Open Response API Documentation

The Search API enables you to perform semantic searches across your vector stores to find relevant document content. This API is at the core of the RAG system, allowing you to retrieve information based on meaning rather than just keywords.

The official documentation for the Search API is available here.

Key Benefits

Semantic Understanding

Find content based on meaning, not just exact keyword matches

Contextual Results

Retrieve document chunks with surrounding context preserved

Flexible Filtering

Narrow results by document attributes and metadata

AI Integration

Connect search results directly to AI responses

API Endpoints

Search a Vector Store

Search for relevant content within a vector store.

Endpoint: POST /v1/vector_stores/{vector_store_id}/search
Content-Type: application/json

Path Parameters:

vector_store_id: The ID of the vector store to search (required)

Request Body:

query: The search query string (required)
max_num_results: Maximum number of results to return (default: 10)
filters: Optional filters to apply based on file attributes
rewrite_query: Whether to rewrite the query for better vector search (default: false)
ranking_options: Options for ranking/scoring results

curl --location 'http://localhost:8080/v1/vector_stores/vs_67f8046b1ad5d3000012/search' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer $YOUR_API_KEY' \
--data '{
  "query": "When did empress matilda reached england?",
  "max_num_results": 2,
  "filters": {
    "type": "and",
    "filters": [
      {
        "type": "eq",
        "key": "language",
        "value": "en"
      },
      {
        "type": "eq",
        "key": "category",
        "value": "api_reference" 
      }
    ]
  },
  "ranking_options": {
    "score_threshold": 0.7
  }
}'

Example Response:

{
    "object": "vector_store.search_results.page",
    "search_query": "When did empress matilda reached england?",
    "data": [
        {
            "file_id": "open-responses-file_67f803701ad5d3000002.pdf",
            "filename": "Empress Matilda.pdf",
            "score": 0.8449070359549928,
            "attributes": {
                "category": "api_reference",
                "language": "en",
                "version": "2.0",
                "filename": "Empress Matilda.pdf",
                "chunk_index": 10,
                "total_chunks": 14,
                "chunk_id": "c_67f8084e1ad5d3000039",
                "file_id": "open-responses-file_67f803701ad5d3000002.pdf"
            },
            "content": [
                {
                    "type": "text",
                    "text": "In 1108, Henry left Matilda..."
                }
            ]
        },
        {
            "file_id": "open-responses-file_67f803701ad5d3000002.pdf",
            "filename": "Empress Matilda.pdf",
            "score": 0.8283641913829363,
            "attributes": {
                "category": "api_reference",
                "language": "en",
                "version": "2.0",
                "filename": "Empress Matilda.pdf",
                "chunk_index": 0,
                "total_chunks": 14,
                "chunk_id": "c_67f8084d1ad5d300002f",
                "file_id": "open-responses-file_67f803701ad5d3000002.pdf"
            },
            "content": [
                {
                    "type": "text",
                    "text": "Matilda Depiction of Matilda in the 12th-century..."
                }
            ]
        }
    ],
    "has_more": false,
    "next_page": null
}

Request Parameters in Detail

Query

The query parameter is a natural language question or statement that describes the information you’re looking for. The system converts this query into a vector embedding and finds document chunks with similar embeddings.

"query": "How do I reset my password?"

Straightforward queries work well for specific information needs.

"query": "How do I reset my password?"

Straightforward queries work well for specific information needs.

"query": "Explain the step-by-step process for configuring SSL certificates on the server"

More detailed queries can help refine the search when looking for procedural information.

"query": "What are the security implications of using default credentials?"

Conceptual queries help find explanatory content about broader topics.

Max Number of Results

The max_num_results parameter controls how many results are returned. The default is 10, but you can adjust this based on your needs:

"max_num_results": 5

For applications that need more context, increase this value, but be aware that higher values may include less relevant results.

Filters

The filters parameter lets you narrow search results based on file attributes. Filters follow a structured format that enables both simple and complex filtering conditions.

Filter Types

The API supports two types of filters:

Comparison Filters

Compare a property value against a specific value

Compound Filters

Combine multiple filters using logical operators

Comparison Operators

Operator	Description	Example
`eq`	Equal to	Match where language is “en”
`ne`	Not equal to	Match where status is not “archived”
`gt`	Greater than	Match where version > 1.0
`gte`	Greater than or equal to	Match where created_at ≥ 1672531200
`lt`	Less than	Match where priority < 3
`lte`	Less than or equal to	Match where size ≤ 1024

Basic Filter Examples

"filters": {
  "type": "eq",
  "key": "language",
  "value": "en"
}

Find documents where the language attribute equals “en”.

"filters": {
  "type": "eq",
  "key": "language",
  "value": "en"
}

Find documents where the language attribute equals “en”.

"filters": {
  "type": "gt",
  "key": "version",
  "value": 2.0
}

Find documents with version greater than 2.0.

"filters": {
  "type": "ne",
  "key": "status",
  "value": "archived"
}

Find documents where status is not “archived”.

Compound Filters

Combine multiple conditions using logical operators:

All conditions must be true for a document to be included:

"filters": {
  "type": "and",
  "filters": [
    {
      "type": "eq",
      "key": "category",
      "value": "documentation"
    },
    {
      "type": "eq",
      "key": "language",
      "value": "en"
    }
  ]
}

At least one condition must be true:

"filters": {
  "type": "or",
  "filters": [
    {
      "type": "eq",
      "key": "filename",
      "value": "document1.txt"
    },
    {
      "type": "eq",
      "key": "filename",
      "value": "document2.txt"
    }
  ]
}

Combine AND and OR for complex conditions:

"filters": {
  "type": "and",
  "filters": [
    {
      "type": "eq",
      "key": "category",
      "value": "documentation"
    },
    {
      "type": "or",
      "filters": [
        {
          "type": "eq",
          "key": "language",
          "value": "en"
        },
        {
          "type": "eq",
          "key": "language",
          "value": "es"
        }
      ]
    }
  ]
}

Advanced Use Cases

Date Range Filtering

"filters": {
  "type": "and",
  "filters": [
    {
      "type": "gte",
      "key": "created_at",
      "value": 1672531200
    },
    {
      "type": "lt",
      "key": "created_at",
      "value": 1704067200
    }
  ]
}

Filter documents created in 2023 (using Unix timestamps).

Boolean Filters

"filters": {
  "type": "and",
  "filters": [
    {
      "type": "eq",
      "key": "is_approved",
      "value": true
    },
    {
      "type": "eq",
      "key": "is_public",
      "value": true
    }
  ]
}

Find approved public documents.

When designing your document attributes, consider what filtering capabilities you’ll need and ensure your attributes are structured accordingly.

Ranking Options

The ranking_options parameter configures how results are scored and ranked:

"ranking_options": {
  "score_threshold": 0.7
}

score_threshold: Minimum similarity score (0.0-1.0) for results to be included

Response Format in Detail

The search response includes:

Search Query

The original query string used for the search:

"search_query": "How do I configure the system?"

Data Array

An array of search results, each containing:

file_id: ID of the file containing the result
filename: Name of the file
score: Similarity score (0.0-1.0)
attributes: File attributes for filtering
content: Array of content segments

The results are ordered by descending score (most relevant first).

Pagination Information

has_more: Boolean indicating if there are more results available
next_page: Token for retrieving the next page of results (if available)

Using the file_search Tool

The file_search tool provides an alternative way to search vector stores through the AI assistant API. This is especially useful for integrating search within conversational AI flows.

Tool Usage with OpenAI Models

curl --location 'http://localhost:8080/v1/responses' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer $OPENAI_API_KEY' \
--header 'x-model-provider: openai' \
--data '{
    "model": "gpt-4o",
    "tools": [{
      "type": "file_search",
      "vector_store_ids": ["vs_abc123"],
      "max_num_results": 5,
      "filters": {
        "type": "and",
        "filters": [
          {
            "type": "eq",
            "key": "category",
            "value": "documentation"
          },
          {
            "type": "eq",
            "key": "language",
            "value": "en"
          }
        ]
      }
    }],
    "input": "How do I configure the system?",
    "instructions": "Answer questions using information from the provided documents."
}'

The file_search tool automatically performs the search and provides the results to the AI model in the same request. This creates a seamless RAG experience.

Advanced Search Techniques

Query Rewriting (Coming Soon)

For improved search results, you can enable query rewriting:

"rewrite_query": true

When enabled, the system will automatically reformulate the query to improve vector similarity matching. This is particularly helpful for:

Queries with ambiguous terms
Questions with implicit context
Queries that could benefit from expansion with related terms

Best Practices

Query Optimization

Be specific and clear

Craft precise queries rather than broad ones. “How do I reset a user password?” is better than “password reset.”

Use natural language

Frame queries as complete questions or statements rather than keyword lists.

Include context

If searching for domain-specific information, include relevant context in the query.

Use filters effectively

Combine query text with appropriate filters to narrow down the search space.

Performance Considerations

Keep max_num_results reasonable (5-20) for better performance
Use filters to reduce the search space when applicable
Consider implementing client-side caching for frequent queries
For very large vector stores, use pagination to handle results efficiently

Integration Patterns

Direct API Integration

Integrate the Search API directly into your application’s backend:

Capture user query from your application UI
Send search request to the Search API
Process and display results in your application
Optionally use results to enhance subsequent AI interactions

AI-Driven Search with file_search Tool

Let the AI assistant drive the search interaction:

Configure AI with the file_search tool
User asks a question to the AI
AI determines when to use the search tool and formulates appropriate queries
AI incorporates search results into its response
User receives a cohesive answer combining search results with AI capabilities

Files API

Upload and manage files for searching

Vector Store API

Create and manage vector stores for embeddings

Get Started

Announcements

Use Cases & Demos

OpenResponses API

Retrieval (RAG)

​Key Benefits

Semantic Understanding

Contextual Results

Flexible Filtering

AI Integration

​API Endpoints

​Search a Vector Store

​Request Parameters in Detail

​Query

​Max Number of Results

​Filters

​Filter Types

Comparison Filters

Compound Filters

​Comparison Operators

​Basic Filter Examples

​Compound Filters

​Advanced Use Cases

Date Range Filtering

Boolean Filters

​Ranking Options

​Response Format in Detail

​Search Query

​Data Array

​Pagination Information

​Using the file_search Tool

​Tool Usage with OpenAI Models

​Advanced Search Techniques

​Query Rewriting (Coming Soon)

​Best Practices

​Query Optimization

​Performance Considerations

​Integration Patterns

​Direct API Integration

​AI-Driven Search with file_search Tool

​Related APIs

Files API

Vector Store API

Key Benefits

API Endpoints

Search a Vector Store

Request Parameters in Detail

Query

Max Number of Results

Filters

Filter Types

Comparison Operators

Basic Filter Examples

Compound Filters

Advanced Use Cases

Ranking Options

Response Format in Detail

Search Query

Data Array

Pagination Information

Using the file_search Tool

Tool Usage with OpenAI Models

Advanced Search Techniques

Query Rewriting (Coming Soon)

Best Practices

Query Optimization

Performance Considerations

Integration Patterns

Direct API Integration

AI-Driven Search with file_search Tool

Related APIs