From 20620cd5bfaee923df3753b04db566ea3148c7ee Mon Sep 17 00:00:00 2001 From: Haystack Bot <73523382+HaystackBot@users.noreply.github.com> Date: Mon, 27 Oct 2025 12:42:41 +0100 Subject: [PATCH] Sync Core Integrations API reference (mistral) on Docusaurus (#9947) Co-authored-by: anakin87 <44616784+anakin87@users.noreply.github.com> --- docs-website/reference/integrations-api/mistral.md | 5 +++++ .../version-2.17/integrations-api/mistral.md | 5 +++++ .../version-2.18/integrations-api/mistral.md | 5 +++++ .../version-2.19/integrations-api/mistral.md | 5 +++++ 4 files changed, 20 insertions(+) diff --git a/docs-website/reference/integrations-api/mistral.md b/docs-website/reference/integrations-api/mistral.md index b0da97561..c5f1f9132 100644 --- a/docs-website/reference/integrations-api/mistral.md +++ b/docs-website/reference/integrations-api/mistral.md @@ -432,6 +432,7 @@ Deserialized component. def run( sources: List[Union[str, Path, ByteStream, DocumentURLChunk, FileChunk, ImageURLChunk]], + meta: Optional[Union[Dict[str, Any], List[Dict[str, Any]]]] = None, bbox_annotation_schema: Optional[Type[BaseModel]] = None, document_annotation_schema: Optional[Type[BaseModel]] = None ) -> Dict[str, Any] @@ -448,6 +449,10 @@ Extract text from documents using Mistral OCR. - DocumentURLChunk: Mistral chunk for document URLs (signed or public URLs to PDFs, etc.) - ImageURLChunk: Mistral chunk for image URLs (signed or public URLs to images) - FileChunk: Mistral chunk for file IDs (files previously uploaded to Mistral) +- `meta`: Optional metadata to attach to the Documents. +This value can be either a list of dictionaries or a single dictionary. +If it's a single dictionary, its content is added to the metadata of all produced Documents. +If it's a list, the length of the list must match the number of sources, because they will be zipped. - `bbox_annotation_schema`: Optional Pydantic model for structured annotations per bounding box. When provided, a Vision LLM analyzes each image region and returns structured data. - `document_annotation_schema`: Optional Pydantic model for structured annotations for the full document. diff --git a/docs-website/reference_versioned_docs/version-2.17/integrations-api/mistral.md b/docs-website/reference_versioned_docs/version-2.17/integrations-api/mistral.md index b0da97561..c5f1f9132 100644 --- a/docs-website/reference_versioned_docs/version-2.17/integrations-api/mistral.md +++ b/docs-website/reference_versioned_docs/version-2.17/integrations-api/mistral.md @@ -432,6 +432,7 @@ Deserialized component. def run( sources: List[Union[str, Path, ByteStream, DocumentURLChunk, FileChunk, ImageURLChunk]], + meta: Optional[Union[Dict[str, Any], List[Dict[str, Any]]]] = None, bbox_annotation_schema: Optional[Type[BaseModel]] = None, document_annotation_schema: Optional[Type[BaseModel]] = None ) -> Dict[str, Any] @@ -448,6 +449,10 @@ Extract text from documents using Mistral OCR. - DocumentURLChunk: Mistral chunk for document URLs (signed or public URLs to PDFs, etc.) - ImageURLChunk: Mistral chunk for image URLs (signed or public URLs to images) - FileChunk: Mistral chunk for file IDs (files previously uploaded to Mistral) +- `meta`: Optional metadata to attach to the Documents. +This value can be either a list of dictionaries or a single dictionary. +If it's a single dictionary, its content is added to the metadata of all produced Documents. +If it's a list, the length of the list must match the number of sources, because they will be zipped. - `bbox_annotation_schema`: Optional Pydantic model for structured annotations per bounding box. When provided, a Vision LLM analyzes each image region and returns structured data. - `document_annotation_schema`: Optional Pydantic model for structured annotations for the full document. diff --git a/docs-website/reference_versioned_docs/version-2.18/integrations-api/mistral.md b/docs-website/reference_versioned_docs/version-2.18/integrations-api/mistral.md index b0da97561..c5f1f9132 100644 --- a/docs-website/reference_versioned_docs/version-2.18/integrations-api/mistral.md +++ b/docs-website/reference_versioned_docs/version-2.18/integrations-api/mistral.md @@ -432,6 +432,7 @@ Deserialized component. def run( sources: List[Union[str, Path, ByteStream, DocumentURLChunk, FileChunk, ImageURLChunk]], + meta: Optional[Union[Dict[str, Any], List[Dict[str, Any]]]] = None, bbox_annotation_schema: Optional[Type[BaseModel]] = None, document_annotation_schema: Optional[Type[BaseModel]] = None ) -> Dict[str, Any] @@ -448,6 +449,10 @@ Extract text from documents using Mistral OCR. - DocumentURLChunk: Mistral chunk for document URLs (signed or public URLs to PDFs, etc.) - ImageURLChunk: Mistral chunk for image URLs (signed or public URLs to images) - FileChunk: Mistral chunk for file IDs (files previously uploaded to Mistral) +- `meta`: Optional metadata to attach to the Documents. +This value can be either a list of dictionaries or a single dictionary. +If it's a single dictionary, its content is added to the metadata of all produced Documents. +If it's a list, the length of the list must match the number of sources, because they will be zipped. - `bbox_annotation_schema`: Optional Pydantic model for structured annotations per bounding box. When provided, a Vision LLM analyzes each image region and returns structured data. - `document_annotation_schema`: Optional Pydantic model for structured annotations for the full document. diff --git a/docs-website/reference_versioned_docs/version-2.19/integrations-api/mistral.md b/docs-website/reference_versioned_docs/version-2.19/integrations-api/mistral.md index b0da97561..c5f1f9132 100644 --- a/docs-website/reference_versioned_docs/version-2.19/integrations-api/mistral.md +++ b/docs-website/reference_versioned_docs/version-2.19/integrations-api/mistral.md @@ -432,6 +432,7 @@ Deserialized component. def run( sources: List[Union[str, Path, ByteStream, DocumentURLChunk, FileChunk, ImageURLChunk]], + meta: Optional[Union[Dict[str, Any], List[Dict[str, Any]]]] = None, bbox_annotation_schema: Optional[Type[BaseModel]] = None, document_annotation_schema: Optional[Type[BaseModel]] = None ) -> Dict[str, Any] @@ -448,6 +449,10 @@ Extract text from documents using Mistral OCR. - DocumentURLChunk: Mistral chunk for document URLs (signed or public URLs to PDFs, etc.) - ImageURLChunk: Mistral chunk for image URLs (signed or public URLs to images) - FileChunk: Mistral chunk for file IDs (files previously uploaded to Mistral) +- `meta`: Optional metadata to attach to the Documents. +This value can be either a list of dictionaries or a single dictionary. +If it's a single dictionary, its content is added to the metadata of all produced Documents. +If it's a list, the length of the list must match the number of sources, because they will be zipped. - `bbox_annotation_schema`: Optional Pydantic model for structured annotations per bounding box. When provided, a Vision LLM analyzes each image region and returns structured data. - `document_annotation_schema`: Optional Pydantic model for structured annotations for the full document.