> ## Documentation Index > Fetch the complete documentation index at: https://developer.watson-orchestrate.ibm.com/llms.txt > Use this file to discover all available pages before exploring further. # Creating knowledge bases With the ADK, you can create knowledge bases for your agents, either by connecting to your own Elasticsearch or Milvus instance, or by uploading your documents. Use YAML, JSON or Python files to create your knowledge bases for watsonx Orchestrate. ## Creating built-in Milvus knowledge bases If you don't have an existing Milvus or Elasticsearch instance to connect to, you can create a knowledge base by simply uploading your documents. These documents will be ingested into the built-in Milvus instance, which will serve as the backend for your knowledge base. The supported documents must follow these requirements: * Each file must have a unique name. * You can include up to 100 files in a single knowledge YAML file. * The maximum file size for `.xlsx` files is 1 MB. * The maximum file size for `.docx`, `.pdf`, and `.pptx` files is 25 MB. * The maximum file size for `.csv`, `.html`, and `.txt` files is 5 MB. The embedding model can be either a model hosted on watsonx.ai or a [custom model](../llm/managing_llm#adding-custom-llm) of type embedding. **Note:** The `embeddings_model_name` field is optional. If you don’t provide it, the system uses `ibm/slate-125m-english-rtrvr-v2` by default. **Example using an OpenAI embedding model:** ```yaml YAML [expandable] theme={null} spec_version: v1 kind: knowledge_base name: knowledge_base_name description: | A description of what information this knowledge base addresses documents: - path: IBM_wikipedia.pdf url: https://url/IBM - path: history_of_ibm.pdf url: https://url/History_of_IBM vector_index: embeddings_model_name: virtual-model/openai/text-embedding-3-small ``` ```json JSON [expandable] theme={null} { "spec_version": "v1", "kind": "knowledge_base", "name": "knowledge_base_name", "description": "A description of what information this knowledge base addresses\n", "documents": [ { "path": "IBM_wikipedia.pdf", "url": "https://url/IBM" }, { "path": "history_of_ibm.pdf", "url": "https://url/History_of_IBM" } ], "vector_index": { "embeddings_model_name": "virtual-model/openai/text-embedding-3-small" } } ``` ```python Python [expandable] theme={null} from ibm_watsonx_orchestrate.agent_builder.knowledge_bases.knowledge_base import KnowledgeBase knowledge_base = KnowledgeBase( name="knowledge_base_name", description="A description of what information this knowledge base addresses", documents=["/file-path-1.pdf", "relative-path/file-path-2.pdf"], vector_index={       "embeddings_model_name": "virtual-model/openai/text-embedding-3-small"    } ) ``` **Example using a watsonx.ai embedding model:** ```yaml YAML [expandable] theme={null} spec_version: v1 kind: knowledge_base name: knowledge_base_name description: | A description of what information this knowledge base addresses documents: - "/file-path-1.pdf" - "relative-path/file-path-2.pdf" vector_index: embeddings_model_name: ibm/slate-125m-english-rtrvr-v2 ``` ```json JSON [expandable] theme={null} { "spec_version": "v1", "kind": "knowledge_base", "name": "knowledge_base_name", "description": "A description of what information this knowledge base addresses", "documents": [ "/file-path-1.pdf", "relative-path/file-path-2.pdf" ], "vector_index": {     "embeddings_model_name": "ibm/slate-125m-english-rtrvr-v2"   } } ``` ```python Python [expandable] theme={null} from ibm_watsonx_orchestrate.agent_builder.knowledge_bases.knowledge_base import KnowledgeBase knowledge_base = KnowledgeBase( name="knowledge_base_name", description="A description of what information this knowledge base addresses", documents=["/file-path-1.pdf", "relative-path/file-path-2.pdf"], vector_index={       "embeddings_model_name": "ibm/slate-125m-english-rtrvr-v2"    } ) ``` Once the knowledge base is created, you can check its [status](https://developer.watson-orchestrate.ibm.com/knowledge_base/manage_kb#getting-knowledge-base-status) to see when it’s ready for use. ## Creating external knowledge bases External knowledge bases allow you to connect your existing Milvus or Elasticsearch databases as a knowledge source for your agent. To configure a knowledge base with your external database, use the `conversational_search_tool.index_config` to define the connection details for your Milvus or Elasticsearch instance. Use the `field_mapping` in your `index_config` to to specify which fields from the search results are used for the `title`, `body` and optionally `url` of the search result ### Milvus When connecting to a Milvus instance: Ensure the provided `embedding_model_id` is the one used when ingesting the documents in your index. Additionally, ensure you use the **GRPC** host and port from your Milvus instance Connections will fail if you use the HTTP host or port. Optionally, provide the `server_cert` to use a custom server certificate when connecting to a Milvus instance. ```yaml YAML [expandable] theme={null} spec_version: v1 kind: knowledge_base name: knowledge_base_name description: | A description of what information this knowledge base addresses prioritize_built_in_index: false conversational_search_tool: index_config: - milvus: grpc_host: my.grpc-host.com grpc_port: "1234" server_cert: database: database-name collection: collection-or-alias-name index: index-name embedding_model_id: ibm/slate-125m-english-rtrvr filter: field_mapping: title: title-field body: text-field url: url-field ``` ```json JSON [expandable] theme={null} { "spec_version": "v1", "kind": "knowledge_base", "name": "knowledge_base_name", "description": "A description of what information this knowledge base addresses\n", "prioritize_built_in_index": false, "conversational_search_tool": { "index_config": [ { "milvus": { "grpc_host": "my.grpc-host.com", "grpc_port": "1234", "server_cert": "" "database": "database-name", "collection": "collection-or-alias-name", "index": "index-name", "embedding_model_id": "ibm/slate-125m-english-rtrvr", "filter": "", "field_mapping": { "title": "title-field", "body": "text-field", "url": "url-field" } } } ] } } ``` ```python Python [expandable] theme={null} from ibm_watsonx_orchestrate.agent_builder.knowledge_bases.knowledge_base import KnowledgeBase from ibm_watsonx_orchestrate.agent_builder.knowledge_bases.types import ConversationalSearchConfig, IndexConnection, MilvusConnection, FieldMapping knowledge_base = KnowledgeBase( name="knowledge_base_name", description="A description of what information this knowledge base addresses", conversational_search_tool=ConversationalSearchConfig( index_config=[ IndexConnection(milvus=MilvusConnection( grpc_host="my.grpc-host.com", grpc_port="1234", server_cert: "" database="database-name", collection="collection-or-alias-name", index="index-name", embedding_model_id="ibm/slate-125m-english-rtrvr", filter="", field_mapping=FieldMapping( title="title-field", body="text-field", url="url-field" ) )) ] ) ) ``` ### ElasticSearch For Elasticsearch, you can provide a custom `query_body` that will be sent as the POST body in the search request. This allows for advanced query customization. * If provided, the `query_body` must include the **\$QUERY** token, which will be replaced by the user's query at runtime. * If no custom `query_body` is provided, a keyword search will be used. To further customize the ElasticSearch query, `result_filter` can be set to an array of ElasticSearch filters. If using both `query_body` and `result_filter`, the `query_body` must include the **\$FILTER** token, which will be replaced by the `result_filter` array at runtime. ```yaml YAML [expandable] theme={null} spec_version: v1 kind: knowledge_base name: knowledge_base_name description: | A description of what information this knowledge base addresses prioritize_built_in_index: false conversational_search_tool: index_config: - elastic_search: url: https://my.elasticsearch-instance.com index: my-index-name port: "1234" query_body: {"size":10,"query":{"bool":{"should":[{"text_expansion":{"ml.tokens":{"model_id":".elser_model_2_linux-x86_64","model_text":"$QUERY"}}}],"filter":"$FILTER"}}} result_filter: [{"match":{"title":"A_keyword_in_title"}},{"match":{"text":"A_keyword_in_text"}},{"match":{"id":"A_specific_ID"}}] field_mapping: title: title-field body: text-field url: url-field ``` ```json JSON [expandable] theme={null} { "spec_version": "v1", "kind": "knowledge_base", "name": "knowledge_base_name", "description": "A description of what information this knowledge base addresses", "prioritize_built_in_index": false, "conversational_search_tool": { "index_config": [ { "elastic_search": { "url": "https://my.elasticsearch-instance.com", "index": "my-index-name", "port": "1234", "query_body": { "size": 10, "query": { "bool": { "should": [ { "text_expansion": { "ml.tokens": { "model_id": ".elser_model_2_linux-x86_64", "model_text": "$QUERY" } } } ], "filter": "$FILTER" } } }, "result_filter": [ { "match": { "title": "A_keyword_in_title" } }, { "match": { "text": "A_keyword_in_text" } }, { "match": { "id": "A_specific_ID" } } ], "field_mapping": { "title": "title-field", "body": "text-field", "url": "url-field" } } } ] } } ``` ```python Python [expandable] theme={null} from ibm_watsonx_orchestrate.agent_builder.knowledge_bases.knowledge_base import KnowledgeBase from ibm_watsonx_orchestrate.agent_builder.knowledge_bases.types import ConversationalSearchConfig, IndexConnection, ElasticSearchConnection, FieldMapping knowledge_base = KnowledgeBase( name="knowledge_base_name", description="A description of what information this knowledge base addresses", conversational_search_tool=ConversationalSearchConfig( index_config=[ IndexConnection(elastic_search=ElasticSearchConnection( url="https://my.elasticsearch-instance.com", index="my-index-name", port="1234", query_body={ "size": 10, "query": { "bool": { "should": [ { "text_expansion": { "ml.tokens": { "model_id": ".elser_model_2_linux-x86_64", "model_text": "$QUERY" } } } ], "filter": "$FILTER" } } }, result_filter=[ { "match": { "title": "A_keyword_in_title" } }, { "match": { "text": "A_keyword_in_text" } }, { "match": { "id": "A_specific_ID" } } ], field_mapping=FieldMapping( title="title-field", body="text-field", url="url-field" ) )) ] ) ) ``` For more information about ElasticSearch query body and filters customizations, see [How to configure the advanced Elasticsearch settings](https://github.com/watson-developer-cloud/assistant-toolkit/blob/master/integrations/extensions/docs/elasticsearch-install-and-setup/how_to_configure_advanced_elasticsearch_settings.md) ### Custom search With custom search, you can connect your own search server, enabling out-of-the-box alternatives to the default search solutions. To set up a custom search, configure the **URL** and optionally the **filter** and **metadata** for your search. For example: ```yaml YAML [expandable] theme={null} spec_version: v1 kind: knowledge_base name: knowledge_base_name description: | A description of what information this knowledge base addresses prioritize_built_in_index: false conversational_search_tool: index_config: - custom_search: url: https://my.custom-server.com filter: my custom filter metadata: foo: bar ``` ```json JSON [expandable] theme={null} { "spec_version": "v1", "kind": "knowledge_base", "name": "knowledge_base_name", "description": "A description of what information this knowledge base addresses", "prioritize_built_in_index": false, "conversational_search_tool": { "index_config": [ { "custom_search": { "url": "https://my.custom-server.com", "filter": "my custom filter", "metadata": { "foo": "bar" } } } ] } } ``` ```python Python [expandable] theme={null} from ibm_watsonx_orchestrate.agent_builder.knowledge_bases.knowledge_base import KnowledgeBase from ibm_watsonx_orchestrate.agent_builder.knowledge_bases.types import ConversationalSearchConfig, IndexConnection, CustomSearchConnection knowledge_base = KnowledgeBase( name="knowledge_base_name", description="A description of what information this knowledge base addresses", conversational_search_tool=ConversationalSearchConfig( index_config=[ IndexConnection(custom_search=CustomSearchConnection( url="https://my.custom-server.com", filter="my custom filter", metadata={ "foo": "bar" } )) ] ) ) ``` Some custom search configurations require authentication. In that case, create a connection and pass it along with the knowledge base when you import it. To set up the server for your custom service, see [Connecting to a content repository on a custom service](https://www.ibm.com/docs/en/watsonx/watson-orchestrate/base?topic=agents-connecting-custom-service-repository#setup-retrieval). ### AstraDB To connect to AstraDB knowledge base, in your knowledge base file, configure the `api_endpoint`, `data_type`, and `embedding_mode` for your AstraDB. You can also configure optional fields like `port`, `server_cert`, `keyspace`, `collection`, `table`, `index_column`, `embedding_model_id`, `search_mode`, `limit`, `filter`, and `field_mapping`. ```yaml YAML [expandable] theme={null} spec_version: v1 kind: knowledge_base name: knowledge_base_name description: | A description of what information this knowledge base addresses prioritize_built_in_index: false conversational_search_tool: index_config: - astradb: api_endpoint: 'https://xxx-us-east-2.apps.astra.datastax.com' keyspace: default_keyspace data_type: collection ## Possible values: `collection` or `table` collection: search_wa_docs ## table: search_wa_docs (Only if `data_type` is `table`) ## index_column: 1 (Only if `data_type` is `table`) embedding_model_id: ibm/slate-125m-english-rtrvr embedding_mode: server ## Possible values: `server` or `client` port: '443' search_mode: vector ## Possible values: `vector` when `data_type` is `table` OR `vector`, `lexical`, and `hybrid` when `data_type` is `collection` filter: '{"product_partNumber": "PS-SL-KIT"}' limit: 5 field_mapping: title: title body: text url: some-url ``` ```json JSON [expandable] theme={null} { "spec_version": "v1", "kind": "knowledge_base", "name": "knowledge_base_name", "description": "A description of what information this knowledge base addresses\n", "prioritize_built_in_index": false, "conversational_search_tool": { "index_config": [ { "astradb": { "api_endpoint": "https://xxx-us-east-2.apps.astra.datastax.com", "keyspace": "default_keyspace", "data_type": "collection", "collection": "search_wa_docs", "embedding_model_id": "ibm/slate-125m-english-rtrvr", "embedding_mode": "server", "port": "443", "search_mode": "vector", "filter": "{\"product_partNumber\": \"PS-SL-KIT\"}", "limit": 5, "field_mapping": { "title": "title", "body": "text", "url": "some-url" } } } ] } } ``` ### OpenSearch To connect to an OpenSearch knowledge base, configure the required url and index. You can also set optional fields like `port`, `text_field`, `vector_field`, `embedding_mode`, `embedding_model_id`, `search_mode`, `query_body`, `result_filter`, and `field_mapping`. ```yaml YAML [expandable] theme={null} spec_version: v1 kind: knowledge_base name: os_kb_hybrid_server_default_pipeline_default_model description: are there monthly maintenance fees? vector_index: embeddings_model_name: ibm/slate-125m-english-rtrvr-v2 chunk_size: 400 chunk_overlap: 50 extraction_strategy: standard conversational_search_tool: language: en index_config: - open_search: url: https://search-wo-opensearch-dev-byo-klgika4kflruyuzps5l2a3onbq.us-east-1.es.amazonaws.com index: index-hybrid-server-default-pipeline-default-model port: '443' search_mode: hybrid embedding_mode: server vector_field: passage_embedding text_field: passage_text field_mapping: title: title body: passage_text prioritize_built_in_index: false representation: tool ``` ```json JSON [expandable] theme={null} { "spec_version": "v1", "kind": "knowledge_base", "name": "os_kb_hybrid_server_default_pipeline_default_model", "description": "are there monthly maintenance fees?", "vector_index": { "embeddings_model_name": "ibm/slate-125m-english-rtrvr-v2", "chunk_size": 400, "chunk_overlap": 50, "extraction_strategy": "standard" }, "conversational_search_tool": { "language": "en", "index_config": [ { "open_search": { "url": "https://search-wo-opensearch-dev-byo-klgika4kflruyuzps5l2a3onbq.us-east-1.es.amazonaws.com", "index": "index-hybrid-server-default-pipeline-default-model", "port": "443", "search_mode": "hybrid", "embedding_mode": "server", "vector_field": "passage_embedding", "text_field": "passage_text", "field_mapping": { "title": "title", "body": "passage_text" } } } ] }, "prioritize_built_in_index": false, "representation": "tool" } ``` ## Configuring dynamic input and output for external knowledge bases To define dynamic retrieval inputs for the agent, use `input_schema` in `conversational_search_tool`. This schema defines structured input parameters that the agent can fill at runtime and use in the query configuration. If you use `input_schema` with `result_filter`, reference the configured input fields with placeholders in the format `{field_name}`. At runtime, the system replaces each placeholder with the value that the agent provides for that field. If an input field name matches an existing context variable, the input `{field_name}` overwrites the context variable with the same name. Use `custom_fields` in `field_mapping` to include additional fields from the search response in the output that goes to the agent. **Example:** ```yaml ElasticSearch [expandable] theme={null} spec_version: v1 kind: knowledge_base name: conversational_search_tool description: Search product support content filtered by category conversational_search_tool: language: en query_source: Agent input_schema: type: object properties: category: type: string description: 'Filter results by category: general, hardware, or software.' default: "general" enum: ["general", "hardware", "software"] index_config: - elastic_search: url: https://example-elasticsearch.example.com index: sample_support_index port: '9200' query_body: query: bool: filter: $FILTER should: - text_expansion: ml.tokens: model_id: .elser_model_2_linux-x86_64 model_text: $QUERY result_filter: - bool: should: - term: metadata.category: general - term: metadata.category: '{category}' minimum_should_match: 1 field_mapping: title: title body: body url: url custom_fields: category: metadata.category ``` ```yaml Milvus [expandable] theme={null} spec_version: v1 kind: knowledge_base name: sample_milvus_kb description: Search product support content filtered by category prioritize_built_in_index: false conversational_search_tool: query_source: Agent input_schema: type: object properties: category: type: string description: 'Filter results by category: general, hardware, or software.' default: "" index_config: - milvus: grpc_host: sample-milvus.example.com grpc_port: "19530" database: "default" collection: "sample_support_collection" index: "vector" embedding_model_id: "ibm/slate-125m-english-rtrvr-v2" filter: 'category like "%{category}%"' limit: 10 field_mapping: title: 'title' body: 'body' custom_fields: category: 'category' ``` ```yaml OpenSearch [expandable] theme={null} spec_version: v1 kind: knowledge_base name: sample_opensearch_kb description: Search product support content filtered by category prioritize_built_in_index: false conversational_search_tool: query_source: Agent input_schema: type: object properties: category: type: string description: 'Filter results by category: general, hardware, or software.' default: "general" generation: enabled: true index_config: - open_search: url: https://example-opensearch.example.com index: sample_support_index port: "9200" filter: [{"match": {"category": "{category}"}}] field_mapping: title: "title" body: "body" custom_fields: category: "category" ``` ```yaml CustomSearch [expandable] theme={null} spec_version: v1 kind: knowledge_base name: custom_search_kb description: Search product support content filtered by category prioritize_built_in_index: false conversational_search_tool: query_source: Agent input_schema: type: object properties: category: type: string description: 'Filter results by category: general, hardware, or software.' default: "" query_source: Agent generation: enabled: false index_config: - custom_search: url: https://example-custom-search.example.com field_mapping: title: "title" body: "body" custom_fields: category: "category" ``` ```yaml AstraDB [expandable] theme={null} spec_version: v1 kind: knowledge_base name: astradb_kb description: Search product support content filtered by category prioritize_built_in_index: false conversational_search_tool: query_source: Agent input_schema: type: object properties: category: type: string description: 'Filter results by category: general, hardware, or software.' default: "" index_config: - astradb: api_endpoint: https://example-astra-db.apps.astra.datastax.com data_type: collection collection: sample_support_collection embedding_mode: server search_mode: vector filter: '{"category": "{category}"}' field_mapping: title: "title" body: "body" custom_fields: category: 'category' source: 'source' ``` **Important:** * Dynamic input schema is only available in Agent mode (`query_source: Agent`) * Custom fields can be used with any knowledge base type (Milvus, Elasticsearch, OpenSearch, AstraDB, Custom Search) * Parameter values from `input_schema` are substituted into filters at query time using the `{parameter_name}` syntax ## Configuring generation options With the ADK, you can further fine-tune how your agent uses knowledge through the `conversational_search_tool` configuration in your knowledge base. You can apply these settings to both built-in Milvus knowledge bases and external knowledge bases. Below are the configurable options available within the `conversational_search_tool` section: | Parameter | Description | | -------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `prompt_instruction` | Set this under `generation`. If specified, this instruction will be included in the prompt sent to the language model to guide response generation. | | `max_docs_passed_to_llm` | Set this under `generation`. If specified, define the maximum number of documents passed to the LLM. This field accepts values from `1` to `20`. | | `generated_response_length` | Set this under `generation` to one of `Concise`, `Moderate` or `Verbose`. This setting adjusts the prompt to request responses of the specified length. If not set, the default is `Moderate`. | | `idk_message` | Set this under `generation`. Defines the fallback message sent to the user when the knowledge base cannot provide an answer. | | `retrieval_confidence_threshold` | Set this under `confidence_thresholds` to one of `Off`, `Lowest`, `Low`, `High` or `Highest`. This threshold determines the minimum confidence required that the retrieved documents answer the user's query. If the confidence is below the threshold, the agent will return a default "**I don't know**" response instead of generating a response. The default is "Low". | | `response_confidence_threshold` | Set this under `confidence_thresholds` to one of `Off`, `Lowest`, `Low`, `High` or `Highest`. This threshold evaluates the confidence that both the generated response and the retrieved documents answer the user's query. If the confidence is below the threshold, the agent will return a default "**I don't know**" response. The default is `Low`. | | `query_rewrite` | If enabled, the user's query is rewritten using the context of the conversation to support multi-turn interactions. This setting is enabled by default. | | `citations_shown` | Set this under `citations`. Use the `citations_shown` parameter to control how many citations appear during the interaction. Set a specific number to define the maximum citations displayed. Use `0` to hide all citations, or `-1` to show every available citation. If not set, the default is `-1`, which means all available citations will be displayed | **Note:** In dynamic knowledge bases, only the `max_docs_passed_to_llm` and `citations_shown` parameters apply. All other settings are ignored. ```yaml YAML [expandable] theme={null} spec_version: v1 kind: knowledge_base name: knowledge_base_name description: | A description of what information this knowledge base addresses documents: - "/file-path-1.pdf" - "relative-path/file-path-2.pdf" conversational_search_tool: generation: prompt_instruction: Custom instruction max_docs_passed_to_llm: 10 generated_response_length: Moderate idk_message: I'm sorry, I don't have enough information to answer that right now. Could you please rephrase or provide more details? confidence_thresholds: retrieval_confidence_threshold: Low response_confidence_threshold: Low query_rewrite: enabled: True citations: citations_shown: -1 ``` ```json JSON [expandable] theme={null} { "spec_version": "v1", "kind": "knowledge_base", "name": "knowledge_base_name", "description": "A description of what information this knowledge base addresses", "documents": [ "/file-path-1.pdf", "relative-path/file-path-2.pdf" ], "conversational_search_tool": { "generation": { "prompt_instruction": "Custom instruction", "max_docs_passed_to_llm": 10, "generated_response_length": "Moderate", "idk_message": "I'm sorry, I don't have enough information to answer that right now. Could you please rephrase or provide more details?" }, "confidence_thresholds": { "retrieval_confidence_threshold": "Low", "response_confidence_threshold": "Low" }, "query_rewrite": { "enabled": true }, "citations": { "citations_shown": -1 } } } ``` ```python Python [expandable] theme={null} from ibm_watsonx_orchestrate.agent_builder.knowledge_bases.knowledge_base import KnowledgeBase from ibm_watsonx_orchestrate.agent_builder.knowledge_bases.types import ConversationalSearchConfig, GenerationConfiguration, GeneratedResponseLength, RetrievalConfidenceThreshold, ResponseConfidenceThreshold, ConfidenceThresholds, QueryRewriteConfig, CitationsConfig knowledge_base = KnowledgeBase( name="knowledge_base_name", description="A description of what information this knowledge base addresses", documents=["/file-path-1.pdf", "relative-path/file-path-2.pdf"], conversational_search_tool=ConversationalSearchConfig( # generation: Optional[GenerationConfiguration] = None generation=GenerationConfiguration( prompt_instruction="Custom instruction", max_docs_passed_to_llm= 10, generated_response_length=GeneratedResponseLength.Moderate ), # confidence_thresholds: Optional[ConfidenceThresholds] = None confidence_thresholds=ConfidenceThresholds( retrieval_confidence_threshold=ResponseConfidenceThreshold.Low, response_confidence_threshold=ResponseConfidenceThreshold.Low ), # query_rewrite: Optional[QueryRewriteConfig] = None query_rewrite=QueryRewriteConfig( enabled=True ), # citations: Optional[CitationsConfig] = None citations=CitationsConfig( citations_shown=-1 ) ) ) ``` ### Configuring knowledge base modes By default, the knowledge base operates in dynamic mode. In this mode, the knowledge base retrieves information from the connected content store, and the agent determines how to use that information. The agent can generate a response, use the retrieved content as context to complete tasks, or supply its own query to the content store. Dynamic mode replaces the earlier classic mode, which followed a linear request-and-response flow. In classic mode, the knowledge base builds a query from the user’s input and the conversation context, retrieves matching content, and generates a response that the agent returns to the user. You can switch between dynamic and classic behavior by updating the configuration file in the `conversational_search_tool` schema. | Parameter | Description | | -------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `query_source` | Defines the query source. Accepted values: | | `generation` | In the `generation` schema, set the `enabled` parameter to `false` to activate dynamic mode. | **Example:** ```yaml YAML [expandable] {10-13} theme={null} spec_version: v1 kind: knowledge_base name: ibm_knowledge_base_dynamic_mode description: General information about IBM and its history documents: - path: IBM_wikipedia.pdf url: https://en.wikipedia.org/wiki/IBM - path: history_of_ibm.pdf url: https://en.wikipedia.org/wiki/History_of_IBM conversational_search_tool: query_source: Agent generation: enabled: False ``` ```json JSON [expandable] {16-21} theme={null} { "spec_version": "v1", "kind": "knowledge_base", "name": "ibm_knowledge_base_dynamic_mode", "description": "General information about IBM and its history", "documents": [ { "path": "IBM_wikipedia.pdf", "url": "https://en.wikipedia.org/wiki/IBM" }, { "path": "history_of_ibm.pdf", "url": "https://en.wikipedia.org/wiki/History_of_IBM" } ], "conversational_search_tool": { "query_source": "Agent", "generation": { "enabled": false } } } ``` ```json Python [expandable] {8-11} theme={null} from ibm_watsonx_orchestrate.agent_builder.knowledge_bases.knowledge_base import KnowledgeBase from ibm_watsonx_orchestrate.agent_builder.knowledge_bases.types import ConversationalSearchConfig knowledge_base = KnowledgeBase( name="knowledge_base_name", description="A description of what information this knowledge base addresses", documents=["/file-path-1.pdf", "relative-path/file-path-2.pdf"], conversational_search_tool=ConversationalSearchConfig( query_source="Agent", generation=GenerationConfiguration(enabled=False) ) ) ```