Documents

Search Document Sentences

Search through document sentences using semantic similarity.

This endpoint performs a semantic search at the sentence level, which is best for:

Finding very specific information or facts
Getting precise answers to questions
When you need the most granular search results

Performance Considerations:

Slower search performance due to more vectors
Highest memory usage
Best for smaller, focused searches
Consider impact on rate limits

Best Practices:

Use only when specific facts are needed
Keep document set focused using metadata filters
Consider caching frequent queries
Use smaller top_k values (5-10 recommended)

Sentence-level search provides the highest precision but with minimal context. Each result is a single, focused statement or fact from the document.

POST

api

documents

sentences

curl --request POST \
  --url https://api.fieldwise.ai/api/v1/documents/search/sentences \
  --header 'Content-Type: application/json' \
  --data '{
  "query": "<string>",
  "metadata_filter": {},
  "top_k": 10,
  "optimize_metadata": false,
  "optimize_query": false
}'

{
  "success": true,
  "data": {
    "results": [
      {
        "id": 123,
        "document_id": 123,
        "page_number": 123,
        "content": "<string>",
        "relevance": 123,
        "page_id": 123,
        "paragraph_index": 123,
        "paragraph_id": 123,
        "sentence_index": 123
      }
    ],
    "optimized_query": "<string>",
    "optimized_metadata": {}
  },
  "error": {
    "error_code": "RESOURCE_NOT_FOUND",
    "message": "Resource not found"
  },
  "meta": {
    "timestamp": "2023-11-07T05:31:56Z",
    "version": "1.0"
  }
}

Headers

X-API-Key

string | null

Body

application/json

Request model for searching sentences.

query

string

required

The search query

metadata_filter

object | null

Optional metadata filters using MongoDB-like query syntax

top_k

integer

default:10

Number of results to return

Required range: 1 <= x <= 100

optimize_metadata

boolean

default:false

Whether to optimize metadata filter

optimize_query

boolean

default:false

Whether to optimize search query

Response

200

application/json

Successful Response

Response model for sentence search.

data

object

required

Response data

success

boolean

default:true

error

object | null

Schema for API error responses.

Example:

{
  "error_code": "RESOURCE_NOT_FOUND",
  "message": "Resource not found"
}

meta

object

Metadata for API responses

Search Document Paragraphs Get Document By External Id

curl --request POST \
  --url https://api.fieldwise.ai/api/v1/documents/search/sentences \
  --header 'Content-Type: application/json' \
  --data '{
  "query": "<string>",
  "metadata_filter": {},
  "top_k": 10,
  "optimize_metadata": false,
  "optimize_query": false
}'

{
  "success": true,
  "data": {
    "results": [
      {
        "id": 123,
        "document_id": 123,
        "page_number": 123,
        "content": "<string>",
        "relevance": 123,
        "page_id": 123,
        "paragraph_index": 123,
        "paragraph_id": 123,
        "sentence_index": 123
      }
    ],
    "optimized_query": "<string>",
    "optimized_metadata": {}
  },
  "error": {
    "error_code": "RESOURCE_NOT_FOUND",
    "message": "Resource not found"
  },
  "meta": {
    "timestamp": "2023-11-07T05:31:56Z",
    "version": "1.0"
  }
}

Documents

Content

Extractions

Tasks

Search Document Sentences

Headers

Body

Response