mirror of
https://github.com/meilisearch/meilisearch.git
synced 2025-03-06 22:02:34 +08:00
Test composite embedders
This commit is contained in:
Louis Dureuil
parent
b190b612a3
commit
57a6beee30
@ -407,3 +407,551 @@ async fn ollama_url_checks() {
|
||||
}
|
||||
"###);
|
||||
}
|
||||
|
||||
#[actix_rt::test]
|
||||
async fn composite_checks() {
|
||||
let server = Server::new().await;
|
||||
let index = server.index("test");
|
||||
// inner distribution
|
||||
let (response, _code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": null
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
server.wait_task(response.uid()).await;
|
||||
|
||||
let (response, code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": {
|
||||
"source": "composite",
|
||||
"searchEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
|
||||
"distribution": {
|
||||
"mean": 0.5,
|
||||
"sigma": 0.2,
|
||||
}
|
||||
},
|
||||
"indexingEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
|
||||
},
|
||||
}
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
snapshot!(code, @"400 Bad Request");
|
||||
snapshot!(response, @r###"
|
||||
{
|
||||
"message": "`.embedders.test.searchEmbedder`: Field `distribution` unavailable for source `huggingFace` for the search embedder.\n - note: available fields for source `huggingFace` for the search embedder: `source`, `model`, `revision`, `pooling`\n - note: `distribution` is available when source `huggingFace` is not for the search embedder",
|
||||
"code": "invalid_settings_embedders",
|
||||
"type": "invalid_request",
|
||||
"link": "https://docs.meilisearch.com/errors#invalid_settings_embedders"
|
||||
}
|
||||
"###);
|
||||
// manual source
|
||||
let (response, _code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": null
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
server.wait_task(response.uid()).await;
|
||||
|
||||
let (response, code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": {
|
||||
"source": "composite",
|
||||
"searchEmbedder": {
|
||||
"source": "userProvided",
|
||||
"dimensions": 42,
|
||||
},
|
||||
"indexingEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
|
||||
},
|
||||
}
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
snapshot!(code, @"400 Bad Request");
|
||||
snapshot!(response, @r###"
|
||||
{
|
||||
"message": "`.embedders.test.searchEmbedder.source`: Source `userProvided` is not available in a nested embedder",
|
||||
"code": "invalid_settings_embedders",
|
||||
"type": "invalid_request",
|
||||
"link": "https://docs.meilisearch.com/errors#invalid_settings_embedders"
|
||||
}
|
||||
"###);
|
||||
// composite source
|
||||
let (response, _code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": null
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
server.wait_task(response.uid()).await;
|
||||
|
||||
let (response, code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": {
|
||||
"source": "composite",
|
||||
"searchEmbedder": {
|
||||
"source": "composite",
|
||||
"searchEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
|
||||
},
|
||||
"indexingEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
|
||||
}
|
||||
},
|
||||
"indexingEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
|
||||
},
|
||||
}
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
snapshot!(code, @"400 Bad Request");
|
||||
snapshot!(response, @r###"
|
||||
{
|
||||
"message": "`.embedders.test.searchEmbedder.source`: Source `composite` is not available in a nested embedder",
|
||||
"code": "invalid_settings_embedders",
|
||||
"type": "invalid_request",
|
||||
"link": "https://docs.meilisearch.com/errors#invalid_settings_embedders"
|
||||
}
|
||||
"###);
|
||||
// no source in indexing
|
||||
let (response, _code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": null
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
server.wait_task(response.uid()).await;
|
||||
|
||||
let (response, code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": {
|
||||
"source": "composite",
|
||||
"searchEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
|
||||
},
|
||||
"indexingEmbedder": {},
|
||||
}
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
snapshot!(code, @"400 Bad Request");
|
||||
snapshot!(response, @r###"
|
||||
{
|
||||
"message": "`.embedders.test.indexingEmbedder`: Missing field `source`.\n - note: this field is mandatory for nested embedders",
|
||||
"code": "invalid_settings_embedders",
|
||||
"type": "invalid_request",
|
||||
"link": "https://docs.meilisearch.com/errors#invalid_settings_embedders"
|
||||
}
|
||||
"###);
|
||||
// no source in search
|
||||
let (response, _code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": null
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
server.wait_task(response.uid()).await;
|
||||
|
||||
let (response, code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": {
|
||||
"source": "composite",
|
||||
"searchEmbedder": {},
|
||||
"indexingEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
|
||||
},
|
||||
}
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
snapshot!(code, @"400 Bad Request");
|
||||
snapshot!(response, @r###"
|
||||
{
|
||||
"message": "`.embedders.test.searchEmbedder`: Missing field `source`.\n - note: this field is mandatory for nested embedders",
|
||||
"code": "invalid_settings_embedders",
|
||||
"type": "invalid_request",
|
||||
"link": "https://docs.meilisearch.com/errors#invalid_settings_embedders"
|
||||
}
|
||||
"###);
|
||||
// no indexing
|
||||
let (response, _code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": null
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
server.wait_task(response.uid()).await;
|
||||
|
||||
let (response, code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": {
|
||||
"source": "composite",
|
||||
"searchEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
|
||||
},
|
||||
}
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
snapshot!(code, @"400 Bad Request");
|
||||
snapshot!(response, @r###"
|
||||
{
|
||||
"message": "`.embedders.test`: Missing field `indexingEmbedder` (note: this field is mandatory for source `composite`)",
|
||||
"code": "invalid_settings_embedders",
|
||||
"type": "invalid_request",
|
||||
"link": "https://docs.meilisearch.com/errors#invalid_settings_embedders"
|
||||
}
|
||||
"###);
|
||||
// no search
|
||||
let (response, _code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": null
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
server.wait_task(response.uid()).await;
|
||||
|
||||
let (response, code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": {
|
||||
"source": "composite",
|
||||
"indexingEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
|
||||
},
|
||||
}
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
snapshot!(code, @"400 Bad Request");
|
||||
snapshot!(response, @r###"
|
||||
{
|
||||
"message": "`.embedders.test`: Missing field `searchEmbedder` (note: this field is mandatory for source `composite`)",
|
||||
"code": "invalid_settings_embedders",
|
||||
"type": "invalid_request",
|
||||
"link": "https://docs.meilisearch.com/errors#invalid_settings_embedders"
|
||||
}
|
||||
"###);
|
||||
// inner quantized
|
||||
let (response, _code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": null
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
server.wait_task(response.uid()).await;
|
||||
|
||||
let (response, code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": {
|
||||
"source": "composite",
|
||||
"searchEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
|
||||
"binaryQuantized": true,
|
||||
},
|
||||
"indexingEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
|
||||
"binaryQuantized": false,
|
||||
},
|
||||
}
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
snapshot!(code, @"400 Bad Request");
|
||||
snapshot!(response, @r###"
|
||||
{
|
||||
"message": "`.embedders.test.searchEmbedder`: Field `binaryQuantized` unavailable for source `huggingFace` for the search embedder.\n - note: available fields for source `huggingFace` for the search embedder: `source`, `model`, `revision`, `pooling`\n - note: `binaryQuantized` is available when source `huggingFace` is not for the search embedder",
|
||||
"code": "invalid_settings_embedders",
|
||||
"type": "invalid_request",
|
||||
"link": "https://docs.meilisearch.com/errors#invalid_settings_embedders"
|
||||
}
|
||||
"###);
|
||||
// prompt in search
|
||||
let (response, _code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": null
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
server.wait_task(response.uid()).await;
|
||||
|
||||
let (response, code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": {
|
||||
"source": "composite",
|
||||
"searchEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
|
||||
"documentTemplate": "toto",
|
||||
},
|
||||
"indexingEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
|
||||
},
|
||||
}
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
snapshot!(code, @"400 Bad Request");
|
||||
snapshot!(response, @r###"
|
||||
{
|
||||
"message": "`.embedders.test.searchEmbedder`: Field `documentTemplate` unavailable for source `huggingFace` for the search embedder.\n - note: available fields for source `huggingFace` for the search embedder: `source`, `model`, `revision`, `pooling`\n - note: `documentTemplate` is available when source `huggingFace` is not for the search embedder",
|
||||
"code": "invalid_settings_embedders",
|
||||
"type": "invalid_request",
|
||||
"link": "https://docs.meilisearch.com/errors#invalid_settings_embedders"
|
||||
}
|
||||
"###);
|
||||
// dimensions don't match
|
||||
let (response, _code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": null
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
server.wait_task(response.uid()).await;
|
||||
|
||||
let (response, code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": {
|
||||
"source": "composite",
|
||||
"searchEmbedder": {
|
||||
"source": "ollama",
|
||||
"dimensions": 0x42,
|
||||
"model": "does-not-exist",
|
||||
},
|
||||
"indexingEmbedder": {
|
||||
"source": "ollama",
|
||||
"dimensions": 42,
|
||||
"model": "does-not-exist",
|
||||
},
|
||||
}
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
snapshot!(code, @"202 Accepted");
|
||||
let response = server.wait_task(response.uid()).await;
|
||||
snapshot!(response, @r###"
|
||||
{
|
||||
"uid": "[uid]",
|
||||
"batchUid": "[batch_uid]",
|
||||
"indexUid": "test",
|
||||
"status": "failed",
|
||||
"type": "settingsUpdate",
|
||||
"canceledBy": null,
|
||||
"details": {
|
||||
"embedders": {
|
||||
"test": {
|
||||
"source": "composite",
|
||||
"searchEmbedder": {
|
||||
"source": "ollama",
|
||||
"model": "does-not-exist",
|
||||
"dimensions": 66
|
||||
},
|
||||
"indexingEmbedder": {
|
||||
"source": "ollama",
|
||||
"model": "does-not-exist",
|
||||
"dimensions": 42
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"error": {
|
||||
"message": "Index `test`: Error while generating embeddings: user error: error while generating test embeddings.\n - the dimensions of embeddings produced at search time and at indexing time don't match.\n - Search time dimensions: 66\n - Indexing time dimensions: 42\n - Note: Dimensions of embeddings produced by both embedders are required to match.",
|
||||
"code": "vector_embedding_error",
|
||||
"type": "invalid_request",
|
||||
"link": "https://docs.meilisearch.com/errors#vector_embedding_error"
|
||||
},
|
||||
"duration": "[duration]",
|
||||
"enqueuedAt": "[date]",
|
||||
"startedAt": "[date]",
|
||||
"finishedAt": "[date]"
|
||||
}
|
||||
"###);
|
||||
// pooling don't match
|
||||
let (response, _code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": null
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
server.wait_task(response.uid()).await;
|
||||
|
||||
let (response, code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": {
|
||||
"source": "composite",
|
||||
"searchEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
|
||||
"pooling": "forceMean"
|
||||
},
|
||||
"indexingEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
|
||||
"pooling": "forceCls"
|
||||
},
|
||||
}
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
snapshot!(code, @"202 Accepted");
|
||||
let response = server.wait_task(response.uid()).await;
|
||||
snapshot!(response, @r###"
|
||||
{
|
||||
"uid": "[uid]",
|
||||
"batchUid": "[batch_uid]",
|
||||
"indexUid": "test",
|
||||
"status": "failed",
|
||||
"type": "settingsUpdate",
|
||||
"canceledBy": null,
|
||||
"details": {
|
||||
"embedders": {
|
||||
"test": {
|
||||
"source": "composite",
|
||||
"searchEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
|
||||
"pooling": "forceMean"
|
||||
},
|
||||
"indexingEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
|
||||
"pooling": "forceCls"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"error": {
|
||||
"message": "Index `test`: Error while generating embeddings: user error: error while generating test embeddings.\n - the embeddings produced at search time and indexing time are not similar enough.\n - angular distance 0.25\n - Meilisearch requires a maximum distance of 0.01.\n - Note: check that both embedders produce similar embeddings.\n - Make sure the `model`, `revision` and `pooling` of both embedders match.",
|
||||
"code": "vector_embedding_error",
|
||||
"type": "invalid_request",
|
||||
"link": "https://docs.meilisearch.com/errors#vector_embedding_error"
|
||||
},
|
||||
"duration": "[duration]",
|
||||
"enqueuedAt": "[date]",
|
||||
"startedAt": "[date]",
|
||||
"finishedAt": "[date]"
|
||||
}
|
||||
"###);
|
||||
|
||||
// ok
|
||||
let (response, _code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": null
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
server.wait_task(response.uid()).await;
|
||||
|
||||
let (response, code) = index
|
||||
.update_settings(json!({
|
||||
"embedders": {
|
||||
"test": {
|
||||
"source": "composite",
|
||||
"searchEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
|
||||
},
|
||||
"indexingEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e",
|
||||
},
|
||||
}
|
||||
}
|
||||
}))
|
||||
.await;
|
||||
snapshot!(code, @"202 Accepted");
|
||||
let response = server.wait_task(response.uid()).await;
|
||||
snapshot!(response, @r###"
|
||||
{
|
||||
"uid": "[uid]",
|
||||
"batchUid": "[batch_uid]",
|
||||
"indexUid": "test",
|
||||
"status": "succeeded",
|
||||
"type": "settingsUpdate",
|
||||
"canceledBy": null,
|
||||
"details": {
|
||||
"embedders": {
|
||||
"test": {
|
||||
"source": "composite",
|
||||
"searchEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e"
|
||||
},
|
||||
"indexingEmbedder": {
|
||||
"source": "huggingFace",
|
||||
"model": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"revision": "e4ce9877abf3edfe10b0d82785e83bdcb973e22e"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"error": null,
|
||||
"duration": "[duration]",
|
||||
"enqueuedAt": "[date]",
|
||||
"startedAt": "[date]",
|
||||
"finishedAt": "[date]"
|
||||
}
|
||||
"###);
|
||||
}
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user