Transcripts

divinci.transcripts manages conversation transcripts in a workspace — listing them, adding messages, and batch-ingesting conversations that were generated elsewhere (for example, inference you ran with a local or third-party model).

Creating and reading transcripts

const transcript = await divinci.transcripts.create({
  workspaceId: "ws_123",
  releaseId: "rel_abc123", // optional
});

const { data } = await divinci.transcripts.list("ws_123", { limit: 20 });
const one = await divinci.transcripts.get(transcript._id);

await divinci.transcripts.delete(transcript._id);

Adding a single message

const message = await divinci.transcripts.addMessage(transcript._id, {
  role: "user",
  content: "How do I reset my password?",
});

Batch ingestion

ingestBatch records a whole conversation in one call. This is the canonical path for persisting messages produced by inference performed outside Divinci.

const result = await divinci.transcripts.ingestBatch({
  workspaceId: "ws_123",
  transcriptId: transcript._id,
  defaults: {
    release: "rel_abc123",
    metadata: { channel: "local-llm" },
  },
  items: [
    { role: "user", content: "Hi" },
    { role: "assistant", content: "Hello! How can I help?", name: "support-bot" },
  ],
});

console.log(result.inserted);   // number of messages stored
console.log(result.messageIds); // ids in order

Method reference

Method	Description
`list(workspaceId, options?)`	Paginated transcripts.
`get(transcriptId)`	Fetch a transcript.
`create(options)`	Create a transcript (`workspaceId`, optional `releaseId`).
`addMessage(transcriptId, options)`	Append a single message.
`ingestBatch(options)`	Bulk-insert messages with shared defaults.
`delete(transcriptId)`	Delete a transcript.