Linking Mistral AI as a source
This source is currently in alpha. The interface and available tables may change.
Let AI connect your sources for you
Skip the manual setup — run this in your project and the wizard auto-detects your databases and APIs and connects them to PostHog.
Contents
The Mistral AI connector syncs models, files, fine-tuning jobs, and batch inference jobs into the PostHog data warehouse. Beta tables for agents, conversations and their entries, libraries and their documents, and observability traces and spans are also available. Use it to analyze fine-tuning progress, batch job throughput, and asset history alongside the rest of your product data.
Prerequisites
Credentials that can read the data you want to sync. PostHog only reads data, so read access is enough.
Adding a data source
- In PostHog, go to the Sources tab of the data pipeline section.
- Click + New source and click Link next to this source.
- Enter your credentials (see Configuration below) and click Next.
- 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.
Enter your Mistral AI API key to sync your Mistral AI platform data.
You can create an API key in La Plateforme.
You'll be asked for:
- API key
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_attimestamp). 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.
Fine-tuning jobs and batch jobs support incremental syncing via their server-side created_after filter. The beta traces and spans tables support incremental syncing on start_time. Models, files, and the beta agents, conversations, conversation entries, libraries, and library documents tables have no creation-time filter in the API, so they sync as a full refresh each run.
Configuration
| Option | Type | Required |
|---|---|---|
API key | password | Yes |
Supported tables
| Table | Description | Sync method | Incremental field | Primary key |
|---|---|---|---|---|
models | Models available to the workspace: Mistral's base models plus any fine-tuned models you own. | Full refresh | — | — |
files | Files uploaded to the workspace (fine-tuning datasets, batch inputs, OCR sources, etc.). | Full refresh | — | — |
fine_tuning_jobs | Fine-tuning jobs with status, hyperparameters, trained-token counts, and timestamps. | Incremental, Full refresh | created_at | — |
batch_jobs | Batch inference jobs with request counts and per-status progress. | Incremental, Full refresh | created_at | — |
agents | Agents defined in the workspace (beta), including model, instructions, and tools. | Full refresh | — | — |
conversations | Conversations (beta) started against models or agents. | Full refresh | — | — |
libraries | Document libraries (beta) used as retrieval knowledge bases. | Full refresh | — | — |
conversation_entries | Entries (beta) of each conversation in the order they were appended: input and output messages, function calls and results, tool executions, and agent handoffs. | Full refresh | — | — |
library_documents | Documents (beta) uploaded to each library, with their processing status. | Full refresh | — | — |
traces | Observability traces (beta): one row per traced agent or workflow run, with latency, token, and error totals. | Incremental, Full refresh | start_time | — |
spans | Observability spans (beta): each step of a traced run, such as an LLM call, a tool call, or a retrieval. | Incremental, Full refresh | start_time | — |
Troubleshooting
- If the connection fails with an authorization error, the API key is wrong, expired, or has been revoked. Create a new one, then reconnect the source.
- If a table syncs no rows, the credential may not have access to that data. Check its permissions, then reconnect the source.
- The beta tables (agents, conversations, conversation entries, libraries, library documents, traces, and spans) are off by default because Mistral marks those endpoint groups as beta and may change their shape. Enable them only if you need them.
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.