Data Preparation

Begin the data preparation process by gathering source documents for upload to the Data Engine. Aim to collect documents that are relevant to the domain, and that are structured in a clear and logical way, with headings and subheadings for readability.

Step 1: Preparing your file for upload

Supported file types

Markdown (.md)
PDF (.pdf)
Word Documents (.docx)
JSON (.json)

Length requirements

Your file should have at least 4 cohesive sections, each detailed enough to form a meaningful “chunk.”
Although exact token counts are not mandatory, each chunk should contain enough substantive text to form meaningful document chunks.

File formatting guidelines

Before uploading, make sure your files are properly formatted by following these steps:

PDF and DOCX	Markdown	JSON
1. Use clear headings and avoid images without context. 2. Ensure text content is structured logically for conversion.	1. Use correct header hierarchy (`#`, `##`, `###`, etc.). 2. Avoid missing or empty headers and skipped levels. 3. Limit headers to six levels (`######`). 4. Ensure all sections have meaningful content under them.	1. Validate the JSON structure using a tool like JSONLint. 2. Ensure all key-value pairs are well-formed and relevant.

Note: Google Docs users can export files as Markdown, PDF, or DOCX.

Once your files look good, proceed to the next step.

Step 2: Upload training files

Use SeekrFlow’s API to upload key documents and generate an AI-ready dataset. Documents can be in the following formats:

PDF
DOCX
Markdown
JSON

This dataset, a storage-efficient QA Pair Parquet file, can then be used to run a supervised instruction fine-tuning job.

Note: If fine-tuning is used in combination with user-provided training data, the resulting dataset from fine-tuning and the training data must be combined prior to using the data as part of the fine-tuning service.

The following example code shows you how to upload either a single file, or multiple files of varying types:

Upload a single file

Upload a single file, up to 4GB.

Endpoint: PUT /v1/flow/filesUpload Training File

import requests

# Define API Endpoint
url = "https://flow.seekr.com/v1/flow/files"

# Set Headers with API Key
headers = {
    "Authorization": "YOUR_API_KEY",
    "accept": "application/json"
}

# Open and Upload File
files = {
    "files": ("example.pdf", open("/path/to/your/example.pdf", "rb")),
    "purpose": (None, "alignment")
}

# Make API Request
response = requests.put(url, files=files, headers=headers)

# Print Response
print("Status Code:", response.status_code)
print("Response:", response.json())

Sample response

Status Code for example.pdf: 200

Response for example.pdf:
{
  "id": "file_1234567890",
  "object": "file",
  "created_at": "example_timestamp",
  "type": "pdf",
  "purpose": "alignment",
  "filename": "example.pdf",
  "bytes": 102400,
  "created_by": "user"
}

Upload multiple files

Upload multiple files up to 4GB each.

Note: File size limits differ between the API/SDK and UI, which supports file uploads up to 10 files/100mb each.

The following example uploads two files, one PDF and one DOCX, simultaneously:

Endpoint: PUT /v1/flow/bulk_filesUpload Multiple Training Files

import requests
import os

url = "https://flow.seekr.com/v1/flow/bulk_files"  

headers = {
    "Authorization": "YOUR_API_KEY",
    "accept": "application/json"
}

file_paths = ["file_1.docx", "file_2.pdf"] 

files_to_upload = [
    ('files', (os.path.basename(file_path), open(file_path, 'rb'))) 
    for file_path in file_paths
]

files_to_upload.append(('purpose', (None, 'alignment')))

response = requests.put(url, files=files_to_upload, headers=headers)

print("Status Code:", response.status_code)
print("Response:", response.json())

Sample response

Status Code for file_1.pdf: 200
Response for file_1.pdf
{
  'id': 'file-12345', 
  'object': 'file', 
  'created_at': 'example_timestamp', 
  'type': 'pdf', 
  'purpose': 'alignment', 
  'filename': 'file_1.docx', 
  'bytes': 348111, 
  'created_by': 'user'
}

Status Code for file_2.pdf: 200
Response for file_2.pdf:
{
  'id': 'file-67890', 
  'object': 'file', 
  'created_at': 'example_timestamp', 
  'type': 'pdf', 
  'purpose': 'alignment', 
  'filename': 'file_2.pdf', 
  'bytes': 1711963, 
  'created_by': 'user'
}

Step 3: Start an ingestion job (for PDFs and DOCX only)

Endpoint: POST /v1/flow/alignment/ingestion Multi-file Ingestion

If your original source was a PDF or DOCX, you must first convert it to Markdown.

If you already have a Markdown file, skip this step.

If your file has tables embedded, make sure there are no empty cells. Empty cells run the risk of shifting all of your content in your table over to fill in the empty cell.

url = "https://flow.seekr.com/v1/flow/alignment/ingestion"

payload = {
    "files": ["file-123456789"]  # The file ID returned from upload
}

response = requests.post(url, json=payload, headers=headers)

print("Status Code:", response.status_code)
print("Response:", response.json())

Sample response:

{
    "id": "ij-123456789",
    "created_at": "example_timestamp",
    "status": "running",
    "output_files": []
}

Once ingestion is complete, you’ll receive a Markdown file that you can use for fine-tuning.

Step 4: Check ingestion status (optional)

Endpoint: GET /v1/flow/alignment/ingestion/{job_id} Get Detailed Job Status

After starting ingestion, you may want to check the status to confirm when it's been completed successfully.

import requests

job_id = "ij-123456789"
url = "https://flow.seekr.com/v1/flow/alignment/ingestion/{job_id}"

response = requests.get(url, headers=headers)
print("Status Code:", response.status_code)
print("Response:", response.json())

Sample response:

{
  "id": "ij-123456789",
  "created_at": "example_timestamp",
  "status": "completed",
  "output_files": [
    "file-123456789"
  ]
}

Check the status field. Once it shows completed, your output file(s) will be available for the next step: generating data for standard instruction fine-tuning.