Skip to main content
Perform a basic vector search:
object
The search results from the R2R system.
string
required
The search query.
VectorSearchSettings | Record<string, any>
default:"None"
Optional settings for vector search, either a dictionary, a VectorSearchSettings object, or None may be passed. If a dictionary or None is passed, then R2R will use server-side defaults for non-specified fields.
Optional[Union[KGSearchSettings, dict]]
default:"None"
Optional settings for knowledge graph search, either a dictionary, a KGSearchSettings object, or None may be passed. If a dictionary or None is passed, then R2R will use server-side defaults for non-specified fields.

Search custom settings

Search with custom settings, such as bespoke document filters and larger search limits
Combine traditional keyword-based search with vector search:
Utilize knowledge graph capabilities to enhance search results:
object
The knowledge graph search results from the R2R system.

Retrieval-Augmented Generation (RAG)

Basic RAG

Generate a response using RAG:
dict
The RAG response from the R2R system.
str
required
The query for RAG.
Optional[Union[VectorSearchSettings, dict]]
default:"None"
Optional settings for vector search, either a dictionary, a VectorSearchSettings object, or None may be passed. If a dictionary is used, non-specified fields will use the server-side default.
Optional[Union[KGSearchSettings, dict]]
default:"None"
Optional settings for knowledge graph search, either a dictionary, a KGSearchSettings object, or None may be passed. If a dictionary or None is passed, then R2R will use server-side defaults for non-specified fields.
Optional[Union[GenerationConfig, dict]]
default:"None"
Optional configuration for LLM to use during RAG generation, including model selection and parameters. Will default to values specified in r2r.toml.
Optional[str]
default:"None"
Optional custom prompt to override the default task prompt.
Optional[bool]
default:"True"
Augment document chunks with their respective document titles?

RAG with custom search settings

Use hybrid search in RAG:

RAG with custom completion LLM

Use a different LLM model for RAG:

Streaming RAG

Stream RAG responses for real-time applications:

Advanced RAG Techniques

R2R supports advanced Retrieval-Augmented Generation (RAG) techniques that can be easily configured at runtime. These techniques include Hypothetical Document Embeddings (HyDE) and RAG-Fusion, which can significantly enhance the quality and relevance of retrieved information. To use an advanced RAG technique, you can specify the search_strategy parameter in your vector search settings:
For a comprehensive guide on implementing and optimizing advanced RAG techniques in R2R, including HyDE and RAG-Fusion, please refer to our Advanced RAG Cookbook.

Customizing RAG

Putting everything together for highly custom RAG functionality:

Agents

Multi-turn agentic RAG

The R2R application includes agents which come equipped with a search tool, enabling them to perform RAG. Using the R2R Agent for multi-turn conversations:
Note that any of the customization seen in AI powered search and RAG documentation above can be applied here.
object
The agent endpoint will return the entire conversation as a response, including internal tool calls.
Array<Message>
required
The array of messages to pass to the RAG agent.
boolean
default:true
Whether to use vector search.
object
Optional filters for the search.
number
default:10
The maximum number of search results to return.
boolean
default:false
Whether to perform a hybrid search (combining vector and keyword search).
boolean
default:false
Whether to use knowledge graph search.
object
Optional configuration for knowledge graph search generation.
GenerationConfig
Optional configuration for RAG generation, including model selection and parameters.
string
Optional custom prompt to override the default task prompt.
boolean
default:true
Whether to include document titles in the context if available.

Multi-turn agentic RAG with streaming

The response from the RAG agent may be streamed directly back:
ReadableStream
The agent endpoint will stream back its response, including internal tool calls.