Skip to content

Latest commit

 

History

History
140 lines (106 loc) · 3.37 KB

vector_store.md

File metadata and controls

140 lines (106 loc) · 3.37 KB
page_title subcategory description
openai_vector_store Resource - terraform-provider-openai
Manages an OpenAI Vector Store.

openai_vector_store (Resource)

Manages an OpenAI Vector Store.

Example Usage

# Create a vector store for document retrieval
resource "openai_vector_store" "knowledge_base" {
  name = "Company Knowledge Base"

  # Optional: Add metadata for organization
  metadata = {
    department   = "documentation"
    version      = "2.0"
    last_updated = "2024-01-15"
    access_level = "internal"
  }
}

# Create a vector store for customer support documents
resource "openai_vector_store" "support_docs" {
  name = "Customer Support Documentation"

  # Optional: Configure file handling
  file_ids = [
    # Reference existing files to include in the vector store
    # These would typically be created with openai_file resources
    # "file-abc123",
    # "file-def456"
  ]

  metadata = {
    category     = "support"
    language     = "en-US"
    indexed_date = "2024-01-15"
  }
}

# Create a vector store for code documentation
resource "openai_vector_store" "code_docs" {
  name = "API and Code Documentation"

  metadata = {
    repository  = "github.com/company/api-docs"
    doc_type    = "technical"
    api_version = "v3"
    team        = "platform-engineering"
  }
}

# Create a vector store for product manuals
resource "openai_vector_store" "product_manuals" {
  name = "Product User Manuals"

  metadata = {
    product_line = "enterprise"
    format       = "pdf"
    languages    = "en,es,fr,de"
    compliance   = "ISO-9001"
  }
}

# Output the vector store ID
output "knowledge_base_id" {
  value       = openai_vector_store.knowledge_base.id
  description = "The ID of the knowledge base vector store"
}

Schema

Optional

  • chunking_strategy (Attributes) (see below for nested schema)
  • expires_after (Attributes) (see below for nested schema)
  • file_ids (List of String) A list of file IDs to add to the vector store.
  • metadata (Map of String) Metadata.
  • name (String) The name of the vector store.

Read-Only

  • created_at (Number)
  • file_counts (Attributes) (see below for nested schema)
  • id (String) The identifier of the vector store.
  • object (String)
  • status (String)
  • usage_bytes (Number)

Nested Schema for chunking_strategy

Required:

  • type (String)

Optional:

  • chunk_overlap_tokens (Number) The number of tokens that overlap between chunks. The default is 400. The maximum is half of max_chunk_size_tokens.
  • max_chunk_size_tokens (Number) The maximum number of tokens in each chunk. The default is 800. The minimum is 100 and the maximum is 4096.

Nested Schema for expires_after

Required:

  • anchor (String)
  • days (Number)

Nested Schema for file_counts

Read-Only:

  • cancelled (Number)
  • completed (Number)
  • failed (Number)
  • in_progress (Number)
  • total (Number)

Import

Import is supported using the following syntax:

#!/bin/bash
# Import existing OpenAI vector store
terraform import openai_vector_store.example vs_abc123def456