Linking Cohere as a source

Alpha release

This source is currently in alpha. The interface and available tables may change.

The Cohere connector syncs your LLM platform assets – datasets, connectors, models, fine-tuned models, and embed jobs – into the PostHog Data warehouse, so you can analyze your AI infrastructure alongside your product data.

Prerequisites

You need a Cohere account with API access so you can create an API key.

Adding a data source

  1. In PostHog, go to the Sources tab of the data pipeline section.
  2. Click + New source and click Link next to this source.
  3. Enter your credentials (see Configuration below) and click Next.
  4. Select the tables you want to sync, choose a sync method and frequency, then click Import.

Once the syncs are complete, you can start querying this data in PostHog.

When linking Cohere, you'll need:

Sync modes

Each table can be synced in one of several modes, depending on what the source supports:

  • Webhook (when available) – the source pushes changes to PostHog in real time. Fastest freshness, lowest ongoing cost, and the only mode that reliably captures updates and deletes.
  • Incremental – only new or updated rows are synced on each run, using a cursor field (such as an updated_at timestamp). Cheaper than a full refresh, but deletes aren't captured.
  • Append only – new rows are appended using a cursor field; existing rows are never updated. Ideal for immutable, append-only tables like event logs.
  • Full refresh – the whole table is reloaded on every sync. Use it when a table has no reliable cursor or when you need deletions reflected.

See sync methods for a full explanation of how each mode works and how to choose between them.

This source is full refresh only. Cohere does not expose reliable server-side timestamp filters across its endpoints, and the synced entities are small and mutable (statuses and timestamps change in place), so full refresh ensures no updates are missed.

Configuration

OptionTypeRequired
API keypasswordYes

Supported tables

TableDescriptionSync methodIncremental fieldPrimary key
datasets

A dataset uploaded to Cohere for fine-tuning or embedding jobs.

Full refresh
connectors

A connector that lets Cohere's chat models retrieve documents from an external data source.

Full refresh
models

A model available to your account in the Cohere model catalog.

Full refresh
finetuned_models

A fine-tuned model trained on your data.

Full refresh
embed_jobs

An asynchronous job that embeds a dataset into vectors.

Full refresh

Troubleshooting

  • If you see an authentication error, your Cohere API key may be invalid or revoked. Create a new key in the Cohere dashboard, then reconnect.

If your sync is failing or data looks wrong, see the Data warehouse troubleshooting guide. If that doesn't help, contact support – we're happy to help.

Community questions

Was this page useful?

Questions about this page? or post a community question.