bridgekit 0.2.0__tar.gz → 0.2.1__tar.gz

{bridgekit-0.2.0 → bridgekit-0.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: bridgekit
-Version: 0.2.0
+Version: 0.2.1
 Summary: AI tools that make you a better data scientist, not a redundant one.
 License: MIT
 Project-URL: Homepage, https://github.com/getbridgekit/bridgekit
@@ -21,8 +21,13 @@ Requires-Dist: pypdf>=3.0.0
 Requires-Dist: python-docx>=1.0.0
 Requires-Dist: python-pptx>=0.6.0
 Requires-Dist: nbformat>=5.0.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-mock>=3.0.0; extra == "dev"
 Dynamic: license-file
 
+<img src="assets/logo.png" width="150"/>
+
 # Bridgekit
 
 **AI tools that make you a better data scientist, not a redundant one.**
@@ -148,6 +153,8 @@ Uses a vector database and semantic similarity to find relevant context across y
 
 Supports `.txt`, `.md`, `.pdf`, `.docx`, `.pptx`, and `.ipynb` files.
 
+> **Note:** The first run will download the MiniLM embedding model (~90MB). This is a one-time download — it gets cached locally for all subsequent calls.
+
 **From a folder:**
 ```python
 from bridgekit import ask

{bridgekit-0.2.0 → bridgekit-0.2.1}/README.md

@@ -1,3 +1,5 @@
+<img src="assets/logo.png" width="150"/>
+
 # Bridgekit
 
 **AI tools that make you a better data scientist, not a redundant one.**
@@ -123,6 +125,8 @@ Uses a vector database and semantic similarity to find relevant context across y
 
 Supports `.txt`, `.md`, `.pdf`, `.docx`, `.pptx`, and `.ipynb` files.
 
+> **Note:** The first run will download the MiniLM embedding model (~90MB). This is a one-time download — it gets cached locally for all subsequent calls.
+
 **From a folder:**
 ```python
 from bridgekit import ask

{bridgekit-0.2.0 → bridgekit-0.2.1}/bridgekit/__init__.py

@@ -1,5 +1,5 @@
 from .reviewer import evaluate
 from .search import ask
 
-__version__ = "0.2.0"
+__version__ = "0.2.1"
 __all__ = ["evaluate", "ask"]

{bridgekit-0.2.0 → bridgekit-0.2.1}/bridgekit/reviewer.py

@@ -56,6 +56,9 @@ def evaluate(text: str) -> str:
     Returns:
         Structured feedback across five dimensions.
     """
+    if not text or not text.strip():
+        raise ValueError("Text cannot be empty.")
+
     api_key = os.environ.get("ANTHROPIC_API_KEY")
     if not api_key:
         raise EnvironmentError(

{bridgekit-0.2.0 → bridgekit-0.2.1}/bridgekit.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: bridgekit
-Version: 0.2.0
+Version: 0.2.1
 Summary: AI tools that make you a better data scientist, not a redundant one.
 License: MIT
 Project-URL: Homepage, https://github.com/getbridgekit/bridgekit
@@ -21,8 +21,13 @@ Requires-Dist: pypdf>=3.0.0
 Requires-Dist: python-docx>=1.0.0
 Requires-Dist: python-pptx>=0.6.0
 Requires-Dist: nbformat>=5.0.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-mock>=3.0.0; extra == "dev"
 Dynamic: license-file
 
+<img src="assets/logo.png" width="150"/>
+
 # Bridgekit
 
 **AI tools that make you a better data scientist, not a redundant one.**
@@ -148,6 +153,8 @@ Uses a vector database and semantic similarity to find relevant context across y
 
 Supports `.txt`, `.md`, `.pdf`, `.docx`, `.pptx`, and `.ipynb` files.
 
+> **Note:** The first run will download the MiniLM embedding model (~90MB). This is a one-time download — it gets cached locally for all subsequent calls.
+
 **From a folder:**
 ```python
 from bridgekit import ask

{bridgekit-0.2.0 → bridgekit-0.2.1}/bridgekit.egg-info/SOURCES.txt

@@ -8,4 +8,6 @@ bridgekit.egg-info/PKG-INFO
 bridgekit.egg-info/SOURCES.txt
 bridgekit.egg-info/dependency_links.txt
 bridgekit.egg-info/requires.txt
-bridgekit.egg-info/top_level.txt
+bridgekit.egg-info/top_level.txt
+tests/test_reviewer.py
+tests/test_search.py

{bridgekit-0.2.0 → bridgekit-0.2.1}/bridgekit.egg-info/requires.txt

@@ -5,3 +5,7 @@ pypdf>=3.0.0
 python-docx>=1.0.0
 python-pptx>=0.6.0
 nbformat>=5.0.0
+
+[dev]
+pytest>=7.0.0
+pytest-mock>=3.0.0

{bridgekit-0.2.0 → bridgekit-0.2.1}/pyproject.toml

@@ -7,7 +7,7 @@ include = ["bridgekit*"]
 
 [project]
 name = "bridgekit"
-version = "0.2.0"
+version = "0.2.1"
 description = "AI tools that make you a better data scientist, not a redundant one."
 readme = "README.md"
 requires-python = ">=3.9"
@@ -30,6 +30,12 @@ dependencies = [
     "nbformat>=5.0.0",
 ]
 
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.0.0",
+    "pytest-mock>=3.0.0",
+]
+
 [project.urls]
 Homepage = "https://github.com/getbridgekit/bridgekit"
 Issues = "https://github.com/getbridgekit/bridgekit/issues"

bridgekit-0.2.1/tests/test_reviewer.py

@@ -0,0 +1,162 @@
+import os
+import pytest
+from unittest.mock import MagicMock, patch
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+def _make_mock_message(text: str):
+    """Build a minimal fake Anthropic message response."""
+    content_block = MagicMock()
+    content_block.text = text
+    message = MagicMock()
+    message.content = [content_block]
+    return message
+
+
+FAKE_RESPONSE = (
+    "BRIDGEKIT ANALYSIS REVIEW\n"
+    "─────────────────────────────────────────\n\n"
+    "1. CLARITY\n"
+    "✅ STRONG — The writeup is clear and jargon-free.\n\n"
+    "2. AUDIENCE CLARITY\n"
+    "✅ STRONG — Written for the right audience.\n\n"
+    "3. STATISTICAL RIGOR\n"
+    "⚠️  NEEDS WORK — Sample size is not mentioned.\n\n"
+    "4. METHODOLOGY\n"
+    "✅ STRONG — Approach is well explained.\n\n"
+    "5. BUSINESS IMPACT\n"
+    "❌ MISSING — No quantified outcomes.\n\n"
+    "─────────────────────────────────────────\n"
+    "BOTTOM LINE\n"
+    "Add specific metrics to quantify business impact."
+)
+
+
+# ---------------------------------------------------------------------------
+# Tests
+# ---------------------------------------------------------------------------
+
+class TestEvaluateReturnsString:
+    """evaluate() should return a plain string."""
+
+    def test_returns_string(self):
+        with patch.dict(os.environ, {"ANTHROPIC_API_KEY": "test-key"}):
+            with patch("anthropic.Anthropic") as MockAnthropic:
+                mock_client = MagicMock()
+                mock_client.messages.create.return_value = _make_mock_message(FAKE_RESPONSE)
+                MockAnthropic.return_value = mock_client
+
+                from bridgekit.reviewer import evaluate
+                result = evaluate("We ran an A/B test on 500 users.")
+
+        assert isinstance(result, str)
+
+    def test_returns_non_empty_string(self):
+        with patch.dict(os.environ, {"ANTHROPIC_API_KEY": "test-key"}):
+            with patch("anthropic.Anthropic") as MockAnthropic:
+                mock_client = MagicMock()
+                mock_client.messages.create.return_value = _make_mock_message(FAKE_RESPONSE)
+                MockAnthropic.return_value = mock_client
+
+                from bridgekit.reviewer import evaluate
+                result = evaluate("We ran an A/B test on 500 users.")
+
+        assert len(result) > 0
+
+
+class TestEvaluateOutputStructure:
+    """evaluate() output should contain the required section headers."""
+
+    def test_output_contains_clarity(self):
+        with patch.dict(os.environ, {"ANTHROPIC_API_KEY": "test-key"}):
+            with patch("anthropic.Anthropic") as MockAnthropic:
+                mock_client = MagicMock()
+                mock_client.messages.create.return_value = _make_mock_message(FAKE_RESPONSE)
+                MockAnthropic.return_value = mock_client
+
+                from bridgekit.reviewer import evaluate
+                result = evaluate("Some analysis text.")
+
+        assert "CLARITY" in result
+
+    def test_output_contains_bottom_line(self):
+        with patch.dict(os.environ, {"ANTHROPIC_API_KEY": "test-key"}):
+            with patch("anthropic.Anthropic") as MockAnthropic:
+                mock_client = MagicMock()
+                mock_client.messages.create.return_value = _make_mock_message(FAKE_RESPONSE)
+                MockAnthropic.return_value = mock_client
+
+                from bridgekit.reviewer import evaluate
+                result = evaluate("Some analysis text.")
+
+        assert "BOTTOM LINE" in result
+
+    def test_output_contains_both_required_sections(self):
+        with patch.dict(os.environ, {"ANTHROPIC_API_KEY": "test-key"}):
+            with patch("anthropic.Anthropic") as MockAnthropic:
+                mock_client = MagicMock()
+                mock_client.messages.create.return_value = _make_mock_message(FAKE_RESPONSE)
+                MockAnthropic.return_value = mock_client
+
+                from bridgekit.reviewer import evaluate
+                result = evaluate("Some analysis text.")
+
+        assert "CLARITY" in result and "BOTTOM LINE" in result
+
+
+class TestEvaluateMissingApiKey:
+    """evaluate() should raise EnvironmentError when the API key is absent."""
+
+    def test_raises_environment_error_when_key_missing(self):
+        env = {k: v for k, v in os.environ.items() if k != "ANTHROPIC_API_KEY"}
+        with patch.dict(os.environ, env, clear=True):
+            from bridgekit.reviewer import evaluate
+            with pytest.raises(EnvironmentError):
+                evaluate("Some analysis text.")
+
+    def test_error_message_mentions_key(self):
+        env = {k: v for k, v in os.environ.items() if k != "ANTHROPIC_API_KEY"}
+        with patch.dict(os.environ, env, clear=True):
+            from bridgekit.reviewer import evaluate
+            with pytest.raises(EnvironmentError, match="ANTHROPIC_API_KEY"):
+                evaluate("Some analysis text.")
+
+
+class TestEvaluateEmptyInput:
+    """evaluate() should raise ValueError for empty or whitespace-only input."""
+
+    def test_empty_string_raises_value_error(self):
+        with patch.dict(os.environ, {"ANTHROPIC_API_KEY": "test-key"}):
+            from bridgekit.reviewer import evaluate
+            with pytest.raises(ValueError, match="empty"):
+                evaluate("")
+
+    def test_whitespace_only_raises_value_error(self):
+        with patch.dict(os.environ, {"ANTHROPIC_API_KEY": "test-key"}):
+            from bridgekit.reviewer import evaluate
+            with pytest.raises(ValueError, match="empty"):
+                evaluate("   ")
+
+
+class TestEvaluateApiCallShape:
+    """evaluate() should pass the user text through to the Anthropic API."""
+
+    def test_api_called_with_user_text(self):
+        user_text = "Our conversion rate improved after the campaign."
+        with patch.dict(os.environ, {"ANTHROPIC_API_KEY": "test-key"}):
+            with patch("anthropic.Anthropic") as MockAnthropic:
+                mock_client = MagicMock()
+                mock_client.messages.create.return_value = _make_mock_message(FAKE_RESPONSE)
+                MockAnthropic.return_value = mock_client
+
+                from bridgekit.reviewer import evaluate
+                evaluate(user_text)
+
+                call_kwargs = mock_client.messages.create.call_args
+                # The user text should appear somewhere in the messages payload
+                messages_arg = call_kwargs.kwargs.get("messages") or call_kwargs.args[0]
+                content = str(messages_arg)
+                assert user_text in content

bridgekit-0.2.1/tests/test_search.py

@@ -0,0 +1,238 @@
+import os
+import pytest
+from pathlib import Path
+from unittest.mock import MagicMock, patch
+import tempfile
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+def _make_mock_message(text: str):
+    """Build a minimal fake Anthropic message response."""
+    content_block = MagicMock()
+    content_block.text = text
+    message = MagicMock()
+    message.content = [content_block]
+    return message
+
+
+FAKE_ANSWER = "Based on the documents, the conversion rate increased by 12%."
+
+
+def _make_mock_chromadb(chunks: list[str] | None = None):
+    """
+    Return a (mock_chromadb_module, mock_embedding_fn_class) pair whose
+    collection.query() returns the supplied chunks as context.
+    """
+    returned_docs = chunks if chunks is not None else ["sample context chunk"]
+
+    mock_collection = MagicMock()
+    mock_collection.query.return_value = {"documents": [returned_docs]}
+
+    mock_chroma_client = MagicMock()
+    mock_chroma_client.get_or_create_collection.return_value = mock_collection
+
+    mock_chromadb = MagicMock()
+    mock_chromadb.Client.return_value = mock_chroma_client
+
+    mock_embedding_fn_class = MagicMock()
+    mock_embedding_fn_class.return_value = MagicMock()
+
+    return mock_chromadb, mock_embedding_fn_class
+
+
+# ---------------------------------------------------------------------------
+# Tests
+# ---------------------------------------------------------------------------
+
+class TestAskReturnsString:
+    """ask() should return a non-empty string."""
+
+    def test_returns_string_with_text_input(self):
+        mock_chromadb, mock_ef = _make_mock_chromadb()
+        with patch.dict(os.environ, {"ANTHROPIC_API_KEY": "test-key"}):
+            with patch("anthropic.Anthropic") as MockAnthropic, \
+                 patch("chromadb.Client", mock_chromadb.Client), \
+                 patch(
+                     "chromadb.utils.embedding_functions.SentenceTransformerEmbeddingFunction",
+                     mock_ef,
+                 ):
+                mock_client = MagicMock()
+                mock_client.messages.create.return_value = _make_mock_message(FAKE_ANSWER)
+                MockAnthropic.return_value = mock_client
+
+                from bridgekit.search import ask
+                result = ask("What was the conversion rate?", text="The conversion rate increased by 12%.")
+
+        assert isinstance(result, str)
+        assert len(result) > 0
+
+    def test_returns_non_empty_answer(self):
+        mock_chromadb, mock_ef = _make_mock_chromadb()
+        with patch.dict(os.environ, {"ANTHROPIC_API_KEY": "test-key"}):
+            with patch("anthropic.Anthropic") as MockAnthropic, \
+                 patch("chromadb.Client", mock_chromadb.Client), \
+                 patch(
+                     "chromadb.utils.embedding_functions.SentenceTransformerEmbeddingFunction",
+                     mock_ef,
+                 ):
+                mock_client = MagicMock()
+                mock_client.messages.create.return_value = _make_mock_message(FAKE_ANSWER)
+                MockAnthropic.return_value = mock_client
+
+                from bridgekit.search import ask
+                result = ask("What was the conversion rate?", text="The conversion rate increased by 12%.")
+
+        assert result == FAKE_ANSWER
+
+
+class TestAskMissingSourceAndText:
+    """ask() should raise ValueError when neither source nor text is supplied."""
+
+    def test_raises_value_error_with_no_inputs(self):
+        with patch.dict(os.environ, {"ANTHROPIC_API_KEY": "test-key"}):
+            from bridgekit.search import ask
+            with pytest.raises(ValueError, match="source"):
+                ask("What happened?")
+
+    def test_raises_value_error_message_mentions_text(self):
+        with patch.dict(os.environ, {"ANTHROPIC_API_KEY": "test-key"}):
+            from bridgekit.search import ask
+            with pytest.raises(ValueError):
+                ask("What happened?", source=None, text=None)
+
+
+class TestAskMissingApiKey:
+    """ask() should raise EnvironmentError when ANTHROPIC_API_KEY is absent."""
+
+    def test_raises_environment_error_when_key_missing(self):
+        env = {k: v for k, v in os.environ.items() if k != "ANTHROPIC_API_KEY"}
+        with patch.dict(os.environ, env, clear=True):
+            from bridgekit.search import ask
+            with pytest.raises(EnvironmentError):
+                ask("What happened?", text="Some text about results.")
+
+    def test_error_message_mentions_key(self):
+        env = {k: v for k, v in os.environ.items() if k != "ANTHROPIC_API_KEY"}
+        with patch.dict(os.environ, env, clear=True):
+            from bridgekit.search import ask
+            with pytest.raises(EnvironmentError, match="ANTHROPIC_API_KEY"):
+                ask("What happened?", text="Some text about results.")
+
+
+class TestAskWithTextInput:
+    """ask() should work correctly when called with the text= parameter."""
+
+    def test_text_input_reaches_api(self):
+        raw_text = "Revenue grew 25% year-over-year driven by enterprise sales."
+        mock_chromadb, mock_ef = _make_mock_chromadb([raw_text])
+
+        with patch.dict(os.environ, {"ANTHROPIC_API_KEY": "test-key"}):
+            with patch("anthropic.Anthropic") as MockAnthropic, \
+                 patch("chromadb.Client", mock_chromadb.Client), \
+                 patch(
+                     "chromadb.utils.embedding_functions.SentenceTransformerEmbeddingFunction",
+                     mock_ef,
+                 ):
+                mock_client = MagicMock()
+                mock_client.messages.create.return_value = _make_mock_message(FAKE_ANSWER)
+                MockAnthropic.return_value = mock_client
+
+                from bridgekit.search import ask
+                ask("What drove revenue growth?", text=raw_text)
+
+                # Verify the Anthropic API was actually called once
+                assert mock_client.messages.create.call_count == 1
+
+    def test_text_input_included_in_context(self):
+        raw_text = "Churn dropped from 8% to 3% after onboarding improvements."
+        mock_chromadb, mock_ef = _make_mock_chromadb([raw_text])
+
+        with patch.dict(os.environ, {"ANTHROPIC_API_KEY": "test-key"}):
+            with patch("anthropic.Anthropic") as MockAnthropic, \
+                 patch("chromadb.Client", mock_chromadb.Client), \
+                 patch(
+                     "chromadb.utils.embedding_functions.SentenceTransformerEmbeddingFunction",
+                     mock_ef,
+                 ):
+                mock_client = MagicMock()
+                mock_client.messages.create.return_value = _make_mock_message(FAKE_ANSWER)
+                MockAnthropic.return_value = mock_client
+
+                from bridgekit.search import ask
+                ask("What happened to churn?", text=raw_text)
+
+                call_kwargs = mock_client.messages.create.call_args
+                messages_arg = call_kwargs.kwargs.get("messages") or call_kwargs.args[0]
+                # The retrieved chunk (raw_text) should appear in the prompt context
+                assert raw_text in str(messages_arg)
+
+
+class TestAskWithSourceFolder:
+    """ask() should load .txt files from a folder and pass their content to the API."""
+
+    def test_source_folder_with_txt_file(self):
+        with tempfile.TemporaryDirectory() as tmpdir:
+            sample_file = Path(tmpdir) / "report.txt"
+            sample_content = "The experiment showed a 15% lift in click-through rate."
+            sample_file.write_text(sample_content, encoding="utf-8")
+
+            mock_chromadb, mock_ef = _make_mock_chromadb([sample_content])
+
+            with patch.dict(os.environ, {"ANTHROPIC_API_KEY": "test-key"}):
+                with patch("anthropic.Anthropic") as MockAnthropic, \
+                     patch("chromadb.Client", mock_chromadb.Client), \
+                     patch(
+                         "chromadb.utils.embedding_functions.SentenceTransformerEmbeddingFunction",
+                         mock_ef,
+                     ):
+                    mock_client = MagicMock()
+                    mock_client.messages.create.return_value = _make_mock_message(FAKE_ANSWER)
+                    MockAnthropic.return_value = mock_client
+
+                    from bridgekit.search import ask
+                    result = ask("What was the lift?", source=tmpdir)
+
+            assert isinstance(result, str)
+            assert len(result) > 0
+
+    def test_source_folder_calls_api_once(self):
+        with tempfile.TemporaryDirectory() as tmpdir:
+            (Path(tmpdir) / "notes.txt").write_text(
+                "User satisfaction scores improved by 20 points.", encoding="utf-8"
+            )
+
+            mock_chromadb, mock_ef = _make_mock_chromadb()
+
+            with patch.dict(os.environ, {"ANTHROPIC_API_KEY": "test-key"}):
+                with patch("anthropic.Anthropic") as MockAnthropic, \
+                     patch("chromadb.Client", mock_chromadb.Client), \
+                     patch(
+                         "chromadb.utils.embedding_functions.SentenceTransformerEmbeddingFunction",
+                         mock_ef,
+                     ):
+                    mock_client = MagicMock()
+                    mock_client.messages.create.return_value = _make_mock_message(FAKE_ANSWER)
+                    MockAnthropic.return_value = mock_client
+
+                    from bridgekit.search import ask
+                    ask("How did satisfaction change?", source=tmpdir)
+
+                    assert mock_client.messages.create.call_count == 1
+
+    def test_source_folder_empty_raises_value_error(self):
+        with tempfile.TemporaryDirectory() as tmpdir:
+            # Folder exists but has no supported files
+            mock_chromadb, mock_ef = _make_mock_chromadb()
+
+            with patch.dict(os.environ, {"ANTHROPIC_API_KEY": "test-key"}):
+                with patch("chromadb.Client", mock_chromadb.Client), \
+                     patch(
+                         "chromadb.utils.embedding_functions.SentenceTransformerEmbeddingFunction",
+                         mock_ef,
+                     ):
+                    from bridgekit.search import ask
+                    with pytest.raises(ValueError, match="No content found"):
+                        ask("What happened?", source=tmpdir)