reindex 2024-03-27 12:01:34 +01:00
Louis Dureuil
4ff0255783
remove unused function 2024-03-27 11:51:14 +01:00
Louis Dureuil
a25456120d
Expose distribution in settings 2024-03-27 11:51:04 +01:00
Louis Dureuil
168ded3b9d
Deserr for distribution 2024-03-27 11:50:33 +01:00
Louis Dureuil
afd1da5642
Add distribution to all embedders 2024-03-27 11:50:22 +01:00
Louis Dureuil
817ccc089a
also allow api_key 2024-03-25 11:50:00 +01:00
Louis Dureuil
58972f35cb
Allow url parameter for ollama embedder 2024-03-25 11:32:55 +01:00
Louis Dureuil
a1db342f01
Expose REST embedder to the API 2024-03-25 11:23:15 +01:00
Louis Dureuil
f87747f4d3
Remove unwraps 2024-03-25 11:23:04 +01:00
Louis Dureuil
ac52c857e8
Update ollama and openai impls to use the rest embedder internally 2024-03-25 11:23:03 +01:00
Louis Dureuil
8708cbef25
Add RestEmbedder 2024-03-25 11:23:03 +01:00
Louis Dureuil
c3d02f092d
OpenAI sync 2024-03-25 11:23:03 +01:00
Louis Dureuil
bc58e8a310
Documentation for the vector module 2024-03-25 11:23:03 +01:00
Tamo
c5322df519
Revert "Revert "Merge remote-tracking branch 'origin/main' into release-v1.7.1"" 2024-03-20 10:08:28 +01:00
Tamo
567194b925 Revert "Merge remote-tracking branch 'origin/main' into release-v1.7.1"
This reverts commit bd74cce86a, reversing
changes made to d2f77e88bd.
2024-03-19 16:56:21 +01:00
Louis Dureuil
a302e258bd
Don't display dimensions as 0 when it is not set 2024-03-18 16:10:12 +01:00
meili-bors[bot]
5ed7b6a0b2
Merge #4456
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>
2024-03-13 08:48:47 +00:00
Louis Dureuil
ae67d5eef0
Update milli/src/vector/error.rs
Fix Meilisearch capitalization
2024-03-13 09:45:04 +01:00
Jakob Klemm
88bc9556a9
Add Ollama dimension inference and add clearer errors
Instead of the user manually specifying the model dimensions it will now automatically get determined
Just like with hf.rs the word "test" gets embedded to determine the dimensions of the output
Add a dedicated error type for if the model doesn't exist (don't automatically pull it though) and set the fault of that error to be the user
2024-03-12 19:59:11 +01:00
Louis Dureuil
0c216048b5
Cap timeout duration 2024-03-05 12:19:25 +01:00
Louis Dureuil
36d17110d8
openai: Handle BAD_GETAWAY, be more resilient to failure 2024-03-05 12:18:54 +01:00
Jakob Klemm
d3004d8040
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
2024-03-04 15:09:43 +01:00
Louis Dureuil
55796406c5
Add GPU analytics 2024-02-26 10:41:47 +01:00
Tamo
e773dfa9ba
get rids of log in milli and add logs for the bucket sort 2024-02-08 15:04:05 +01:00
Louis Dureuil
a1caac9bfb
Correct distribution shifts for new models 2024-02-07 15:09:16 +01:00
Louis Dureuil
32ee05ccef
Fix default dimensions for models 2024-02-07 11:52:09 +01:00
Louis Dureuil
74c180267e
pass dimensions only when defined 2024-02-07 11:52:08 +01:00
Louis Dureuil
517f5332d6
Allow actually passing dimensions for OpenAI source
-> make sure the settings change is rejected or the settings task fails when the specified model doesn't support
overriding `dimensions` and the passed `dimensions` differs from the model's default dimensions.
2024-02-07 11:51:44 +01:00
Louis Dureuil
9ac5750096
Retrieve the overriden dimensions from the configuration when fetching settings 2024-02-07 11:51:44 +01:00
Louis Dureuil
7ae4013478
Make sure the overriden dimensions are always used when embedding 2024-02-07 11:51:44 +01:00
Gosti
fb705116a6
feat: add new models and ability to override dimensions 2024-02-07 11:51:42 +01:00
Louis Dureuil
fbf5f2a392
Don't use a runtime in extract_embedder, use it only for OpenAI 2024-02-01 10:33:27 +01:00
Louis Dureuil
1555870088
Truncate HuggingFace vectors that are too long 2024-02-01 10:33:27 +01:00
Louis Dureuil
f692021bfc
Implement PR comments 2024-01-22 10:25:56 +01:00
Louis Dureuil
84f49d76cd
Add cuda feature 2024-01-22 10:25:16 +01:00
Louis Dureuil
0bf879fb88
Fix warning on rust stable 2023-12-20 17:48:09 +01:00
Louis Dureuil
393216bf30
Flatten embedders settings 2023-12-20 17:16:43 +01:00
Louis Dureuil
333ce12eb2
Fixed issue where the default revision is always the one we picked for the default model 2023-12-20 10:17:49 +01:00
Louis Dureuil
eb5cb91da2
Switch default from hf to openai 2023-12-14 16:19:46 +01:00
Louis Dureuil
87bba98bd8
Various changes
- fixed seed for arroy
- check vector dimensions as soon as it is provided to search
- don't embed whitespace
2023-12-14 16:08:42 +01:00
Louis Dureuil
a4536b1381
Small adjustments to respect the spec 2023-12-14 16:08:42 +01:00
Louis Dureuil
5b51cb04af
Remove some settings 2023-12-14 16:08:42 +01:00
Louis Dureuil
b8e4709dfa
Remove prompt strategy and fallback 2023-12-14 16:08:41 +01:00
Louis Dureuil
e0cc775dc4
Various changes
- DistributionShift in Search object (to be set from model in embed?)
- Fix issue where embedder index wasn't computed at search time
- Accept as default embedder either the "default" one, or the only embedder when there is only one
2023-12-14 16:08:41 +01:00
Louis Dureuil
12940d79a9
WIP
- manual embedder
- multi embedders OK
- clippy + tests OK
2023-12-14 16:08:41 +01:00
Louis Dureuil
922a640188
WIP multi embedders
fixed template bugs
2023-12-14 16:08:41 +01:00
Louis Dureuil
65e49b7092
Remove stuff, add distribution shift (WIP) 2023-12-14 16:08:38 +01:00
Louis Dureuil
13c2c6c16b
Small commit to add hybrid search and autoembedding 2023-12-14 16:07:48 +01:00