yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2026-01-08 21:28:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

Sync Core Integrations API reference (mistral) on Docusaurus (#9947)

Browse Source 
Co-authored-by: anakin87 <44616784+anakin87@users.noreply.github.com>
This commit is contained in:
Haystack Bot 2025-10-27 12:42:41 +01:00 committed by GitHub
parent 8d0755455d
commit 20620cd5bf
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 20 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
docs-website/reference/integrations-api/mistral.md
View File

@ -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.

5
docs-website/reference_versioned_docs/version-2.17/integrations-api/mistral.md
View File

@ -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.

5
docs-website/reference_versioned_docs/version-2.18/integrations-api/mistral.md
View File

@ -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.

5
docs-website/reference_versioned_docs/version-2.19/integrations-api/mistral.md
View File

@ -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.