Mistral-Inference v1.4.0 Adds Vision via Pixtral-12B

Mistral AI released mistral-inference v1.4.0, adding multimodal vision support to its open-source inference library through a new model called Pixtral. The update enables the Pixtral-12B-2409 model to process images alongside text, accessible via a command-line interface or Python API after a standard pip upgrade.

Research

Papers, benchmarks, and what we'd build differently after reading them.

All Research →

Research · May 21 · 6 min

NeuroAgent Automates Multimodal Neuroimaging Pipelines

Tutorials

Code-first dispatches. Most run in under fifteen minutes.

All Tutorials →

Tutorial · May 18 · 11 min

Multimodal Retrieval Pipeline with LlamaIndex AgentMesh Trust Layer

Tutorial · May 18 · 10 min

Per-Generation LLM Cost Tracking with Langfuse v4 SDK

Tutorial · May 18 · 8 min

Wiring OpenTelemetry Spans into a LangGraph Agent for Cost Attribution

Tutorial · May 18 · 7 min

Wiring OpenTelemetry Spans into a LightRAG Retrieval Pipeline

Tools this week View all →

Mistral

Mistral's open-weight model family and the mistral-inference reference runtime, now including Pixtral vision support.

May 21

Mistral's open-weight model family and the mistral-inference reference runtime, now including Pixtral vision support.

LangGraph

Stateful, multi-actor agent graphs built on top of LangChain.

May 18

Stateful, multi-actor agent graphs built on top of LangChain.

LlamaIndex

Data framework for LLM applications, including the AgentMesh trust layer for multi-agent retrieval.

May 18

Data framework for LLM applications, including the AgentMesh trust layer for multi-agent retrieval.

LightRAG

Graph-augmented retrieval framework with OpenInference instrumentation.

May 18

Graph-augmented retrieval framework with OpenInference instrumentation.