Create context-grounded fine-tuning data

Context-grounded fine-tuning stops working on November 9, 2026. You can keep using it until then. For new projects, choose another fine-tuning method.

Context-grounded data jobs ground model responses in an existing knowledge source. Two job types are available:

context_grounded_files — aligns against uploaded and ingested documents. Follows the same file preparation and ingestion steps as principle_files, but no system prompt is required.
context_grounded_vector_db — aligns against a pre-built SeekrFlow vector database. No file upload or ingestion is needed.

Neither type requires a system prompt to start. Not sure which approach fits your use case? See Fine-tuning.

context_grounded_files

Step 1: Create the job

Endpoint: POST /v1/flow/data-jobs

from seekrai import SeekrFlow

client = SeekrFlow()

data_job = client.data_jobs.create(
    name="Customer support context grounding",
    instructions="Generate QA pairs grounded in the ingested support docs.",
    job_type="context_grounded_files",
)
data_job_id = data_job.id
print("Data job ID:", data_job_id)

Step 2: Upload and attach files

Upload your source files using the Files API, then attach them to the job. Ingestion runs automatically for non-Markdown files. Markdown files are alignment-ready immediately. Endpoint: POST /v1/flow/data-jobs/{id}/add-files

data_job = client.data_jobs.add_files(
    data_job_id,
    file_ids=[
        "file-25e34f96-2130-11f0-9236-3e11346bffff",
        "file-efd0b334-2130-11f0-9236-3e11346bffff",
    ],
    method="accuracy-optimized",
)
print("Status:", data_job.status)

Poll GET /v1/flow/data-jobs/{id} until status is ready_to_start. See Monitor ingestion for details on job states and error handling.

Step 3: Start alignment

No system prompt is required. Call /start once status is ready_to_start. Endpoint: POST /v1/flow/data-jobs/{id}/start

detail = client.data_jobs.start(data_job_id)
print("Alignment job:", detail.alignment_job.id, detail.alignment_job.status)

Prerequisites:

status must be ready_to_start
At least one processed Markdown file attached (ingested or uploaded)

Step 4: Monitor alignment

detail = client.data_jobs.retrieve(data_job_id)
print("Status:", detail.status)
if detail.alignment_job:
    print("Alignment job:", detail.alignment_job.id, detail.alignment_job.status)
    if detail.alignment_job.status_message:
        print("Status detail:", detail.alignment_job.status_message)

status_message gives a human-readable description of the alignment job’s current state, including the reason if the job fails. Once status shows completed, retrieve the output files as described in Step 5.

Step 5: Retrieve output files

Endpoint: GET /v1/flow/data-jobs/{id}

detail = client.data_jobs.retrieve(data_job_id)
outputs = detail.alignment_job.output_files
for f in outputs:
    print(f.id, f.filename, f.file_type, f.purpose)

The output file with "purpose": "fine-tune" (the .parquet) is the file ID to use when creating a fine-tuning job.

context_grounded_vector_db

Use this job type when your knowledge source is already indexed in a SeekrFlow vector database. No file upload or ingestion is needed — attach the vector database ID and start.

Step 1: Create the job and attach the vector database

Endpoints: POST /v1/flow/data-jobs Submit data job · PATCH /v1/flow/data-jobs/{id} Update data job Create the job and set vector_database_id before starting. No file upload or ingestion is needed.

data_job = client.data_jobs.create(
    name="Customer support refresh",
    instructions="Generate QA pairs grounded in the existing vector store.",
    job_type="context_grounded_vector_db",
)
data_job_id = data_job.id

data_job = client.data_jobs.update(
    data_job_id,
    vector_database_id="9aab2ceb-7c7b-4c07-8ff4-5416dfad221a",
)
print("Vector DB set:", data_job.vector_database_id)

Step 2: Start alignment

Endpoint: POST /v1/flow/data-jobs/{id}/start

detail = client.data_jobs.start(data_job_id)
print("Alignment job:", detail.alignment_job.id, detail.alignment_job.status)

Prerequisites:

status must be ready_to_start
vector_database_id must be set
No system prompt required

Step 3: Monitor alignment

detail = client.data_jobs.retrieve(data_job_id)
print("Status:", detail.status)
if detail.alignment_job:
    print("Alignment job:", detail.alignment_job.id)

Once status shows completed, retrieve the output files as described in Step 4.

Step 4: Retrieve output files

Endpoint: GET /v1/flow/data-jobs/{id}

detail = client.data_jobs.retrieve(data_job_id)
outputs = detail.alignment_job.output_files
for f in outputs:
    print(f.id, f.filename, f.file_type, f.purpose)

The output file with "purpose": "fine-tune" (the .parquet) is the file ID to use when creating a fine-tuning job.

​context_grounded_files

​Step 1: Create the job

​Step 2: Upload and attach files

​Step 3: Start alignment

​Step 4: Monitor alignment

​Step 5: Retrieve output files

​context_grounded_vector_db

​Step 1: Create the job and attach the vector database

​Step 2: Start alignment

​Step 3: Monitor alignment

​Step 4: Retrieve output files

context_grounded_files

Step 1: Create the job

Step 2: Upload and attach files

Step 3: Start alignment

Step 4: Monitor alignment

Step 5: Retrieve output files

context_grounded_vector_db

Step 1: Create the job and attach the vector database

Step 2: Start alignment

Step 3: Monitor alignment

Step 4: Retrieve output files