Chat with your documents

The scenario

Half of what your agent should know is in files — a policy, a spec, a handbook. You do not want a second retrieval system for them, and you do not want to pre-chunk anything. Uploads land in the same space as recorded memories, so one retrieve answers from both.

Step 1 — Upload

job = client.upload_file(space_id=space, file="refund-policy.txt")

file takes a path, raw bytes, or a file object. PDF, DOCX, PPTX, XLSX, HTML, TXT/MD/CSV, images, MP3/WAV audio and MP4/MOV/WEBM/MKV video are all read into text.

Step 2 — Wait for it to be searchable

Ingestion is asynchronous. The upload returns job ids; completed means that file is searchable.

for job_id in job["job_ids"]:
    while client.get_job(space_id=space, job_id=job_id)["status"] not in ("completed", "failed"):
        time.sleep(5)

In production use webhooks instead of a loop.

Step 3 — Ask, and see which file answered

for row in client.retrieve(space_id=space, query="How long do I have to return hardware?"):
    print(row["content"], "from", row.get("document_id"))

Step 4 — The document stays a first-class object

for doc in client.list_documents(space_id=space):
    print(doc["document_id"], "->", doc["memory_count"], "memories")

Deleting a document removes every memory extracted from it in one call — which is what makes “remove that outdated policy” a single operation rather than a hunt.

Evals

Upload one file you know the answers in. Ask three questions from it.
Ask something the file does not cover. Empty is correct.
Check document_id resolves on every answer you would act on.
Delete the document and re-ask. Everything from it should be gone.

Guardrails

A question asked seconds after upload may legitimately find nothing. Wait for completed; do not treat the gap as a bug.
Per-file limits apply — 25 MB generally, 64 MB for video, with request totals above that. One oversized file rejects the whole request.
Uploads take scope too. Pass tags on upload if later reads will be scoped, or the document is invisible to every scoped query.

The script

Complete and runnable: document_qa.py.

Getting Started

API Essentials

Memory (data plane)

LLM Proxy (drop-in)

Account (control plane)

SDKs & MCP

Integrations

Guides

Use Cases

Changelog

Chat with your documents

The scenario

Step 1 — Upload

Step 2 — Wait for it to be searchable

Step 3 — Ask, and see which file answered

Step 4 — The document stays a first-class object

Evals

Guardrails

The script

​The scenario

​Step 1 — Upload

​Step 2 — Wait for it to be searchable

​Step 3 — Ask, and see which file answered

​Step 4 — The document stays a first-class object

​Evals

​Guardrails

​The script

The scenario

Step 1 — Upload

Step 2 — Wait for it to be searchable

Step 3 — Ask, and see which file answered

Step 4 — The document stays a first-class object

Evals

Guardrails

The script