From 8f32330ea38cd9ed742fc5507ef8d2de3643a868 Mon Sep 17 00:00:00 2001 From: Mike Birnstiehl Date: Mon, 21 Jul 2025 15:47:05 -0500 Subject: [PATCH 1/6] add multilingual functionality --- .../observability-ai-assistant.md | 20 +++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/solutions/observability/observability-ai-assistant.md b/solutions/observability/observability-ai-assistant.md index 4192b4c0e8..e3f6cb0568 100644 --- a/solutions/observability/observability-ai-assistant.md +++ b/solutions/observability/observability-ai-assistant.md @@ -102,7 +102,12 @@ The AI Assistant connects to one of these supported LLM providers: ## Add data to the AI Assistant knowledge base [obs-ai-add-data] -The AI Assistant uses [ELSER](/explore-analyze/machine-learning/nlp/ml-nlp-elser.md), Elastic’s semantic search engine, to recall data from its internal knowledge base index to create retrieval augmented generation (RAG) responses. Adding data such as Runbooks, GitHub issues, internal documentation, and Slack messages to the knowledge base gives the AI Assistant context to provide more specific assistance. +The AI Assistant uses one of the following language models to recall data from its internal knowledge base index to create retrieval augmented generation (RAG) responses: + +* [ELSER](/explore-analyze/machine-learning/nlp/ml-nlp-elser.md): Elastic’s semantic search engine. ELSER is recommended for English-only use cases. +* [E5](/explore-analyze/machine-learning/nlp/): {applies_to}`stack: ga 9.1` A natural language processing model that enables you to perform multilingual semantic search by using dense vector representations. + +Adding data such as Runbooks, GitHub issues, internal documentation, and Slack messages to the knowledge base gives the AI Assistant context to provide more specific assistance. Add data to the knowledge base with one or more of the following methods: @@ -167,7 +172,7 @@ Field names in custom indices have no specific requirements. Any `semantic_text` - Create a connector using the [Connector APIs](https://www.elastic.co/docs/api/doc/elasticsearch/group/endpoint-connector) 2. **Create embeddings** (choose one method): - - [`semantic_text` field](#obs-ai-search-connectors-semantic-text): Recommended workflow which handles model setup automatically + - [`semantic_text` field](#obs-ai-search-connectors-semantic-text): Recommended workflow which handles model setup automatically. Allows the use of any available ML model (Elser, e5, or custom models). - [ML pipeline](#obs-ai-search-connectors-ml-embeddings): Requires manual setup of the ELSER model and inference pipeline #### Option 1: Use a `semantic_text` field type to create embeddings (recommended) [obs-ai-search-connectors-semantic-text] @@ -235,6 +240,17 @@ If asked about a Kubernetes pod, namespace, cluster, location, or owner, return ``` +### Choose the Knowledge Base language model +```{applies_to} +stack: ga 9.1 +``` +Choose the default language model for the AI Assistant in the AI Assistant settings under **Set text embeddings model**. + +* [ELSER](/explore-analyze/machine-learning/nlp/ml-nlp-elser.md): recommended for English-only use cases. +* [E5](/explore-analyze/machine-learning/nlp/ml-nlp-e5.md): supports multilingual use cases. + +Select the language model and click **Update**. If you're switching models, every existing Knowledge Base entry must be reindexed. Entries will be unavailable until they are reindexed. + ## Interact with the AI Assistant [obs-ai-interact] ::::{important} From 625a5d82b83df9637f94e7777898071b57042f49 Mon Sep 17 00:00:00 2001 From: Mike Birnstiehl Date: Mon, 21 Jul 2025 16:01:28 -0500 Subject: [PATCH 2/6] fix link --- solutions/observability/observability-ai-assistant.md | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/solutions/observability/observability-ai-assistant.md b/solutions/observability/observability-ai-assistant.md index e3f6cb0568..425af63380 100644 --- a/solutions/observability/observability-ai-assistant.md +++ b/solutions/observability/observability-ai-assistant.md @@ -105,7 +105,7 @@ The AI Assistant connects to one of these supported LLM providers: The AI Assistant uses one of the following language models to recall data from its internal knowledge base index to create retrieval augmented generation (RAG) responses: * [ELSER](/explore-analyze/machine-learning/nlp/ml-nlp-elser.md): Elastic’s semantic search engine. ELSER is recommended for English-only use cases. -* [E5](/explore-analyze/machine-learning/nlp/): {applies_to}`stack: ga 9.1` A natural language processing model that enables you to perform multilingual semantic search by using dense vector representations. +* [E5](/explore-analyze/machine-learning/nlp/ml-nlp-e5.md): {applies_to}`stack: ga 9.1` A natural language processing model that enables you to perform multilingual semantic search by using dense vector representations. Adding data such as Runbooks, GitHub issues, internal documentation, and Slack messages to the knowledge base gives the AI Assistant context to provide more specific assistance. @@ -215,7 +215,7 @@ After creating the pipeline, complete the following steps: Ask something to the AI Assistant related with the indexed data. -### Add user-specific system prompts +### Add user-specific system prompts [obs-ai-assistant-user-prompt] User-specific prompts customize how the AI assistant responds by appending personalized instructions to built-in system prompts. For example, you could specify "Always respond in French," and all subsequent responses will be in French. @@ -249,7 +249,11 @@ Choose the default language model for the AI Assistant in the AI Assistant setti * [ELSER](/explore-analyze/machine-learning/nlp/ml-nlp-elser.md): recommended for English-only use cases. * [E5](/explore-analyze/machine-learning/nlp/ml-nlp-e5.md): supports multilingual use cases. -Select the language model and click **Update**. If you're switching models, every existing Knowledge Base entry must be reindexed. Entries will be unavailable until they are reindexed. +Select the language model and click **Update**. + +When switching models, every existing Knowledge Base entry must be reindexed. Entries will be unavailable until they are reindexed. + +To have the AI Assistant respond in a language other than English, set a [user specific prompt](#obs-ai-assistant-user-prompt). ## Interact with the AI Assistant [obs-ai-interact] From af4bfffd567e98321e54d224355e7dbad6e0869a Mon Sep 17 00:00:00 2001 From: Mike Birnstiehl Date: Mon, 21 Jul 2025 16:03:15 -0500 Subject: [PATCH 3/6] update list --- solutions/observability/observability-ai-assistant.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/solutions/observability/observability-ai-assistant.md b/solutions/observability/observability-ai-assistant.md index 425af63380..7655f3650b 100644 --- a/solutions/observability/observability-ai-assistant.md +++ b/solutions/observability/observability-ai-assistant.md @@ -172,7 +172,7 @@ Field names in custom indices have no specific requirements. Any `semantic_text` - Create a connector using the [Connector APIs](https://www.elastic.co/docs/api/doc/elasticsearch/group/endpoint-connector) 2. **Create embeddings** (choose one method): - - [`semantic_text` field](#obs-ai-search-connectors-semantic-text): Recommended workflow which handles model setup automatically. Allows the use of any available ML model (Elser, e5, or custom models). + - [`semantic_text` field](#obs-ai-search-connectors-semantic-text): Recommended workflow which handles model setup automatically. - [ML pipeline](#obs-ai-search-connectors-ml-embeddings): Requires manual setup of the ELSER model and inference pipeline #### Option 1: Use a `semantic_text` field type to create embeddings (recommended) [obs-ai-search-connectors-semantic-text] From 281fd093ec1e55bcc5ffb7b89c8c25ecd9ac1ad3 Mon Sep 17 00:00:00 2001 From: Mike Birnstiehl Date: Mon, 21 Jul 2025 16:04:52 -0500 Subject: [PATCH 4/6] add ML model note. --- solutions/observability/observability-ai-assistant.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/solutions/observability/observability-ai-assistant.md b/solutions/observability/observability-ai-assistant.md index 7655f3650b..ff7aedc586 100644 --- a/solutions/observability/observability-ai-assistant.md +++ b/solutions/observability/observability-ai-assistant.md @@ -172,8 +172,8 @@ Field names in custom indices have no specific requirements. Any `semantic_text` - Create a connector using the [Connector APIs](https://www.elastic.co/docs/api/doc/elasticsearch/group/endpoint-connector) 2. **Create embeddings** (choose one method): - - [`semantic_text` field](#obs-ai-search-connectors-semantic-text): Recommended workflow which handles model setup automatically. - - [ML pipeline](#obs-ai-search-connectors-ml-embeddings): Requires manual setup of the ELSER model and inference pipeline + - [`semantic_text` field](#obs-ai-search-connectors-semantic-text): Recommended workflow which handles model setup automatically. Allows the use of any available ML model (Elser, e5, or custom models). + - [ML pipeline](#obs-ai-search-connectors-ml-embeddings): Requires manual setup of the ELSER model and inference pipeline. #### Option 1: Use a `semantic_text` field type to create embeddings (recommended) [obs-ai-search-connectors-semantic-text] From 83bad4fa8501315cda41b85c646b3cedc9b8cf52 Mon Sep 17 00:00:00 2001 From: Mike Birnstiehl Date: Mon, 21 Jul 2025 16:35:55 -0500 Subject: [PATCH 5/6] clarify language --- solutions/observability/observability-ai-assistant.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/solutions/observability/observability-ai-assistant.md b/solutions/observability/observability-ai-assistant.md index ff7aedc586..7adb922e37 100644 --- a/solutions/observability/observability-ai-assistant.md +++ b/solutions/observability/observability-ai-assistant.md @@ -102,9 +102,9 @@ The AI Assistant connects to one of these supported LLM providers: ## Add data to the AI Assistant knowledge base [obs-ai-add-data] -The AI Assistant uses one of the following language models to recall data from its internal knowledge base index to create retrieval augmented generation (RAG) responses: +The AI Assistant uses one of the following language models to recall data from its internal knowledge base index to generate retrieval augmented generation (RAG) responses: -* [ELSER](/explore-analyze/machine-learning/nlp/ml-nlp-elser.md): Elastic’s semantic search engine. ELSER is recommended for English-only use cases. +* [ELSER](/explore-analyze/machine-learning/nlp/ml-nlp-elser.md): Elastic’s semantic search engine, recommended for English-only use cases. * [E5](/explore-analyze/machine-learning/nlp/ml-nlp-e5.md): {applies_to}`stack: ga 9.1` A natural language processing model that enables you to perform multilingual semantic search by using dense vector representations. Adding data such as Runbooks, GitHub issues, internal documentation, and Slack messages to the knowledge base gives the AI Assistant context to provide more specific assistance. @@ -251,7 +251,7 @@ Choose the default language model for the AI Assistant in the AI Assistant setti Select the language model and click **Update**. -When switching models, every existing Knowledge Base entry must be reindexed. Entries will be unavailable until they are reindexed. +When switching models, all existing Knowledge Base entries must be reindexed. Entries will be unavailable until reindexing is complete. To have the AI Assistant respond in a language other than English, set a [user specific prompt](#obs-ai-assistant-user-prompt). From c1c351d4dd1e321bee47a1017ba319e7379e7c52 Mon Sep 17 00:00:00 2001 From: Mike Birnstiehl Date: Mon, 21 Jul 2025 18:35:35 -0500 Subject: [PATCH 6/6] review updates --- solutions/observability/observability-ai-assistant.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/solutions/observability/observability-ai-assistant.md b/solutions/observability/observability-ai-assistant.md index 7adb922e37..6f6a588a86 100644 --- a/solutions/observability/observability-ai-assistant.md +++ b/solutions/observability/observability-ai-assistant.md @@ -102,10 +102,10 @@ The AI Assistant connects to one of these supported LLM providers: ## Add data to the AI Assistant knowledge base [obs-ai-add-data] -The AI Assistant uses one of the following language models to recall data from its internal knowledge base index to generate retrieval augmented generation (RAG) responses: +The AI Assistant uses one of the following text embedding models to run semantic search against the internal knowledge base index. The top results are passed to the LLM as context (retrieval‑augmented generation), producing more accurate and grounded responses: -* [ELSER](/explore-analyze/machine-learning/nlp/ml-nlp-elser.md): Elastic’s semantic search engine, recommended for English-only use cases. -* [E5](/explore-analyze/machine-learning/nlp/ml-nlp-e5.md): {applies_to}`stack: ga 9.1` A natural language processing model that enables you to perform multilingual semantic search by using dense vector representations. +* [ELSER](/explore-analyze/machine-learning/nlp/ml-nlp-elser.md): Recommended for English-only use cases. +* [E5](/explore-analyze/machine-learning/nlp/ml-nlp-e5.md): {applies_to}`stack: ga 9.1` Recommended for non-English use cases. Adding data such as Runbooks, GitHub issues, internal documentation, and Slack messages to the knowledge base gives the AI Assistant context to provide more specific assistance.