deepeval 3.4.8__tar.gz → 3.5.0__tar.gz

{deepeval-3.4.8 → deepeval-3.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: deepeval
-Version: 3.4.8
+Version: 3.5.0
 Summary: The LLM Evaluation Framework
 Home-page: https://github.com/confident-ai/deepeval
 License: Apache-2.0
@@ -25,6 +25,8 @@ Requires-Dist: opentelemetry-exporter-otlp-proto-grpc (>=1.24.0,<2.0.0)
 Requires-Dist: opentelemetry-sdk (>=1.24.0,<2.0.0)
 Requires-Dist: portalocker
 Requires-Dist: posthog (>=6.3.0,<7.0.0)
+Requires-Dist: pydantic (>=2.11.7,<3.0.0)
+Requires-Dist: pydantic-settings (>=2.10.1,<3.0.0)
 Requires-Dist: pyfiglet
 Requires-Dist: pytest
 Requires-Dist: pytest-asyncio
@@ -187,16 +189,6 @@ Let's pretend your LLM application is a RAG based customer support chatbot; here
 ```
 pip install -U deepeval
 ```
-### Environment variables (.env / .env.local)
-
-DeepEval auto-loads `.env.local` then `.env` from the current working directory **at import time**.
-**Precedence:** process env -> `.env.local` -> `.env`.
-Opt out with `DEEPEVAL_DISABLE_DOTENV=1`.
-
-```bash
-cp .env.example .env.local
-# then edit .env.local (ignored by git)
-```
 
 ## Create an account (highly recommended)
 
@@ -389,9 +381,20 @@ evaluate(dataset, [answer_relevancy_metric])
 dataset.evaluate([answer_relevancy_metric])
 ```
 
-# LLM Evaluation With Confident AI
+## A Note on Env Variables (.env / .env.local)
+
+DeepEval auto-loads `.env.local` then `.env` from the current working directory **at import time**.
+**Precedence:** process env -> `.env.local` -> `.env`.
+Opt out with `DEEPEVAL_DISABLE_DOTENV=1`.
+
+```bash
+cp .env.example .env.local
+# then edit .env.local (ignored by git)
+```
+
+# DeepEval With Confident AI
 
-The correct LLM evaluation lifecycle is only achievable with [the DeepEval platform](https://confident-ai.com?utm_source=Github). It allows you to:
+DeepEval's cloud platform, [Confident AI](https://confident-ai.com?utm_source=Github), allows you to:
 
 1. Curate/annotate evaluation datasets on the cloud
 2. Benchmark LLM app using dataset, and compare with previous iterations to experiment which models/prompts works best

{deepeval-3.4.8 → deepeval-3.5.0}/README.md

@@ -140,16 +140,6 @@ Let's pretend your LLM application is a RAG based customer support chatbot; here
 ```
 pip install -U deepeval
 ```
-### Environment variables (.env / .env.local)
-
-DeepEval auto-loads `.env.local` then `.env` from the current working directory **at import time**.
-**Precedence:** process env -> `.env.local` -> `.env`.
-Opt out with `DEEPEVAL_DISABLE_DOTENV=1`.
-
-```bash
-cp .env.example .env.local
-# then edit .env.local (ignored by git)
-```
 
 ## Create an account (highly recommended)
 
@@ -342,9 +332,20 @@ evaluate(dataset, [answer_relevancy_metric])
 dataset.evaluate([answer_relevancy_metric])
 ```
 
-# LLM Evaluation With Confident AI
+## A Note on Env Variables (.env / .env.local)
+
+DeepEval auto-loads `.env.local` then `.env` from the current working directory **at import time**.
+**Precedence:** process env -> `.env.local` -> `.env`.
+Opt out with `DEEPEVAL_DISABLE_DOTENV=1`.
+
+```bash
+cp .env.example .env.local
+# then edit .env.local (ignored by git)
+```
+
+# DeepEval With Confident AI
 
-The correct LLM evaluation lifecycle is only achievable with [the DeepEval platform](https://confident-ai.com?utm_source=Github). It allows you to:
+DeepEval's cloud platform, [Confident AI](https://confident-ai.com?utm_source=Github), allows you to:
 
 1. Curate/annotate evaluation datasets on the cloud
 2. Benchmark LLM app using dataset, and compare with previous iterations to experiment which models/prompts works best

{deepeval-3.4.8 → deepeval-3.5.0}/deepeval/__init__.py

@@ -3,9 +3,9 @@ import warnings
 import re
 
 # load environment variables before other imports
-from .env import autoload_dotenv as _autoload_dotenv
+from deepeval.config.settings import autoload_dotenv, get_settings
 
-_autoload_dotenv()
+autoload_dotenv()
 
 from ._version import __version__
 from deepeval.evaluate import evaluate, assert_test
@@ -14,9 +14,12 @@ from deepeval.test_run import on_test_run_end, log_hyperparameters
 from deepeval.utils import login
 from deepeval.telemetry import *
 
-if os.getenv("DEEPEVAL_GRPC_LOGGING") != "1":
-    os.environ["GRPC_VERBOSITY"] = "ERROR"
-    os.environ["GRPC_TRACE"] = ""
+
+settings = get_settings()
+if not settings.DEEPEVAL_GRPC_LOGGING:
+    os.environ.setdefault("GRPC_VERBOSITY", "ERROR")
+    os.environ.setdefault("GRPC_TRACE", "")
+
 
 __all__ = [
     "login",

deepeval-3.5.0/deepeval/_version.py

@@ -0,0 +1 @@
+__version__: str = "3.5.0"

{deepeval-3.4.8 → deepeval-3.5.0}/deepeval/benchmarks/drop/drop.py

@@ -1,6 +1,5 @@
-from typing import List, Optional, Dict
+from typing import List, Optional, Dict, Union
 from tqdm import tqdm
-from typing import Union
 
 from deepeval.dataset import Golden
 from deepeval.benchmarks.base_benchmark import (
@@ -50,7 +49,7 @@ class DROP(DeepEvalBaseBenchmark):
         self,
         model: DeepEvalBaseLLM,
         *args,
-        batch_size: int | None = None,
+        batch_size: Union[int, None] = None,
         **kwargs,
     ) -> DeepEvalBaseBenchmarkResult:
         import pandas as pd

{deepeval-3.4.8 → deepeval-3.5.0}/deepeval/benchmarks/hellaswag/hellaswag.py

@@ -1,4 +1,4 @@
-from typing import List, Dict, Optional
+from typing import List, Dict, Optional, Union
 from tqdm import tqdm
 
 from deepeval.dataset import Golden
@@ -51,7 +51,7 @@ class HellaSwag(DeepEvalBaseBenchmark):
         self,
         model: DeepEvalBaseLLM,
         *args,
-        batch_size: int | None = None,
+        batch_size: Union[int, None] = None,
         **kwargs,
     ) -> DeepEvalBaseBenchmarkResult:
         import pandas as pd

{deepeval-3.4.8 → deepeval-3.5.0}/deepeval/benchmarks/logi_qa/logi_qa.py

@@ -1,4 +1,4 @@
-from typing import List, Optional, Dict
+from typing import List, Optional, Dict, Union
 from tqdm import tqdm
 import requests
 import json
@@ -52,7 +52,7 @@ class LogiQA(DeepEvalBaseBenchmark):
         self,
         model: DeepEvalBaseLLM,
         *args,
-        batch_size: int | None = None,
+        batch_size: Union[int, None] = None,
         **kwargs,
     ) -> DeepEvalBaseBenchmarkResult:
         import pandas as pd

{deepeval-3.4.8 → deepeval-3.5.0}/deepeval/benchmarks/math_qa/math_qa.py

@@ -1,4 +1,4 @@
-from typing import List, Optional, Dict
+from typing import List, Optional, Dict, Union
 from tqdm import tqdm
 
 from deepeval.dataset import Golden
@@ -50,7 +50,7 @@ class MathQA(DeepEvalBaseBenchmark):
         self,
         model: DeepEvalBaseLLM,
         *args,
-        batch_size: int | None = None,
+        batch_size: Union[int, None] = None,
         **kwargs,
     ) -> DeepEvalBaseBenchmarkResult:
         import pandas as pd

{deepeval-3.4.8 → deepeval-3.5.0}/deepeval/benchmarks/mmlu/mmlu.py

@@ -1,4 +1,4 @@
-from typing import List, Optional, Dict
+from typing import List, Optional, Dict, Union
 from tqdm import tqdm
 
 from deepeval.dataset import Golden
@@ -49,7 +49,7 @@ class MMLU(DeepEvalBaseBenchmark):
         self,
         model: DeepEvalBaseLLM,
         *args,
-        batch_size: int | None = None,
+        batch_size: Union[int, None] = None,
         **kwargs,
     ) -> DeepEvalBaseBenchmarkResult:
         import pandas as pd

{deepeval-3.4.8 → deepeval-3.5.0}/deepeval/benchmarks/truthful_qa/truthful_qa.py

@@ -1,4 +1,4 @@
-from typing import List, Dict, Optional
+from typing import List, Dict, Optional, Union
 from tqdm import tqdm
 
 from deepeval.dataset import Golden
@@ -59,7 +59,7 @@ class TruthfulQA(DeepEvalBaseBenchmark):
         self,
         model: DeepEvalBaseLLM,
         *args,
-        batch_size: int | None = None,
+        batch_size: Union[int, None] = None,
         **kwargs,
     ) -> DeepEvalBaseBenchmarkResult:
         import pandas as pd