# llm_vision_mistral A RocketRide node that sends images to Mistral AI's vision-capable models and returns text analysis. ## What it does Accepts either a single image (via the `image` lane) or a stream of image documents (via the `documents` lane, e.g. from a frame grabber), calls the configured Mistral vision model, and returns the model's response as text or as text documents. Uses the official **mistralai** Python SDK with a custom `httpx` client (120 s timeout, redirects followed) to handle large image payloads. Token counting uses the **mistral-common** tokenizer, with per-model tokenizers loaded strictly; the v3 tokenizer is used as a fallback when no model-specific tokenizer is available. All requests are sent with **temperature 0.0** for deterministic output. Transient failures (timeouts, connection errors, 5xx responses) are retried up to 3 times with exponential backoff. The base delay scales with model size: 2.0 s for `large` models, 1.5 s for `medium`, 1.0 s for all others. API errors are translated into user-friendly messages covering authentication failures, rate limits, quota exhaustion, content-policy violations, and image-processing errors. --- ## Configuration ### Lanes | Lane in | Lane out | Description | | ----------- | ----------- | ------------------------------------------------------------------------------ | | `image` | `text` | Analyze a single image, receive text | | `documents` | `documents` | Analyze image documents, return text analysis with original metadata preserved | On the `image` lane, incoming image bytes are buffered across chunks, base64-encoded with the source MIME type, and sent to the model together with the configured analysis prompt. The answer is written downstream as text. On the `documents` lane, only documents of type `Image` are processed. Documents with a different type, or an `Image` document with empty content, are skipped with a warning. The document's `page_content` is expected to be base64-encoded PNG (the frame grabber always outputs PNG). Each answer is emitted as a `Text` document that preserves the original metadata (`chunkId`, `time_stamp`, etc.). If inference fails for a chunk, a warning is logged and processing continues with the next document. ### Fields | Field | Type | Description | |---|---|---| | `model` | string | Mistral Vision model | | `modelTotalTokens` | number | Maximum context length in tokens | | `systemPrompt` | string | Define the model's role and behavior for image analysis | | `prompt` | string | Describe what you want to analyze or extract from the image | | `profile` | string | Default "mistral-large-3". Select the Mistral vision model to use | ### Profiles | Profile key | Title | Model | Context tokens | | --------------------- | -------------------------------------------- | --------------------- | -------------- | | `mistral-large-3` _(default)_ | Mistral Large 3 - Premier Vision | `mistral-large-2512` | 256,000 | | `mistral-medium-3.1` | Mistral Medium 3.1 - Balanced Vision | `mistral-medium-2508` | 128,000 | | `mistral-small-3.2` | Mistral Small 3.2 - Fast & Cheap Vision | `mistral-small-2506` | 128,000 | | `ministral-14b-3` | Ministral 3 14B - High Performance Vision | `ministral-14b-2512` | 256,000 | | `ministral-8b-3` | Ministral 3 8B - Balanced Vision | `ministral-8b-2512` | 256,000 | | `ministral-3b-3` | Ministral 3 3B - Efficient Vision | `ministral-3b-2512` | 256,000 | --- ## Image input The node accepts images in the following formats: - **HTTP(S) URL**: passed to the Mistral API as-is. - **Data URI** (`data:image/...` or `data:application/...`): passed as-is. - **Local file path**: read from disk, base64-encoded, and sent as a data URI. Files over **10 MB** are rejected. MIME type is inferred from the file extension (`.jpg`/`.jpeg` -> `image/jpeg`, `.png` -> `image/png`, `.gif` -> `image/gif`, `.webp` -> `image/webp`; any unrecognized extension defaults to `image/jpeg`). --- ## Authentication Provide a Mistral AI API key in the `apikey` field for the selected profile. The node validates the key format at startup: if you supply an OpenAI key (starting with `sk-`) or a Google AI/Gemini key (starting with `AI`), initialization fails immediately with a specific error message pointing to the wrong provider. See the [Mistral vision documentation](https://docs.mistral.ai/capabilities/vision/) for model capabilities and upstream limits. --- ## Schema | Field | Type | Description | Default | |---|---|---|---| | `image_vision_mistral.profile` | `string` | **Vision Model**
Select the Mistral vision model to use | `"mistral-large-3"` | | `model` | `string` | **Model**
Mistral Vision model | | | `modelTotalTokens` | `number` | **Tokens**
Maximum context length in tokens | | | `vision.prompt` | `string` | **Analysis Prompt**
Describe what you want to analyze or extract from the image | | | `vision.systemPrompt` | `string` | **System Instructions**
Define the model's role and behavior for image analysis | | ## Dependencies - `mistralai` - `mistral-common[sentencepiece]` ## Source [ View source](https://github.com/rocketride-org/rocketride-server/tree/develop/nodes/src/nodes/llm_vision_mistral)