mistral-haystack 2.0.0__tar.gz → 2.1.0__tar.gz

{mistral_haystack-2.0.0 → mistral_haystack-2.1.0}/CHANGELOG.md

@@ -1,5 +1,25 @@
 # Changelog
 
+## [integrations/mistral-v2.0.0] - 2026-09-08
+
+### 🚀 Features
+
+- [**breaking**] Mistral - add lifecycle handling (#3929)
+
+### 🐛 Bug Fixes
+
+- Fix new issues raised by ruff 0.16.0 (#3670)
+- Standardize license files (#3771)
+
+### 🧪 Testing
+
+- Fix Mistral test due to new OpenAI SDK release (#3879)
+
+### 🧹 Chores
+
+- Clarify how generation_kwargs passed in run are handled (#3805)
+
+
 ## [integrations/mistral-v1.5.0] - 2026-07-06
 
 ### 🐛 Bug Fixes

{mistral_haystack-2.0.0 → mistral_haystack-2.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: mistral-haystack
-Version: 2.0.0
+Version: 2.1.0
 Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/mistral#readme
 Project-URL: Issues, https://github.com/deepset-ai/haystack-core-integrations/issues
 Project-URL: Source, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/mistral

{mistral_haystack-2.0.0 → mistral_haystack-2.1.0}/examples/indexing_ocr_pipeline.py

@@ -1,6 +1,11 @@
+# SPDX-FileCopyrightText: 2025-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 # To run this example, you will need to:
 # 1. Set a `MISTRAL_API_KEY` environment variable
 # 2. Place a PDF file named `sample.pdf` in the same directory as this script
+# 3. Run this example from that directory
 #
 # This example demonstrates OCR document processing with structured annotations,
 # embedding the extracted documents using Mistral embeddings, and storing them
@@ -13,7 +18,7 @@
 from haystack import Pipeline
 from haystack.components.writers import DocumentWriter
 from haystack.document_stores.in_memory import InMemoryDocumentStore
-from mistralai.models import DocumentURLChunk
+from mistralai.client.models import DocumentURLChunk
 from pydantic import BaseModel, Field
 
 from haystack_integrations.components.converters.mistral.ocr_document_converter import (

{mistral_haystack-2.0.0 → mistral_haystack-2.1.0}/examples/indexing_pipeline.py

@@ -1,5 +1,9 @@
-# To run this example, you will need an to set a `MISTRAL_API_KEY` environment variable.
-# This example streams chat replies to the console.
+# SPDX-FileCopyrightText: 2024-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+# To run this example, set the `MISTRAL_API_KEY` environment variable
+# and install `trafilatura`, used by HTMLToDocument: `pip install trafilatura`
 
 from haystack import Pipeline
 from haystack.components.converters import HTMLToDocument

{mistral_haystack-2.0.0 → mistral_haystack-2.1.0}/examples/streaming_chat_with_rag.py

@@ -1,4 +1,9 @@
-# To run this example, you will need an to set a `MISTRAL_API_KEY` environment variable.
+# SPDX-FileCopyrightText: 2024-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+# To run this example, set the `MISTRAL_API_KEY` environment variable
+# and install `trafilatura`, used by HTMLToDocument: `pip install trafilatura`.
 # This example streams chat replies to the console.
 
 from haystack import Pipeline

{mistral_haystack-2.0.0 → mistral_haystack-2.1.0}/src/haystack_integrations/components/converters/mistral/ocr_document_converter.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2025-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import json
 import re
 from pathlib import Path
@@ -46,12 +50,12 @@ class MistralOCRDocumentConverter:
     **Usage Example:**
     ```python
     from haystack.utils import Secret
-    from haystack_integrations.mistral import MistralOCRDocumentConverter
-    from mistralai.models import DocumentURLChunk, ImageURLChunk, FileChunk
+    from haystack_integrations.components.converters.mistral import MistralOCRDocumentConverter
+    from mistralai.client.models import DocumentURLChunk, ImageURLChunk, FileChunk
 
     converter = MistralOCRDocumentConverter(
         api_key=Secret.from_env_var("MISTRAL_API_KEY"),
-        model="mistral-ocr-2505"
+        model="mistral-ocr-latest"
     )
 
     # Process multiple sources
@@ -68,8 +72,9 @@ class MistralOCRDocumentConverter:
 
     **Structured Output Example:**
     ```python
+    from mistralai.client.models import DocumentURLChunk
     from pydantic import BaseModel, Field
-    from haystack_integrations.mistral import MistralOCRDocumentConverter
+    from haystack_integrations.components.converters.mistral import MistralOCRDocumentConverter
 
     # Define schema for structured image annotations
     class ImageAnnotation(BaseModel):
@@ -80,11 +85,11 @@ class MistralOCRDocumentConverter:
     # Define schema for structured document annotations
     class DocumentAnnotation(BaseModel):
         language: str = Field(..., description="Primary language of the document")
-        chapter_titles: List[str] = Field(..., description="Detected chapter or section titles")
-        urls: List[str] = Field(..., description="URLs found in the text")
+        chapter_titles: list[str] = Field(..., description="Detected chapter or section titles")
+        urls: list[str] = Field(..., description="URLs found in the text")
 
     converter = MistralOCRDocumentConverter(
-        model="mistral-ocr-2505",
+        model="mistral-ocr-latest",
     )
 
     sources = [DocumentURLChunk(document_url="https://example.com/report.pdf")]
@@ -100,10 +105,10 @@ class MistralOCRDocumentConverter:
     """
 
     SUPPORTED_MODELS: ClassVar[list[str]] = [
-        "mistral-ocr-2512",
+        "mistral-ocr-3-0",
+        "mistral-ocr-4-0",
+        "mistral-ocr-4-1",
         "mistral-ocr-latest",
-        "mistral-ocr-2503",
-        "mistral-ocr-2505",
     ]
     """A list of models supported by Mistral AI
     see [Mistral AI docs](https://docs.mistral.ai/getting-started/models) for more information
@@ -112,7 +117,7 @@ class MistralOCRDocumentConverter:
     def __init__(
         self,
         api_key: Secret = Secret.from_env_var("MISTRAL_API_KEY"),
-        model: str = "mistral-ocr-2505",
+        model: str = "mistral-ocr-4-1",
         include_image_base64: bool = False,
         pages: list[int] | None = None,
         image_limit: int | None = None,
@@ -125,8 +130,7 @@ class MistralOCRDocumentConverter:
         :param api_key:
             The Mistral API key. Defaults to the MISTRAL_API_KEY environment variable.
         :param model:
-            The OCR model to use. Default is "mistral-ocr-2505".
-            See more: https://docs.mistral.ai/getting-started/models/models_overview/
+            The OCR model to use. See more: https://docs.mistral.ai/getting-started/models/models_overview/
         :param include_image_base64:
             If True, includes base64 encoded images in the response.
             This may significantly increase response size and processing time.

{mistral_haystack-2.0.0 → mistral_haystack-2.1.0}/tests/test_ocr_document_converter.py

@@ -29,7 +29,7 @@ class TestInitialization:
         converter = MistralOCRDocumentConverter()
 
         assert converter.api_key == Secret.from_env_var("MISTRAL_API_KEY")
-        assert converter.model == "mistral-ocr-2505"
+        assert converter.model == "mistral-ocr-4-1"
         assert converter.include_image_base64 is False
         assert converter.pages is None
         assert converter.image_limit is None
@@ -72,7 +72,7 @@ class TestSerialization:
                     "strict": True,
                     "type": "env_var",
                 },
-                "model": "mistral-ocr-2505",
+                "model": "mistral-ocr-4-1",
                 "include_image_base64": False,
                 "pages": None,
                 "image_limit": None,