Vector Store Files

POST /v1/vector_stores/{vector_store_id}/files

Python

from openai import OpenAI
client = OpenAI()

# Add file to vector store
vector_store_file = client.beta.vector_stores.files.create(
    vector_store_id="vs_abc123",
    file_id="file-abc123"
)

print(vector_store_file.id, vector_store_file.status)

# List files in vector store
files = client.beta.vector_stores.files.list(
    vector_store_id="vs_abc123"
)

for file in files:
    print(file.id, file.status)

# Upload and attach file in one step
vector_store_file = client.beta.vector_stores.files.upload(
    vector_store_id="vs_abc123",
    file=open("mydata.pdf", "rb")
)

import OpenAI from "openai";
import fs from "fs";
const openai = new OpenAI();

// Add file to vector store
const vectorStoreFile = await openai.beta.vectorStores.files.create(
  "vs_abc123",
  {
    file_id: "file-abc123"
  }
);

console.log(vectorStoreFile.id, vectorStoreFile.status);

// List files in vector store
const files = await openai.beta.vectorStores.files.list(
  "vs_abc123"
);

for (const file of files.data) {
  console.log(file.id, file.status);
}

// Upload and attach file in one step
const uploadedFile = await openai.beta.vectorStores.files.upload(
  "vs_abc123",
  fs.createReadStream("mydata.pdf")
);

# Add file to vector store
curl https://api.openai.com/v1/vector_stores/vs_abc123/files \\
  -H "Authorization: Bearer $OPENAI_API_KEY" \\
  -H "Content-Type: application/json" \\
  -H "OpenAI-Beta: assistants=v2" \\
  -d '{
    "file_id": "file-abc123"
  }'

# List files
curl https://api.openai.com/v1/vector_stores/vs_abc123/files \\
  -H "Authorization: Bearer $OPENAI_API_KEY" \\
  -H "OpenAI-Beta: assistants=v2"

{
  "id": "file-abc123",
  "object": "vector_store.file",
  "usage_bytes": 1234,
  "created_at": 1699061776,
  "vector_store_id": "vs_abc123",
  "status": "in_progress",
  "last_error": null,
  "chunking_strategy": {
    "type": "auto"
  }
}

Create a vector store file by attaching a File to a vector store.

Path Parameters

vector_store_id · string · required

The ID of the vector store.

Request Body

file_id · string · required

A File ID that the vector store should use. Useful for tools like file_search that can access files.

chunking_strategy · object

The chunking strategy used to chunk the file(s). If not set, will use the auto strategy.

Show Auto strategy

{
  "type": "auto"
}

Show Static strategy

{
  "type": "static",
  "static": {
    "max_chunk_size_tokens": 800,
    "chunk_overlap_tokens": 400
  }
}

attributes · object

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format.

Keys are strings with a maximum length of 64 characters. Values can be strings (max 512 characters), booleans, or numbers.

Response

Returns a VectorStoreFile object.

id · string

The identifier of the vector store file.

object · string

The object type, always vector_store.file.

vector_store_id · string

The ID of the vector store that the file is attached to.

status · string

The status of the vector store file. One of:

• in_progress
• completed
• cancelled
• failed

created_at · integer

The Unix timestamp (in seconds) for when the vector store file was created.

List Vector Store Files

GET https://api.openai.com/v1/vector_stores/{vector_store_id}/files

Returns a list of vector store files.

Query Parameters

limit · integer · default: "20"

A limit on the number of objects to be returned. Limit can range between 1 and 100.

order · string · default: "desc"

Sort order by the created_at timestamp. asc for ascending order and desc for descending order.

after · string

A cursor for use in pagination.

before · string

A cursor for use in pagination.

filter · string

Filter by file status. One of in_progress, completed, failed, cancelled.

Retrieve Vector Store File

GET https://api.openai.com/v1/vector_stores/{vector_store_id}/files/{file_id}

Retrieves a vector store file.

Delete Vector Store File

DELETE https://api.openai.com/v1/vector_stores/{vector_store_id}/files/{file_id}

Delete a vector store file. This will remove the file from the vector store but the file itself will not be deleted. To delete the file, use the delete file endpoint.

Python

from openai import OpenAI
client = OpenAI()

# Add file to vector store
vector_store_file = client.beta.vector_stores.files.create(
    vector_store_id="vs_abc123",
    file_id="file-abc123"
)

print(vector_store_file.id, vector_store_file.status)

# List files in vector store
files = client.beta.vector_stores.files.list(
    vector_store_id="vs_abc123"
)

for file in files:
    print(file.id, file.status)

# Upload and attach file in one step
vector_store_file = client.beta.vector_stores.files.upload(
    vector_store_id="vs_abc123",
    file=open("mydata.pdf", "rb")
)

import OpenAI from "openai";
import fs from "fs";
const openai = new OpenAI();

// Add file to vector store
const vectorStoreFile = await openai.beta.vectorStores.files.create(
  "vs_abc123",
  {
    file_id: "file-abc123"
  }
);

console.log(vectorStoreFile.id, vectorStoreFile.status);

// List files in vector store
const files = await openai.beta.vectorStores.files.list(
  "vs_abc123"
);

for (const file of files.data) {
  console.log(file.id, file.status);
}

// Upload and attach file in one step
const uploadedFile = await openai.beta.vectorStores.files.upload(
  "vs_abc123",
  fs.createReadStream("mydata.pdf")
);

# Add file to vector store
curl https://api.openai.com/v1/vector_stores/vs_abc123/files \\
  -H "Authorization: Bearer $OPENAI_API_KEY" \\
  -H "Content-Type: application/json" \\
  -H "OpenAI-Beta: assistants=v2" \\
  -d '{
    "file_id": "file-abc123"
  }'

# List files
curl https://api.openai.com/v1/vector_stores/vs_abc123/files \\
  -H "Authorization: Bearer $OPENAI_API_KEY" \\
  -H "OpenAI-Beta: assistants=v2"

{
  "id": "file-abc123",
  "object": "vector_store.file",
  "usage_bytes": 1234,
  "created_at": 1699061776,
  "vector_store_id": "vs_abc123",
  "status": "in_progress",
  "last_error": null,
  "chunking_strategy": {
    "type": "auto"
  }
}