Skip to main content
PUT
/
v1
/
flow
/
files
Upload file
curl --request PUT \
  --url https://flow.seekr.com/v1/flow/files \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: multipart/form-data' \
  --form 'files=<string>' \
  --form 'vector_database_id=<string>'
{
  "id": "<string>",
  "object": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "filename": "<string>",
  "bytes": 123,
  "created_by": "<string>",
  "original_file_id": "<string>",
  "deleted": true
}

Purpose values and file formats

Each purpose value requires a specific JSONL schema. Each line of the file must be a valid JSON object matching the format for the chosen purpose.

fine-tune and alignment

Each line requires a messages array of {"role", "content"} objects. Valid roles are system, user, and assistant.
{"messages": [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "What is the capital of France?"}, {"role": "assistant", "content": "The capital of France is Paris."}]}

preference-fine-tune

Each line requires three fields — messages, chosen, and rejected — each an array of {"role", "content"} objects.
{"messages": [{"role": "user", "content": "What is the capital of France?"}], "chosen": [{"role": "user", "content": "What is the capital of France?"}, {"role": "assistant", "content": "Paris."}], "rejected": [{"role": "user", "content": "What is the capital of France?"}, {"role": "assistant", "content": "Lyon."}]}

pre-train

Each line requires a single text field containing raw training text.
{"text": "Raw training text goes here."}

Authorizations

Authorization
string
header
required

Seekr API Key without 'Bearer' Prefix

Body

multipart/form-data
purpose
enum<string>
required
Available options:
reinforcement-fine-tune,
fine-tune,
preference-fine-tune,
pre-train,
alignment
files
string
required
vector_database_id
string | null

Response

Successful Response

Files API response type

id
string
required
object
string
required
Allowed value: "file"
created_at
string<date-time> | null
type
Available options:
jsonl,
parquet,
pt
purpose
enum<string> | null
Available options:
reinforcement-fine-tune,
fine-tune,
preference-fine-tune,
pre-train,
alignment
filename
string | null
bytes
integer | null
created_by
string | null
original_file_id
string | null
deleted
boolean | null
Last modified on June 18, 2026