LLM Search Index

The LLM Search Index task takes a query, which can be a question, statement, or request made in natural language. This query is processed to generate a vector representation, which is then used to search the vector database. The task returns a list of documents with vectors similar to the query vector, providing the closest matches based on the degree of similarity.

Prerequisites

Integrate the required AI model with Orkes Conductor.
Integrate the required vector database with Orkes Conductor.

Task parameters

Configure these parameters for the LLM Search Index task.

Parameter	Description	Required/ Optional
inputParameters.vectorDB	The vector database to retrieve the data. Note: If you haven’t configured the vector database on your Orkes Conductor cluster, navigate to the Integrations tab and configure your required provider.	Required.
inputParameters.index	The index in your vector database to search for relevant embeddings. The terminology of the index field varies depending on the integration: For Weaviate, the index field indicates the collection name. For other integrations, it denotes the index name.	Required.
inputParameters.namespace	Namespaces are separate isolated environments within the database to manage and organize vector data effectively. Enter the namespace the task will utilize. The usage and terminology of the namespace field vary depending on the integration: For Pinecone, the namespace field is applicable. For Weaviate, the namespace field is not applicable. For MongoDB, the namespace field is referred to as “Collection” in MongoDB. For Postgres, the namespace field is referred to as “Table” in Postgres.	Required.
inputParameters.embeddingModelProvider	The LLM provider for the embeddings. Note: If you haven’t configured your AI/LLM provider on your Orkes Conductor cluster, navigate to the Integrations tab and configure your required provider.	Required.
inputParameters.embeddingModel	The embedding model provided by the selected LLM provider.	Required.
inputParameters.query	The search query. A query typically refers to a question, statement, or request made in natural language that is used to search, retrieve, or manipulate data stored in a database.	Required.
inputParameters.maxResults	The maximum number of results to return. Provide a non-zero integer between 1 and 10000.	Required.
inputParameters.dimensions	The size of the vector, which is the number of elements in the vector.	Optional.

The following are generic configuration parameters that can be applied to the task and are not specific to the LLM Search Index task.

Caching parameters

You can cache the task outputs using the following parameters. Refer to Caching Task Outputs for a full guide.

Parameter	Description	Required/ Optional
cacheConfig.ttlInSecond	The time to live in seconds, which is the duration for the output to be cached.	Required if using cacheConfig.
cacheConfig.key	The cache key is a unique identifier for the cached output and must be constructed exclusively from the task’s input parameters. It can be a string concatenation that contains the task’s input keys, such as `${uri}-${method}` or `re_${uri}_${method}`.	Required if using cacheConfig.

Other generic parameters

Here are other parameters for configuring the task behavior.

Parameter	Description	Required/ Optional
optional	Whether the task is optional. If set to`true`, any task failure is ignored, and the workflow continues with the task status updated to `COMPLETED_WITH_ERRORS`. However, the task must reach a terminal state. If the task remains incomplete, the workflow waits until it reaches a terminal state before proceeding.	Optional.

Task configuration

This is the task configuration for an LLM Search Index task.

{
     "name": "llm_search_index",
     "taskReferenceName": "llm_search_index_ref",
     "inputParameters": {
       "vectorDB": "Pinecone",
       "index": "doc",
       "namespace": "docs",
       "embeddingModelProvider": "openAI",
       "embeddingModel": "text-embedding-3-large",
       "query": "${workflow.input.query}",
       "maxResults": 10,
       "dimensions": 3024
     },
     "type": "LLM_SEARCH_INDEX"
}

Task output

The LLM Search Index task will return the following parameters.

Parameter	Description
result	A JSON array containing the results of the query.
score	Represents a value quantifying the degree of likeness between a specific item and a query vector, facilitating ranking and ordering of results. Higher scores denote stronger relevance to the query vector.
metadata	An object containing additional metadata related to the retrieved document.
docId	The unique identifier of the queried document.
parentDocId	An identifier that denotes a parent document in hierarchical or relational data structures.
text	The actual content retrieved.

Examples

Here are some examples for using the LLM Search Index task.

Using an LLM Search Index task in a workflow

See an example of building a document retrieval workflow using Orkes Conductor.