Knowledge Base: Upload Documents and Query with the SDK

Go to app.futureagi.com → Knowledge base (left sidebar) → Create Knowledge Base.

1. Enter a name: product-docs
2. In the Upload tab, upload your documents (PDF, TXT, DOCX, or RTF)
3. Click Create

Click on product-docs in the Knowledge Base list. Inside, you can see:

• All uploaded files with their file size and processing status
• Add docs: upload additional documents
• Create Synthetic data: generate a synthetic dataset grounded in this KB (available once processing completes)

You can also create and manage a KB programmatically:

import os
from fi.kb import KnowledgeBase

kb_client = KnowledgeBase(
    fi_api_key=os.environ["FI_API_KEY"],
    fi_secret_key=os.environ["FI_SECRET_KEY"],
)

kb_client.create_kb(
    name="product-docs",
    file_paths=[
        "./docs/return-policy.txt",
        "./docs/shipping-info.txt",
        "./docs/product-catalog.pdf",
    ],
)

print(f"KB created: {kb_client.kb.name}")

Expected output:

KB created: product-docs

When your content changes, add files without recreating the KB:

kb_client.update_kb(
    kb_name="product-docs",
    file_paths=["./docs/warranty-policy.txt"],
)

print("New document added to product-docs.")

You can also rename the KB at the same time:

kb_client.update_kb(
    kb_name="product-docs",
    new_name="product-docs-v2",
    file_paths=["./docs/new-policy.txt"],
)

Remove specific files from a KB:

kb_client.delete_files_from_kb(
    file_names=["return-policy.txt"],
    kb_name="product-docs",
)

print("File removed from KB.")

Delete the entire KB:

kb_client.delete_kb(kb_names="product-docs")

print("KB deleted.")

When running evaluations on a dataset, you can attach your Knowledge Base so the evaluator uses your domain documents as grounding context.

1. Go to app.futureagi.com → Dataset → open your dataset
2. Click Evaluate → Add Evaluations → select an eval metric (e.g. completeness)
3. In the evaluation configuration, find the Knowledge base dropdown
4. Select your KB (e.g. product-docs) — this allows the evaluator to leverage your domain-specific documents when scoring
5. Map the remaining keys and click Add & Run

You can generate a synthetic dataset grounded in your KB documents — either from the KB detail view or from the synthetic data wizard.

From the KB detail view:

1. Go to Knowledge base → click on your KB → click Create Synthetic data (top action bar)
2. The synthetic data wizard opens with your KB pre-selected

From the synthetic data wizard:

1. Go to Dataset → Add Dataset → Create Synthetic Data
2. In the Add details step, select your KB from the Select knowledge base dropdown

Both paths lead to the same synthetic data generation pipeline. Follow the full walkthrough in Generate a Synthetic Dataset.