Merge pull request #14 from confident-ai/main

merge from main.

.github/workflows/deepeval-results.yml

@@ -37,9 +37,6 @@ jobs:
         if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
         run: poetry install --no-interaction
 
-      - name: Run tests without pytest
-        run: poetry run python tests/test_without_pytest.py
-
       - name: Run deepeval tests and capture output
         run: poetry run deepeval test run tests/test_quickstart.py > output.txt 2>&1
 

.github/workflows/test.yml

@@ -65,4 +65,4 @@ jobs:
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
         run: |
-          poetry run pytest tests/ --ignore=tests/test_llm_metric.py --ignore=tests/test_overall_score.py
+          poetry run pytest tests/ --ignore=tests/test_llm_metric.py

README.md

@@ -73,7 +73,7 @@ from deepeval.evaluator import assert_test
 
 def test_case():
     input = "What if these shoes don't fit?"
-    context = "All customers are eligible for a 30 day full refund at no extra costs."
+    context = ["All customers are eligible for a 30 day full refund at no extra costs."]
 
     # Replace this with the actual output from your LLM application
     actual_output = "We offer a 30-day full refund at no extra costs."
@@ -118,7 +118,7 @@ deepeval test run test_chatbot.py
 
 You should see a link displayed in the CLI once the test has finished running. Paste it into your browser to view the results!
 
-![ok](https://d2lsxfc3p6r9rv.cloudfront.net/dashboard.png)
+![ok](https://d2lsxfc3p6r9rv.cloudfront.net/test-summary.png)
 
 <br />
 

deepeval/_version.py

@@ -1 +1 @@
-__version__: str = "0.20.17"
+__version__: str = "0.20.19"

deepeval/cli/test.py

@@ -2,8 +2,6 @@
 import typer
 import os
 from typing_extensions import Annotated
-from deepeval.metrics.overall_score import assert_overall_score
-from .cli_key_handler import set_env_vars
 from typing import Optional
 from deepeval.test_run import test_run_manager, TEMP_FILE_NAME
 from deepeval.utils import delete_file_if_exists
@@ -17,67 +15,6 @@
 app = typer.Typer(name="test")
 
 
-def sample():
-    set_env_vars()
-    print("Sending sample test results...")
-    print(
-        "If this is your first time running these models, it may take a while."
-    )
-    try:
-        query = "How does photosynthesis work?"
-        output = "Photosynthesis is the process by which green plants and some other organisms use sunlight to synthesize foods with the help of chlorophyll pigment."
-        expected_output = "Photosynthesis is the process by which green plants and some other organisms use sunlight to synthesize food with the help of chlorophyll pigment."
-        context = "Biology"
-
-        assert_overall_score(query, output, expected_output, context)
-
-    except AssertionError as e:
-        pass
-    try:
-        query = "What is the capital of France?"
-        output = "The capital of France is Paris."
-        expected_output = "The capital of France is Paris."
-        context = "Geography"
-
-        assert_overall_score(query, output, expected_output, context)
-
-    except AssertionError as e:
-        pass
-    try:
-        query = "What are the major components of a cell?"
-        output = "Cells have many major components, including the cell membrane, nucleus, mitochondria, and endoplasmic reticulum."
-        expected_output = "Cells have several major components, such as the cell membrane, nucleus, mitochondria, and endoplasmic reticulum."
-        context = "Biology"
-        minimum_score = 0.8  # Adjusting the minimum score threshold
-
-        assert_overall_score(
-            query, output, expected_output, context, minimum_score
-        )
-
-    except AssertionError as e:
-        pass
-
-    try:
-        query = "What is the capital of Japan?"
-        output = "The largest city in Japan is Tokyo."
-        expected_output = "The capital of Japan is Tokyo."
-        context = "Geography"
-
-        assert_overall_score(query, output, expected_output, context)
-    except AssertionError as e:
-        pass
-
-    try:
-        query = "Explain the theory of relativity."
-        output = "Einstein's theory of relativity is famous."
-        expected_output = "Einstein's theory of relativity revolutionized our understanding of space, time, and gravity."
-        context = "Physics"
-
-        assert_overall_score(query, output, expected_output, context)
-    except AssertionError as e:
-        pass
-
-
 def check_if_valid_file(test_file_or_directory: str):
     if "::" in test_file_or_directory:
         test_file_or_directory, test_case = test_file_or_directory.split("::")