Context Management: Overview

​

Endpoint references

​

Lifecycle

• type picks the store: knowledge (documents, app sources, and facts) or memory (preferences, decisions, and past conversations). It routes the ingest to the right store.
• Within type=knowledge, you pick the payload shape: documents (binary documents HydraDB will parse: PDFs, DOCX, CSV) or app_knowledge (a JSON array of already-extracted content from your app: Slack messages, Notion pages, web pages). You can send both in the same request.

​

Core ingestion concepts

• Knowledge vs. memories: Knowledge includes documents, app sources, and facts your AI uses. Memories are preferences, decisions, and past conversations. Both live in a collection, and type: "all" on POST /query searches both from the same scope.
• IDs: Unique identifiers returned by /context/ingest. You can assign custom IDs using id in document_metadata, app_knowledge, or memories items. Use them for polling status, inspecting content, and deleting context.
• Metadata and Filters covers metadata fields, ingestion, updates, and filtering.

​

Forceful relations and metadata

import json

with open("runbook.pdf", "rb") as f:
    result = client.context.ingest(
        type="knowledge",
        database="acme_corp",
        documents=[("runbook.pdf", f, "application/pdf")],
        document_metadata=json.dumps([{
            "id": "runbook_deploy",
            "metadata": {"department": "ops"},
            "additional_metadata": {"owner": "platform-team"},
            "relations": {"ids": ["monitoring_guide"]},
        }]),
    )

​

Related

• Knowledge: forceful relations: linking sources at ingestion
• Memories: memories vs knowledge, when to use which
• Metadata: database-level vs document-level metadata
• Query: retrieve ingested content