István Zoltán Szabó
9b7d808bf4
[DOCS] Fixes adaptive_allocations examples ( #113248 )
...
Co-authored-by: Jan Kuipers <148754765+jan-elastic@users.noreply.github.com>
2024-09-20 11:31:04 +02:00
István Zoltán Szabó
3636797cfe
[DOCS] Adds path params and available task types to the PUT inference page ( #112696 )
...
Co-authored-by: Liam Thompson <32779855+leemthompo@users.noreply.github.com>
2024-09-10 12:43:08 +02:00
David Kyle
e3e562ffbf
[ML] Support sparse embedding models in the elasticsearch inference service ( #112270 )
...
For a sparse embedding model created with the ml trained models APIs
2024-08-29 17:18:54 +01:00
weizijun
35fe3a9c47
some fixed ( #112332 )
2024-08-29 13:46:58 +02:00
weizijun
b9dea69b5c
[Inference API] Add Docs for AlibabaCloud AI Search Support for the Inference API ( #112273 )
...
Co-authored-by: István Zoltán Szabó <istvan.szabo@elastic.co>
2024-08-29 09:17:27 +02:00
István Zoltán Szabó
7f67ba9958
[DOCS] Expands inference API main page info ( #111830 )
2024-08-14 16:04:11 +02:00
István Zoltán Szabó
0b064c7539
[DOCS] Publishes Anthropic inference service docs. ( #111619 )
2024-08-07 11:18:43 +02:00
István Zoltán Szabó
d6c532135e
[DOCS] Adds adaptive_allocations to inference and trained model API docs ( #111476 )
2024-08-01 12:37:07 +02:00
István Zoltán Szabó
845dc6f252
[DOCS] Expands top_n parameter description in the PUT inference API docs ( #111446 )
...
Co-authored-by: Adam Demjen <demjened@gmail.com>
2024-07-30 17:32:14 +02:00
Pius
d04f5c4e10
[DOCS] Clarify that inference ID cannot match model ID ( #111310 )
...
* Clarify that inference ID cannot match model ID
* Update service-elasticsearch.asciidoc
2024-07-26 12:09:53 +02:00
István Zoltán Szabó
f4c05bdcab
[DOCS] Amends PUT inference API docs with model download info ( #111278 )
...
* [DOCS] Amends PUT inference API docs with model download info.
* [DOCS] Addresses feedback.
2024-07-26 11:32:00 +02:00
David Kyle
12d26b7573
[ML DOCS]Timeout only applies to ELSER and built in E5 models ( #111159 )
2024-07-23 09:26:40 +01:00
Jonathan Buttner
07c7bf438f
Anthropic docs ( #110850 )
2024-07-15 13:43:14 -04:00
Liam Thompson
6590894c99
[DOCS] Add note about ML model 502 timeout when using Create inference API ( #110835 )
...
* [DOCS] Add note about ml model 502 timeout
* Add note to API ref
2024-07-15 12:19:21 +02:00
Mark J. Hoy
560d4048d2
[Inference API] Add Docs for Amazon Bedrock Support for the Inference API ( #110594 )
...
* Add Amazon Bedrock Inference API to docs
* fix example errors
* update semantic search tutorial; add changelog
* fix typo
* fix error; accept suggestions
2024-07-12 10:14:54 -04:00
David Kyle
1b6d44b55d
[DOCS] Fix typo: though -> through ( #110636 )
2024-07-09 07:30:42 -07:00
Tim Grein
406b969c62
[Inference API] Add Google Vertex AI reranking docs ( #110390 )
2024-07-03 14:03:12 +02:00
Tim Grein
390439ad9f
[Inference API] Add Google Vertex AI text embeddings docs ( #110317 )
2024-07-02 14:47:14 +02:00
Tim Grein
99749aa277
[Inference API] Fix wording in Azure AI Studio docs ( #110322 )
2024-07-01 14:37:56 +02:00
Tim Grein
6accd6e247
[Inference API] Fix wording in delete-inference docs ( #110321 )
2024-07-01 13:37:30 +02:00
Tim Grein
35eae4029a
Fix typo in get-inference docs (retrives -> retrieves) ( #110320 )
2024-07-01 10:13:48 +02:00
István Zoltán Szabó
43f5696406
[DOCS] Refactors PUT inference API docs ( #109812 )
2024-07-01 10:12:16 +02:00
Jan Kuipers
13478b2bca
Fix put inference API docs ( #110025 )
...
* Fix put inference API docs
* Update docs/changelog/110025.yaml
* Delete docs/changelog/110025.yaml
2024-06-21 16:01:08 +02:00
Jonathan Buttner
6a1ece0c06
Adding input type to docs ( #109588 )
2024-06-12 09:15:08 -04:00
Mark J. Hoy
80a22ec046
[Inference API] Add Docs for Mistral Embedding Support for the Inference API ( #109319 )
...
* Initial docs for put-inference for Mistral
* adds mistral embeddings to tutorial; add changelog
* update mistral text and dimensions
* fix mistral spelling error
* fix azure AI studio; fix Mistral label
* fix auto-formatted items
* change pipeline button back to azure openai
* put proper Azure AI Studio include in
* fix missing azure-openai; fix huggingface hidden
* fix mistral tab for reindex
* re-add Mistral service settings to put inference
2024-06-05 11:23:29 -04:00
Tim Grein
dc13b75656
[Inference API] Add text_embedding task type to Google AI Studio docs ( #109307 )
2024-06-05 15:35:31 +02:00
Jonathan Buttner
fdb5058b13
[ML] Inference API rate limit queuing logic refactor ( #107706 )
...
* Adding new executor
* Adding in queuing logic
* working tests
* Added cleanup task
* Update docs/changelog/107706.yaml
* Updating yml
* deregistering callbacks for settings changes
* Cleaning up code
* Update docs/changelog/107706.yaml
* Fixing rate limit settings bug and only sleeping least amount
* Removing debug logging
* Removing commented code
* Renaming feedback
* fixing tests
* Updating docs and validation
* Fixing source blocks
* Adjusting cancel logic
* Reformatting ascii
* Addressing feedback
* adding rate limiting for google embeddings and mistral
---------
Co-authored-by: Elastic Machine <elasticmachine@users.noreply.github.com>
2024-06-05 08:25:25 -04:00
István Zoltán Szabó
d1da412a3e
[DOCS] Expands DELETE inference API docs ( #109282 )
...
* [DOCS] Expands DELETE inference API docs.
* [DOCS] Adds discrete flag.
2024-06-03 17:32:31 +02:00
István Zoltán Szabó
1413c67d99
[DOCS] Amends inference reference docs and tutorials ( #109159 )
...
* [DOCS] Fixes inference tutorial widgets.
* [DOCS] Adds link to notebooks, rearranges sections in PUT inference API docs.
2024-05-29 17:43:10 +02:00
Tim Grein
6d864154ca
[Inference API] Add Google AI Studio completion docs ( #109089 )
2024-05-28 15:21:33 +02:00
Mark J. Hoy
b3a902e035
Add Docs for Azure AI Studio Support for the Inference API ( #108737 )
...
* add docs and embeddings tutorial pieces
* cleanup openai reference
* Suggested cleanups; add missing div tag
* one more change for clarity (requests per minute)
2024-05-17 10:35:43 -04:00
Tim Grein
8a43665d77
[Inference API] Fix two typos in docs ( #108724 )
2024-05-16 15:01:56 +02:00
Tim Grein
6ff29c32c7
[Inference API] Add completion task type to cohere docs ( #108723 )
2024-05-16 14:59:29 +02:00
Tim Grein
34293131b8
[Inference API] Add Azure OpenAI completion docs ( #108704 )
2024-05-16 13:22:01 +02:00
Tim Grein
662a171dcd
[Inference API] Remove duplicate section in inference api task settings docs ( #108615 )
2024-05-14 17:44:37 +02:00
David Kyle
f8fe610966
[ML] Add GET _inference for all inference endpoints ( #107517 )
2024-04-16 17:15:59 +01:00
Mark J. Hoy
624a5b1fe5
Add Docs for Azure OpenAI Embeddings Inference ( #107498 )
...
* Update docs for Azure OpenAI Embeddings inference
* cleanups
* update link for dot_product similarity
* final cleanups
2024-04-16 10:52:27 -04:00
István Zoltán Szabó
2e847e8817
[DOCS] Documents the rerank task type of the Inference API ( #107404 )
...
* [DOCS] Documents the rerank task type of the Inference API.
2024-04-16 09:39:36 +02:00
István Zoltán Szabó
b9322da325
[DOCS] Fixes section levels in POST inference API docs. ( #107451 )
2024-04-15 10:31:09 +02:00
István Zoltán Szabó
1587dada58
[DOCS] Fixes a typo in the HugggingFace tutorial. ( #107321 )
2024-04-10 18:50:44 +02:00
Jonathan Buttner
c9e84558b7
[ML] Adding a timeout parameter to the inference API ( #107242 )
...
* Plumbing timeout through the request
* Passing timeout through external services
* Update docs/changelog/107242.yaml
* Fixing tests and adjusting docs
* Correcting timeout field name
* Reporting error message for elser
* Removing unused code
2024-04-10 12:29:40 -04:00
István Zoltán Szabó
afb492272a
[DOCS] Adds HuggingFace example to inference API tutorial ( #107298 )
2024-04-10 17:57:18 +02:00
Jonathan Buttner
8638deeb9e
Openai model_id is required ( #107286 )
2024-04-10 08:37:49 -04:00
David Kyle
173900f89e
[ML] Update last usages of model_id to inference_id ( #107133 )
2024-04-05 12:10:03 +01:00
István Zoltán Szabó
29a3256a7d
[DOCS] Makes Inference APIs main page more informative. ( #107100 )
2024-04-04 15:42:03 +02:00
Tim Grein
e56dcee078
[Inference API] Add completion task type docs ( #106876 )
2024-04-02 13:34:46 +02:00
István Zoltán Szabó
a3d96b9333
[DOCS] Changes model_id path param to inference_id ( #106719 )
2024-03-26 08:20:34 +01:00
István Zoltán Szabó
11a4e4029a
[DOCS] Adjusts PUT inference API docs examples ( #106604 )
...
Co-authored-by: David Kyle <david.kyle@elastic.co>
2024-03-21 14:57:10 +01:00
István Zoltán Szabó
09b6072afd
[DOCS] Changes Cohere inference examples in tutorial and API docs ( #106524 )
2024-03-20 15:07:41 +01:00
David Kyle
2087b65523
[ML] Create inference_user and inference_admin roles ( #106371 )
...
Defines new inference_user and inference_admin roles with the
related cluster privileges manage_inference and monitor_inference.
inference_user can list the models and preform inference,
inference_admin can do the same plus create and delete models
2024-03-20 11:15:21 +00:00
