Bump pydantic support to v2 (#1645)

* update setup.py

* changes from bump-pydantic

* Style and some more changes

* update test client usage with fastapi update

* fix tests/test_pipeline_benchmark.py

* pin fastapi version

* Use pydantic v1 for Numpy Schemas

* Fix tests/deepsparse/pipelines/test_bucketing.py

* Deprecate haystack

* Remove launch.json

Author: rahul-tuli

.github/workflows/test-check.yaml

@@ -97,6 +97,6 @@ jobs:
       - name: "Clean sparsezoo directory"
         run: rm -r sparsezoo/
       - name: ⚙️ Install dependencies
-        run: pip install .[dev,haystack]
+        run: pip install .[dev]
       - name: Run integrations tests
         run: make test_integrations

MANIFEST.in

@@ -1,6 +1,5 @@
 include LICENSE
 include utils/artifacts.py
-include src/deepsparse/transformers/haystack/haystack_reqs.txt
 recursive-include src/deepsparse/avx2 *
 recursive-include src/deepsparse/avx512 *
 recursive-include src/deepsparse/neon *

examples/vit_pose/schemas.py

@@ -15,7 +15,7 @@
 from typing import List
 
 import numpy
-from pydantic import BaseModel
+from pydantic import BaseModel, ConfigDict
 
 from deepsparse.pipelines.computer_vision import ComputerVisionSchema
 
@@ -32,6 +32,4 @@ class VitPoseInput(ComputerVisionSchema):
 
 class VitPoseOutput(BaseModel):
     out: List[numpy.ndarray]
-
-    class Config:
-        arbitrary_types_allowed = True
+    model_config = ConfigDict(arbitrary_types_allowed=True)

integrations/haystack/README.md

@@ -0,0 +1,14 @@
+
+def test_placeholder():
+    """
+    Needed to make the test suite run and not throw
+    an error about no tests being found when
+    `make test_integrations` is used.
+    
+    The error would look like this:
+        make: *** [Makefile:61: test_integrations] Error 5
+    
+    More information can be found here:
+        https://github.com/pytest-dev/pytest/issues/2393
+    """
+    pass

integrations/haystack/tests/test_smoke.py

@@ -77,17 +77,10 @@
 ]
 
 
-def _parse_requirements_file(file_path):
-    with open(file_path, "r") as requirements_file:
-        lines = requirements_file.read().splitlines()
-
-    return [line for line in lines if len(line) > 0 and line[0] != "#"]
-
-
 _deps = [
     "numpy>=1.16.3",
     "onnx>=1.5.0,<1.15.0",
-    "pydantic>=1.8.2,<2.0.0",
+    "pydantic>=2.0.0,<2.8.0",
     "requests>=2.0.0",
     "tqdm>=4.0.0",
     "protobuf>=3.12.2",
@@ -122,7 +115,7 @@ def _parse_requirements_file(file_path):
 ]
 _server_deps = [
     "uvicorn>=0.15.0",
-    "fastapi>=0.70.0,<0.87.0",
+    "fastapi>=0.100.0,<0.111",
     "requests>=2.26.0",
     "python-multipart>=0.0.5",
     "prometheus-client>=0.14.1",
@@ -153,17 +146,6 @@ def _parse_requirements_file(file_path):
 ]
 _sentence_transformers_integration_deps = ["optimum-deepsparse"] + _torch_deps
 
-# haystack dependencies are installed from a requirements file to avoid
-# conflicting versions with NM's deepsparse/transformers
-_haystack_requirements_file_path = os.path.join(
-    os.path.dirname(os.path.realpath(__file__)),
-    "src",
-    "deepsparse",
-    "transformers",
-    "haystack",
-    "haystack_reqs.txt",
-)
-_haystack_integration_deps = _parse_requirements_file(_haystack_requirements_file_path)
 _clip_deps = [
     "open_clip_torch==2.20.0",
     "transformers<4.40",
@@ -270,7 +252,6 @@ def _setup_extras() -> Dict:
         "image_classification": _computer_vision_deps,
         "yolo": _computer_vision_deps,
         "yolov5": _computer_vision_deps,
-        "haystack": _haystack_integration_deps,
         "openpifpaf": _openpifpaf_integration_deps,
         "yolov8": _yolov8_integration_deps,
         "transformers": _transformers_integration_deps,

integrations/test_placeholder.py

@@ -17,7 +17,7 @@
 import random
 import string
 from os import path
-from typing import Dict, List, Tuple
+from typing import Dict, List, Tuple, get_args
 
 import numpy
 
@@ -58,15 +58,11 @@ def get_input_schema_type(pipeline: Pipeline) -> str:
     if SchemaType.TEXT_SEQ in input_schema_requirements:
         if input_schema_fields.get(SchemaType.TEXT_SEQ).alias == SchemaType.TEXT_PROMPT:
             return SchemaType.TEXT_PROMPT
-        sequence_types = [
-            f.outer_type_ for f in input_schema_fields[SchemaType.TEXT_SEQ].sub_fields
-        ]
+        sequence_types = get_args(input_schema_fields[SchemaType.TEXT_SEQ].annotation)
         if List[str] in sequence_types:
             return SchemaType.TEXT_SEQ
     elif SchemaType.TEXT_INPUT in input_schema_requirements:
-        sequence_types = [
-            f.outer_type_ for f in input_schema_fields[SchemaType.TEXT_INPUT].sub_fields
-        ]
+        sequence_types = get_args(input_schema_fields[SchemaType.TEXT_INPUT].annotation)
         if List[str] in sequence_types:
             return SchemaType.TEXT_INPUT
     elif SchemaType.QUESTION in input_schema_requirements:

setup.py

@@ -30,10 +30,10 @@ class CLIPDecoderInput(BaseModel):
     """
 
     text_embeddings: Any = Field(
-        description="np.array of text emebddings from the " "text branch"
+        None, description="np.array of text emebddings from the " "text branch"
     )
     image_embeddings: Any = Field(
-        description="np.array of image embeddings from the " "visual branch"
+        None, description="np.array of image embeddings from the " "visual branch"
     )
 
 

src/deepsparse/benchmark/data_creation.py

@@ -36,15 +36,15 @@ class Metric(BaseModel):
 
 
 class Dataset(BaseModel):
-    type: Optional[str] = Field(description="Type of dataset")
+    type: Optional[str] = Field(None, description="Type of dataset")
     name: str = Field(description="Name of the dataset")
-    config: Any = Field(description="Configuration for the dataset")
-    split: Optional[str] = Field(description="Split of the dataset")
+    config: Any = Field(None, description="Configuration for the dataset")
+    split: Optional[str] = Field(None, description="Split of the dataset")
 
 
 class EvalSample(BaseModel):
-    input: Any = Field(description="Sample input to the model")
-    output: Any = Field(description="Sample output from the model")
+    input: Any = Field(None, description="Sample input to the model")
+    output: Any = Field(None, description="Sample output from the model")
 
 
 class Evaluation(BaseModel):
@@ -55,7 +55,7 @@ class Evaluation(BaseModel):
     dataset: Dataset = Field(description="Dataset that the evaluation was performed on")
     metrics: List[Metric] = Field(description="List of metrics for the evaluation")
     samples: Optional[List[EvalSample]] = Field(
-        description="List of samples for the evaluation"
+        None, description="List of samples for the evaluation"
     )
 
 
@@ -64,8 +64,9 @@ class Result(BaseModel):
         description="Evaluation result represented in the unified, structured format"
     )
     raw: Any = Field(
+        None,
         description="Evaluation result represented in the raw format "
-        "(characteristic for the specific evaluation integration)"
+        "(characteristic for the specific evaluation integration)",
     )
 
 
@@ -97,7 +98,7 @@ def _save_to_json(result: Result, save_path: str):
 
 
 def _save_to_yaml(result: Result, save_path: str):
-    _save(yaml.dump(result.dict()), save_path, expected_ext=".yaml")
+    _save(yaml.dump(result.model_dump()), save_path, expected_ext=".yaml")
 
 
 def _save(data: str, save_path: str, expected_ext: str):