SearchType

Enum defining the available search modes for cognee.search().

from cognee import SearchType

results = await cognee.search("query", query_type=SearchType.GRAPH_COMPLETION)

Values

Value	Description
`SearchType.SUMMARIES`	Pre-generated hierarchical summaries of content.
`SearchType.CHUNKS`	Raw text segments matching semantically.
`SearchType.RAG_COMPLETION`	Traditional RAG: retrieve chunks, then LLM answer.
`SearchType.TRIPLET_COMPLETION`	Retrieve via triplet relationships, then LLM answer.
`SearchType.GRAPH_COMPLETION`	Default. Full graph context with LLM completion. (default)
`SearchType.GRAPH_SUMMARY_COMPLETION`	Graph context with summary-enhanced completion.
`SearchType.CYPHER`	Direct Cypher query against the graph database.
`SearchType.NATURAL_LANGUAGE`	Natural language translated to Cypher.
`SearchType.GRAPH_COMPLETION_COT`	Graph completion with chain-of-thought reasoning.
`SearchType.GRAPH_COMPLETION_CONTEXT_EXTENSION`	Graph completion with extended context window.
`SearchType.FEELING_LUCKY`	Auto-select the best search type for the query.
`SearchType.TEMPORAL`	Temporal-aware search for time-sensitive queries.
`SearchType.CODING_RULES`	Code-specific retrieval (coding rules, codebase search).
`SearchType.CHUNKS_LEXICAL`	Token-based lexical chunk search (e.g. Jaccard similarity).

I want an LLM-generated answer grounded in my data

Use GRAPH_COMPLETION (default) for the best balance of accuracy and context. Use RAG_COMPLETION for a simpler chunk-based approach.

I want raw data, not an LLM answer

Use CHUNKS for semantic chunk retrieval or CHUNKS_LEXICAL for keyword-based. Use SUMMARIES for pre-generated summaries.

I want to query the graph directly

Use CYPHER for raw Cypher queries or NATURAL_LANGUAGE to have cognee translate your question to Cypher.

I'm not sure which to use

Use FEELING_LUCKY — cognee will pick the best search type for your query.

I need more accurate or comprehensive answers from the graph

All four graph-completion modes retrieve graph triplets and generate an LLM answer, but they differ in depth and latency:

Mode	Strategy	Best for	Trade-off
`GRAPH_COMPLETION`	Single-pass retrieval + completion	Most queries — good accuracy, low latency	Baseline
`GRAPH_SUMMARY_COMPLETION`	Graph context condensed via summaries before completion	Noisy or large graphs where a tighter context improves coherence	Slightly slower; summary quality matters
`GRAPH_COMPLETION_COT`	Iterative: retrieve → answer → validate → follow-up (up to `max_iter` rounds, default 4)	Complex multi-hop questions where stepwise reasoning helps	Higher latency; more LLM calls
`GRAPH_COMPLETION_CONTEXT_EXTENSION`	Iterative: retrieve → generate → use output as new query (up to `context_extension_rounds`, default 4)	Open-ended or exploratory queries needing a broader subgraph	Higher latency; early convergence stops extra rounds