Multimodal: Providers Extended to handle image/pdf/multimodal flows#628

Merged

vprashrex merged 17 commits into

mainfrom

feature/multimodal-integration

Mar 2, 2026

Commits on Feb 24, 2026

Enhance multimodal support: Add Image and PDF input types, update processing logic
vprashrex
committed

Commits on Feb 26, 2026

Enhance multimodal support: Allow None for instructions in Image, PDF, and Multimodal parameters; update validation to restrict audio input in multimodal processing.
vprashrex
committed
Merge branch 'main' into feature/multimodal-integration
vprashrex
committed
Refactor multimodal input handling: Introduce ContentPart type for better type management and update relevant classes to use it.
vprashrex
committed
Add comprehensive tests for multimodal input validation and processing
vprashrex
committed
removed multimodal, image and pdf llmparams and from both input type and completion type
vprashrex
committed
added the table reference for image, pdf and multimodal
vprashrex
committed

Commits on Feb 28, 2026

Remove completion_type for image, pdf, and multimodal types in NativeCompletionConfig and related methods in GoogleAIProvider
vprashrex
committed

Commits on Mar 2, 2026

Enhance LLM API documentation to support multimodal input types and clarify configuration parameters
vprashrex
committed