Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[8.x] [Connectors][GenAI] Inference Service Kibana connector (elastic…
…#189027) (elastic#196035) # Backport This will backport the following commits from `main` to `8.x`: - [[Connectors][GenAI] Inference Service Kibana connector (elastic#189027)](elastic#189027) <!--- Backport version: 9.4.3 --> ### Questions ? Please refer to the [Backport tool documentation](https://github.com/sqren/backport) <!--BACKPORT [{"author":{"name":"Yuliia Naumenko","email":"[email protected]"},"sourceCommit":{"committedDate":"2024-10-13T20:39:09Z","message":"[Connectors][GenAI] Inference Service Kibana connector (elastic#189027)\n\n## Summary\r\nResolves https://github.com/elastic/kibana/issues/188043\r\n\r\nThis PR adds new connector which is define integration with Elastic\r\nInference Endpoint via [Inference\r\nAPIs](https://www.elastic.co/guide/en/elasticsearch/reference/current/inference-apis.html)\r\nThe lifecycle of the Inference Endpoint are managed by the connector\r\nregistered handlers:\r\n\r\n- `preSaveHook` -\r\n[create](https://www.elastic.co/guide/en/elasticsearch/reference/current/put-inference-api.html)\r\nnew Inference Endpoint in the connector create mode (`isEdit === false`)\r\nand\r\n[delete](https://www.elastic.co/guide/en/elasticsearch/reference/current/delete-inference-api.html)+[create](https://www.elastic.co/guide/en/elasticsearch/reference/current/put-inference-api.html)\r\nin the connector edit mode (`isEdit === true`)\r\n- `postSaveHook` - check if the connector SO was created/updated and if\r\nnot removes Inference Endpoint from preSaveHook\r\n- `postDeleteHook` -\r\n[delete](https://www.elastic.co/guide/en/elasticsearch/reference/current/delete-inference-api.html)\r\nInference Endpoint if connector was deleted.\r\n\r\nIn the Kibana Stack Management Connectors, its represented with the new\r\ncard (Technical preview badge):\r\n\r\n<img width=\"1261\" alt=\"Screenshot 2024-09-27 at 2 11 12 PM\"\r\nsrc=\"https://github.com/user-attachments/assets/dcbcce1f-06e7-4d08-8b77-0ba4105354f8\">\r\n\r\nTo simplify the future integration with AI Assistants, the Connector\r\nconsists from the two main UI parts: provider selector and required\r\nprovider settings, which will be always displayed\r\n<img width=\"862\" alt=\"Screenshot 2024-10-07 at 7 59 09 AM\"\r\nsrc=\"https://github.com/user-attachments/assets/87bae493-c642-479e-b28f-6150354608dd\">\r\n\r\nand Additional options, which contains optional provider settings and\r\nTask Type configuration:\r\n\r\n<img width=\"861\" alt=\"Screenshot 2024-10-07 at 8 00 15 AM\"\r\nsrc=\"https://github.com/user-attachments/assets/2341c034-6198-4731-8ce7-e22e6c6fb20f\">\r\n\r\n\r\nsubActions corresponds to the different taskTypes Inference API\r\nsupports. Each of the task type has its own Inference Perform params.\r\nCurrently added:\r\n\r\n- completion & completionStream\r\n- rerank\r\n- text_embedding\r\n- sparse_embedding\r\n\r\nFollow up work:\r\n\r\n1. Collapse/expand Additional options, when the connector flyout/modal\r\nhas AI Assistant as a context (path through the extending context\r\nimplementation on the connector framework level)\r\n2. Add support for additional params for Completion subAction to be able\r\nto path functions\r\n3. Add support for tokens usage Dashboard, when inference API will\r\ninclude the used tokens count in the response\r\n4. Add functionality and UX for migration from existing specific AI\r\nconnectors to the Inference connector with proper provider and\r\ncompletion task\r\n5. Integrate Connector with the AI Assistants\r\n\r\n---------\r\n\r\nCo-authored-by: kibanamachine <[email protected]>\r\nCo-authored-by: István Zoltán Szabó <[email protected]>\r\nCo-authored-by: Liam Thompson <[email protected]>\r\nCo-authored-by: Steph Milovic <[email protected]>","sha":"288d41d61ec2389b2e8856da75fd0f3107f9c484","branchLabelMapping":{"^v9.0.0$":"main","^v8.16.0$":"8.x","^v(\\d+).(\\d+).\\d+$":"$1.$2"}},"sourcePullRequest":{"labels":["v9.0.0","release_note:feature","Feature:Actions/ConnectorTypes","8.16 candidate","v8.16.0","backport:version"],"title":"[Connectors][GenAI] Inference Service Kibana connector","number":189027,"url":"https://github.com/elastic/kibana/pull/189027","mergeCommit":{"message":"[Connectors][GenAI] Inference Service Kibana connector (elastic#189027)\n\n## Summary\r\nResolves https://github.com/elastic/kibana/issues/188043\r\n\r\nThis PR adds new connector which is define integration with Elastic\r\nInference Endpoint via [Inference\r\nAPIs](https://www.elastic.co/guide/en/elasticsearch/reference/current/inference-apis.html)\r\nThe lifecycle of the Inference Endpoint are managed by the connector\r\nregistered handlers:\r\n\r\n- `preSaveHook` -\r\n[create](https://www.elastic.co/guide/en/elasticsearch/reference/current/put-inference-api.html)\r\nnew Inference Endpoint in the connector create mode (`isEdit === false`)\r\nand\r\n[delete](https://www.elastic.co/guide/en/elasticsearch/reference/current/delete-inference-api.html)+[create](https://www.elastic.co/guide/en/elasticsearch/reference/current/put-inference-api.html)\r\nin the connector edit mode (`isEdit === true`)\r\n- `postSaveHook` - check if the connector SO was created/updated and if\r\nnot removes Inference Endpoint from preSaveHook\r\n- `postDeleteHook` -\r\n[delete](https://www.elastic.co/guide/en/elasticsearch/reference/current/delete-inference-api.html)\r\nInference Endpoint if connector was deleted.\r\n\r\nIn the Kibana Stack Management Connectors, its represented with the new\r\ncard (Technical preview badge):\r\n\r\n<img width=\"1261\" alt=\"Screenshot 2024-09-27 at 2 11 12 PM\"\r\nsrc=\"https://github.com/user-attachments/assets/dcbcce1f-06e7-4d08-8b77-0ba4105354f8\">\r\n\r\nTo simplify the future integration with AI Assistants, the Connector\r\nconsists from the two main UI parts: provider selector and required\r\nprovider settings, which will be always displayed\r\n<img width=\"862\" alt=\"Screenshot 2024-10-07 at 7 59 09 AM\"\r\nsrc=\"https://github.com/user-attachments/assets/87bae493-c642-479e-b28f-6150354608dd\">\r\n\r\nand Additional options, which contains optional provider settings and\r\nTask Type configuration:\r\n\r\n<img width=\"861\" alt=\"Screenshot 2024-10-07 at 8 00 15 AM\"\r\nsrc=\"https://github.com/user-attachments/assets/2341c034-6198-4731-8ce7-e22e6c6fb20f\">\r\n\r\n\r\nsubActions corresponds to the different taskTypes Inference API\r\nsupports. Each of the task type has its own Inference Perform params.\r\nCurrently added:\r\n\r\n- completion & completionStream\r\n- rerank\r\n- text_embedding\r\n- sparse_embedding\r\n\r\nFollow up work:\r\n\r\n1. Collapse/expand Additional options, when the connector flyout/modal\r\nhas AI Assistant as a context (path through the extending context\r\nimplementation on the connector framework level)\r\n2. Add support for additional params for Completion subAction to be able\r\nto path functions\r\n3. Add support for tokens usage Dashboard, when inference API will\r\ninclude the used tokens count in the response\r\n4. Add functionality and UX for migration from existing specific AI\r\nconnectors to the Inference connector with proper provider and\r\ncompletion task\r\n5. Integrate Connector with the AI Assistants\r\n\r\n---------\r\n\r\nCo-authored-by: kibanamachine <[email protected]>\r\nCo-authored-by: István Zoltán Szabó <[email protected]>\r\nCo-authored-by: Liam Thompson <[email protected]>\r\nCo-authored-by: Steph Milovic <[email protected]>","sha":"288d41d61ec2389b2e8856da75fd0f3107f9c484"}},"sourceBranch":"main","suggestedTargetBranches":["8.x"],"targetPullRequestStates":[{"branch":"main","label":"v9.0.0","branchLabelMappingKey":"^v9.0.0$","isSourceBranch":true,"state":"MERGED","url":"https://github.com/elastic/kibana/pull/189027","number":189027,"mergeCommit":{"message":"[Connectors][GenAI] Inference Service Kibana connector (elastic#189027)\n\n## Summary\r\nResolves https://github.com/elastic/kibana/issues/188043\r\n\r\nThis PR adds new connector which is define integration with Elastic\r\nInference Endpoint via [Inference\r\nAPIs](https://www.elastic.co/guide/en/elasticsearch/reference/current/inference-apis.html)\r\nThe lifecycle of the Inference Endpoint are managed by the connector\r\nregistered handlers:\r\n\r\n- `preSaveHook` -\r\n[create](https://www.elastic.co/guide/en/elasticsearch/reference/current/put-inference-api.html)\r\nnew Inference Endpoint in the connector create mode (`isEdit === false`)\r\nand\r\n[delete](https://www.elastic.co/guide/en/elasticsearch/reference/current/delete-inference-api.html)+[create](https://www.elastic.co/guide/en/elasticsearch/reference/current/put-inference-api.html)\r\nin the connector edit mode (`isEdit === true`)\r\n- `postSaveHook` - check if the connector SO was created/updated and if\r\nnot removes Inference Endpoint from preSaveHook\r\n- `postDeleteHook` -\r\n[delete](https://www.elastic.co/guide/en/elasticsearch/reference/current/delete-inference-api.html)\r\nInference Endpoint if connector was deleted.\r\n\r\nIn the Kibana Stack Management Connectors, its represented with the new\r\ncard (Technical preview badge):\r\n\r\n<img width=\"1261\" alt=\"Screenshot 2024-09-27 at 2 11 12 PM\"\r\nsrc=\"https://github.com/user-attachments/assets/dcbcce1f-06e7-4d08-8b77-0ba4105354f8\">\r\n\r\nTo simplify the future integration with AI Assistants, the Connector\r\nconsists from the two main UI parts: provider selector and required\r\nprovider settings, which will be always displayed\r\n<img width=\"862\" alt=\"Screenshot 2024-10-07 at 7 59 09 AM\"\r\nsrc=\"https://github.com/user-attachments/assets/87bae493-c642-479e-b28f-6150354608dd\">\r\n\r\nand Additional options, which contains optional provider settings and\r\nTask Type configuration:\r\n\r\n<img width=\"861\" alt=\"Screenshot 2024-10-07 at 8 00 15 AM\"\r\nsrc=\"https://github.com/user-attachments/assets/2341c034-6198-4731-8ce7-e22e6c6fb20f\">\r\n\r\n\r\nsubActions corresponds to the different taskTypes Inference API\r\nsupports. Each of the task type has its own Inference Perform params.\r\nCurrently added:\r\n\r\n- completion & completionStream\r\n- rerank\r\n- text_embedding\r\n- sparse_embedding\r\n\r\nFollow up work:\r\n\r\n1. Collapse/expand Additional options, when the connector flyout/modal\r\nhas AI Assistant as a context (path through the extending context\r\nimplementation on the connector framework level)\r\n2. Add support for additional params for Completion subAction to be able\r\nto path functions\r\n3. Add support for tokens usage Dashboard, when inference API will\r\ninclude the used tokens count in the response\r\n4. Add functionality and UX for migration from existing specific AI\r\nconnectors to the Inference connector with proper provider and\r\ncompletion task\r\n5. Integrate Connector with the AI Assistants\r\n\r\n---------\r\n\r\nCo-authored-by: kibanamachine <[email protected]>\r\nCo-authored-by: István Zoltán Szabó <[email protected]>\r\nCo-authored-by: Liam Thompson <[email protected]>\r\nCo-authored-by: Steph Milovic <[email protected]>","sha":"288d41d61ec2389b2e8856da75fd0f3107f9c484"}},{"branch":"8.x","label":"v8.16.0","branchLabelMappingKey":"^v8.16.0$","isSourceBranch":false,"state":"NOT_CREATED"}]}] BACKPORT--> Co-authored-by: Yuliia Naumenko <[email protected]>
- Loading branch information