Search R2R

1 from r2r import R2RClient 2 3 client = R2RClient() 4 # if using auth, do client.login(...) 5 6 # Basic search 7 response = client.retrieval.search( 8 query="What is DeepSeek R1?", 9 ) 10 11 # Advanced mode with specific filters 12 response = client.retrieval.search( 13 query="What is DeepSeek R1?", 14 search_mode="advanced", 15 search_settings={ 16 "filters": {"document_id": {"$eq": "e43864f5-a36f-548e-aacd-6f8d48b30c7f"}}, 17 "limit": 5 18 } 19 ) 20 21 # Using hybrid search 22 response = client.retrieval.search( 23 query="What was Uber's profit in 2020?", 24 search_settings={ 25 "use_hybrid_search": True, 26 "hybrid_settings": { 27 "full_text_weight": 1.0, 28 "semantic_weight": 5.0, 29 "full_text_limit": 200, 30 "rrf_k": 50 31 }, 32 "filters": {"title": {"$in": ["DeepSeek_R1.pdf"]}}, 33 } 34 ) 35 36 # Advanced filtering 37 results = client.retrieval.search( 38 query="What are the effects of climate change?", 39 search_settings={ 40 "filters": { 41 "$and":[ 42 {"document_type": {"$eq": "pdf"}}, 43 {"metadata.year": {"$gt": 2020}} 44 ] 45 }, 46 "limit": 10 47 } 48 ) 49 50 # Knowledge graph enhanced search 51 results = client.retrieval.search( 52 query="What was DeepSeek R1", 53 )

1 { 2 "results": { 3 "chunk_search_results": [ 4 { 5 "id": "3f3d47f3-8baf-58eb-8bc2-0171fb1c6e09", 6 "document_id": "3e157b3a-8469-51db-90d9-52e7d896b49b", 7 "collection_ids": [ 8 "collection_ids" 9 ], 10 "text": "Example text from the document", 11 "metadata": { 12 "associated_query": "What is the capital of France?", 13 "title": "example_document.pdf" 14 }, 15 "owner_id": "2acb499e-8428-543b-bd85-0d9098718220", 16 "score": 0.23943702876567796 17 } 18 ], 19 "graph_search_results": [ 20 { 21 "content": { 22 "id": "3f3d47f3-8baf-58eb-8bc2-0171fb1c6e09", 23 "name": "Entity Name", 24 "description": "Entity Description", 25 "metadata": { 26 "key": "value" 27 } 28 }, 29 "id": "id", 30 "result_type": "entity", 31 "chunk_ids": [ 32 "c68dc72e-fc23-5452-8f49-d7bd46088a96" 33 ], 34 "metadata": { 35 "associated_query": "What is the capital of France?" 36 } 37 } 38 ], 39 "web_search_results": [ 40 { 41 "position": 1, 42 "id": "id", 43 "title": "Page Title", 44 "link": "https://example.com/page", 45 "snippet": "Page snippet", 46 "date": "2021-01-01", 47 "sitelinks": [ 48 { 49 "link": "https://example.com/sitelink", 50 "title": "Sitelink Title" 51 } 52 ] 53 } 54 ], 55 "document_search_results": [ 56 { 57 "id": "id", 58 "collection_ids": [ 59 "collection_ids" 60 ], 61 "owner_id": "owner_id", 62 "document_type": "mp3", 63 "metadata": { 64 "key": "value" 65 }, 66 "version": "version" 67 } 68 ] 69 } 70 }

Perform a search query against vector and/or graph-based databases.

Search Modes:

basic: Defaults to semantic search. Simple and easy to use.
advanced: Combines semantic search with full-text search for more comprehensive results.
custom: Complete control over how search is performed. Provide a full SearchSettings object.

Filters: Apply filters directly inside search_settings.filters. For example:

1 {
2 "filters": {"document_id": {"$eq": "e43864f5-a36f-548e-aacd-6f8d48b30c7f"}}
3 }

Supported operators: $eq, $neq, $gt, $gte, $lt, $lte, $like, $ilike, $in, $nin.

Hybrid Search: Enable hybrid search by setting use_hybrid_search: true in search_settings. This combines semantic search with keyword-based search for improved results. Configure with hybrid_settings:

1 {
2 "use_hybrid_search": true,
3 "hybrid_settings": {
4     "full_text_weight": 1.0,
5     "semantic_weight": 5.0,
6     "full_text_limit": 200,
7     "rrf_k": 50
8 }
9 }

Graph-Enhanced Search: Knowledge graph integration is enabled by default. Control with graph_search_settings:

1 {
2 "graph_search_settings": {
3     "use_graph_search": true,
4     "kg_search_type": "local"
5 }
6 }

Advanced Filtering: Use complex filters to narrow down results by metadata fields or document properties:

1 {
2 "filters": {
3     "$and":[
4         {"document_type": {"$eq": "pdf"}},
5         {"metadata.year": {"$gt": 2020}}
6     ]
7 }
8 }

Results: The response includes vector search results and optional graph search results. Each result contains the matched text, document ID, and relevance score.

Perform a search query against vector and/or graph-based databases. **Search Modes:** - `basic`: Defaults to semantic search. Simple and easy to use. - `advanced`: Combines semantic search with full-text search for more comprehensive results. - `custom`: Complete control over how search is performed. Provide a full `SearchSettings` object. **Filters:** Apply filters directly inside `search_settings.filters`. For example: ```json { "filters": {"document_id": {"$eq": "e43864f5-a36f-548e-aacd-6f8d48b30c7f"}} } ``` Supported operators: `$eq`, `$neq`, `$gt`, `$gte`, `$lt`, `$lte`, `$like`, `$ilike`, `$in`, `$nin`. **Hybrid Search:** Enable hybrid search by setting `use_hybrid_search: true` in search_settings. This combines semantic search with keyword-based search for improved results. Configure with `hybrid_settings`: ```json { "use_hybrid_search": true, "hybrid_settings": { "full_text_weight": 1.0, "semantic_weight": 5.0, "full_text_limit": 200, "rrf_k": 50 } } ``` **Graph-Enhanced Search:** Knowledge graph integration is enabled by default. Control with `graph_search_settings`: ```json { "graph_search_settings": { "use_graph_search": true, "kg_search_type": "local" } } ``` **Advanced Filtering:** Use complex filters to narrow down results by metadata fields or document properties: ```json { "filters": { "$and":[ {"document_type": {"$eq": "pdf"}}, {"metadata.year": {"$gt": 2020}} ] } } ``` **Results:** The response includes vector search results and optional graph search results. Each result contains the matched text, document ID, and relevance score.

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Request

This endpoint expects an object.

querystringRequired

Search query to find relevant documents

search_modeenumOptional

Default value of custom allows full control over search settings.

Pre-configured search modes: basic: A simple semantic-based search. advanced: A more powerful hybrid search combining semantic and full-text. custom: Full control via search_settings.

If filters or limit are provided alongside basic or advanced, they will override the default settings for that mode.

Default value of `custom` allows full control over search settings. Pre-configured search modes: `basic`: A simple semantic-based search. `advanced`: A more powerful hybrid search combining semantic and full-text. `custom`: Full control via `search_settings`. If `filters` or `limit` are provided alongside `basic` or `advanced`, they will override the default settings for that mode.

Allowed values:

search_settingsobjectOptional

The search configuration object. If search_mode is custom, these settings are used as-is. For basic or advanced, these settings will override the default mode configuration.

Common overrides include filters to narrow results and limit to control how many results are returned.

Response

Successful Response

resultsobject

Result of an aggregate search operation.

Authentication

Headers

Request

Response

Errors

1	{
2	"filters": {"document_id": {"$eq": "e43864f5-a36f-548e-aacd-6f8d48b30c7f"}}
3	}

1	{
2	"use_hybrid_search": true,
3	"hybrid_settings": {
4	"full_text_weight": 1.0,
5	"semantic_weight": 5.0,
6	"full_text_limit": 200,
7	"rrf_k": 50
8	}
9	}

1	{
2	"graph_search_settings": {
3	"use_graph_search": true,
4	"kg_search_type": "local"
5	}
6	}

1	{
2	"filters": {
3	"$and":[
4	{"document_type": {"$eq": "pdf"}},
5	{"metadata.year": {"$gt": 2020}}
6	]
7	}
8	}