Boolean Recall

Full-text search

import requests

url = "https://api.hydradb.com/recall/boolean_recall"

payload = {
    "tenant_id": "tenant_1234",
    "query": "John Smith Jake",
    "sub_tenant_id": "sub_tenant_4567",
    "operator": "and",
    "max_results": 1,
    "search_mode": "sources"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    tenant_id: 'tenant_1234',
    query: 'John Smith Jake',
    sub_tenant_id: 'sub_tenant_4567',
    operator: 'and',
    max_results: 1,
    search_mode: 'sources'
  })
};

fetch('https://api.hydradb.com/recall/boolean_recall', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

curl --request POST \
  --url https://api.hydradb.com/recall/boolean_recall \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "tenant_id": "tenant_1234",
  "query": "John Smith Jake",
  "sub_tenant_id": "sub_tenant_4567",
  "operator": "and",
  "max_results": 1,
  "search_mode": "sources"
}
'

{
  "chunks": [],
  "sources": [
    {
      "id": "HydraDoc1234",
      "title": "<title>",
      "type": "<type>",
      "description": "<description>",
      "url": "<url>",
      "timestamp": "<timestamp>",
      "tenant_metadata": {},
      "document_metadata": {}
    }
  ],
  "graph_context": {
    "query_paths": [],
    "chunk_relations": [],
    "chunk_id_to_group_ids": {}
  },
  "additional_context": {}
}

{
  "detail": {
    "success": false,
    "message": "Error occurred",
    "error_code": "<string>"
  }
}

{
  "detail": {
    "success": false,
    "message": "Error occurred",
    "error_code": "<string>"
  }
}

{
  "detail": {
    "success": false,
    "message": "Error occurred",
    "error_code": "<string>"
  }
}

{
  "detail": {
    "success": false,
    "message": "Error occurred",
    "error_code": "<string>"
  }
}

{
  "detail": {
    "success": false,
    "message": "Error occurred",
    "error_code": "<string>"
  }
}

{
  "detail": {
    "success": false,
    "message": "Error occurred",
    "error_code": "<string>"
  }
}

{
  "detail": {
    "success": false,
    "message": "Error occurred",
    "error_code": "<string>"
  }
}

{
  "detail": {
    "success": false,
    "message": "Error occurred",
    "error_code": "<string>"
  }
}

POST

recall

boolean_recall

Full-text search

import requests

url = "https://api.hydradb.com/recall/boolean_recall"

payload = {
    "tenant_id": "tenant_1234",
    "query": "John Smith Jake",
    "sub_tenant_id": "sub_tenant_4567",
    "operator": "and",
    "max_results": 1,
    "search_mode": "sources"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    tenant_id: 'tenant_1234',
    query: 'John Smith Jake',
    sub_tenant_id: 'sub_tenant_4567',
    operator: 'and',
    max_results: 1,
    search_mode: 'sources'
  })
};

fetch('https://api.hydradb.com/recall/boolean_recall', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

curl --request POST \
  --url https://api.hydradb.com/recall/boolean_recall \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "tenant_id": "tenant_1234",
  "query": "John Smith Jake",
  "sub_tenant_id": "sub_tenant_4567",
  "operator": "and",
  "max_results": 1,
  "search_mode": "sources"
}
'

{
  "chunks": [],
  "sources": [
    {
      "id": "HydraDoc1234",
      "title": "<title>",
      "type": "<type>",
      "description": "<description>",
      "url": "<url>",
      "timestamp": "<timestamp>",
      "tenant_metadata": {},
      "document_metadata": {}
    }
  ],
  "graph_context": {
    "query_paths": [],
    "chunk_relations": [],
    "chunk_id_to_group_ids": {}
  },
  "additional_context": {}
}

{
  "detail": {
    "success": false,
    "message": "Error occurred",
    "error_code": "<string>"
  }
}

{
  "detail": {
    "success": false,
    "message": "Error occurred",
    "error_code": "<string>"
  }
}

{
  "detail": {
    "success": false,
    "message": "Error occurred",
    "error_code": "<string>"
  }
}

{
  "detail": {
    "success": false,
    "message": "Error occurred",
    "error_code": "<string>"
  }
}

{
  "detail": {
    "success": false,
    "message": "Error occurred",
    "error_code": "<string>"
  }
}

{
  "detail": {
    "success": false,
    "message": "Error occurred",
    "error_code": "<string>"
  }
}

{
  "detail": {
    "success": false,
    "message": "Error occurred",
    "error_code": "<string>"
  }
}

{
  "detail": {
    "success": false,
    "message": "Error occurred",
    "error_code": "<string>"
  }
}

When to use it

/recall/boolean_recall runs a BM25-style full-text search. It’s the right tool when:

Exact terms matter – product codes, error codes, legal terms, regulatory IDs
Auditability matters – compliance searches need provable matches, not “semantically similar”
Speed matters – no embedding inference, no graph traversal, no reranking

Use this instead of full_recall when the query is a literal lookup, not a semantic question.

Endpoint

Auth: Bearer token
Idempotency: Read-only
Async: No

Example

curl -X POST 'https://api.hydradb.com/recall/boolean_recall' \
  -H "Authorization: Bearer <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "tenant_id": "my_first_tenant",
    "query": "ERROR_429 rate limit",
    "operator": "and",
    "max_results": 10,
    "search_mode": "sources"
  }'

const result = await client.recall.booleanRecall({
  tenant_id: "my_first_tenant",
  query: "ERROR_429 rate limit",
  operator: "and",
  max_results: 10,
  search_mode: "sources"
});

result = client.recall.boolean_recall(
    tenant_id="my_first_tenant",
    query="ERROR_429 rate limit",
    operator="and",
    max_results=10,
    search_mode="sources",
)

Request parameters

Name	Type	Required	Default	Description
`tenant_id`	string	Yes	–	The tenant to search.
`query`	string	Yes	–	Search terms. Tokenized for matching.
`sub_tenant_id`	string	No	default	Sub-tenant scope.
`operator`	enum	No	`or`	`or` (any term), `and` (all terms), `phrase` (exact phrase in order).
`max_results`	integer	No	`10`	Maximum number of chunks to return.
`search_mode`	enum	No	`sources`	`sources` (knowledge) or `memories` (user memories).

Operators

Operator	Behavior	Example
`or` (default)	Match chunks containing any of the search terms	Query `"refund cancel"` matches chunks with either “refund” or “cancel”
`and`	Match chunks containing all of the search terms	Query `"refund cancel"` matches chunks with both terms
`phrase`	Match chunks containing the exact phrase in order	Query `"refund within 30 days"` matches that exact wording

Response

Same shape as POST /recall/full_recall.

{
  "chunks": [
    {
      "chunk_uuid": "...",
      "source_id": "doc_67890",
      "chunk_content": "If you encounter ERROR_429, you've exceeded the rate limit. Wait and retry.",
      "source_title": "API Error Codes",
      "relevancy_score": 1.0,
      "additional_metadata": { "category": "errors" }
    }
  ],
  "sources": [...]
}

relevancy_score reflects BM25 scoring rather than semantic similarity.

Boolean vs full recall

	`boolean_recall`	`full_recall`
Match type	Exact term/phrase	Semantic similarity
Embeddings	No	Yes
Graph traversal	No	Optional
Reranking	No	Yes (in `thinking` mode)
Best for	Lookups, audits, compliance	Q&A, exploration, RAG
Latency	Lowest	Higher (especially `thinking` mode)

Behavior notes

phrase operator is order-sensitive. “30 days refund” will not match “refund within 30 days.” Use and if you want all terms regardless of order.

For semantic search: Full recall – embeddings + graph

Errors

Common codes: 400 INVALID_PARAMETERS, 404 TENANT_NOT_FOUND, 422 VALIDATION_ERROR, 429 RATE_LIMITED. See Error Responses for the full list. Read more: Essentials → Recall

Authorizations

Authorization

string

header

required

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

Body

application/json

tenant_id

string

required

Unique identifier for the tenant/organization

Example:

"tenant_1234"

query

string

required

Search terms to find in your content

Example:

"John Smith Jake"

sub_tenant_id

string | null

Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.

Example:

"sub_tenant_4567"

operator

enum<string>

default:or

How to combine search terms: 'or' (any term matches), 'and' (all terms must match), 'phrase' (exact phrase must appear)

Available options:

or,

and,

phrase

Example:

"and"

max_results

integer

default:10

Maximum number of results to return

Example:

1

search_mode

enum<string>

default:sources

What to search: 'sources' for documents or 'memories' for user memories

Available options:

sources,

memories

Response

Successful Response

Result of a hybrid search retrieval operation.

chunks

VectorStoreChunk · object[]

Show child attributes

Example:

[]

sources

SourceInfo · object[]

Deduplicated source documents corresponding to the returned chunks

Show child attributes

graph_context

GraphContext · object

Graph context containing query-based paths and chunk-based relation paths.

Show child attributes

additional_context

Additional Context · object

Map of chunk_uuid to VectorStoreChunk for extra context from forcefully related sources. Use chunk.extra_context_ids to look up chunks: extra_context[id] for id in chunk.extra_context_ids.

Show child attributes

API Documentation

Tenants

Knowledge & Memories

Recall

Managing Data

When to use it

Endpoint

Example

Request parameters

Operators

Response

Boolean vs full recall

Behavior notes

Errors

Authorizations

Body

Response

​When to use it

​Endpoint

​Example

​Request parameters

​Operators

​Response

​Boolean vs full recall

​Behavior notes

​Related endpoints

​Errors

Authorizations

Body

Response

When to use it

Endpoint

Example

Request parameters

Operators

Response

Boolean vs full recall

Behavior notes

Related endpoints

Errors