bridgekit 0.1.1__tar.gz → 0.2.1__tar.gz

{bridgekit-0.1.1/bridgekit.egg-info → bridgekit-0.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: bridgekit
-Version: 0.1.1
+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
@@ -15,8 +15,19 @@ Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: anthropic>=0.20.0
+Requires-Dist: chromadb>=0.4.0
+Requires-Dist: sentence-transformers>=2.0.0
+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.**
@@ -134,6 +145,49 @@ Paste your writeup as a string and call `evaluate()` — that's it.
 
 ---
 
+## Tool #2: Analysis Search
+
+Ask questions across a collection of your past analysis documents. Point it at a folder and get answers grounded in your actual work — no digging through files manually.
+
+Uses a vector database and semantic similarity to find relevant context across your documents — not keyword matching.
+
+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
+
+print(ask("what drove churn in Q3?", source="reports/"))
+```
+
+**From raw text:**
+```python
+from bridgekit import ask
+
+text = """
+Q3 churn rose to 4.5%, driven by a product outage in August and a pricing
+change in July that increased SMB costs by 12%.
+"""
+
+print(ask("what caused the Q3 churn spike?", text=text))
+```
+
+**Output** *(based on sample data included in the repo)*:
+```
+Based on the Q3 2024 Churn Analysis, two primary factors drove the elevated
+churn rate of 4.5%:
+
+1. August Product Outage — A 14-hour outage affected 3,800 accounts. Impacted
+   accounts churned at 8.1% vs 3.2% for unaffected accounts.
+
+2. July Pricing Change — SMB costs increased by an average of 12%, causing SMB
+   churn to spike to 7.2% — the highest single-month figure in the dataset.
+```
+
+---
+
 ## Why not just use Claude?
 
 You could. But you'd need to know what to ask, how to frame it, and what a good answer looks like. Bridgekit has that baked in — it knows you're a data scientist presenting findings, so it asks the right questions automatically. No prompt engineering required. Just paste your work and run it.
@@ -156,7 +210,7 @@ Bridgekit only ever sees text you write yourself — your narrative, your conclu
 
 ## What's next?
 
-Bridgekit is a suite, not a one-off. The analysis reviewer is tool #1. Coming next:
+Bridgekit is a suite, not a one-off. Two tools are live — more are coming:
 
 - **Statistical approach suggester** — describe your problem in plain English, get the right test and why
 - **Stakeholder translator** — turn your technical findings into a narrative a non-technical audience will actually follow

bridgekit-0.1.1/PKG-INFO → bridgekit-0.2.1/README.md

@@ -1,21 +1,4 @@
-Metadata-Version: 2.4
-Name: bridgekit
-Version: 0.1.1
-Summary: AI tools that make you a better data scientist, not a redundant one.
-License: MIT
-Project-URL: Homepage, https://github.com/getbridgekit/bridgekit
-Project-URL: Issues, https://github.com/getbridgekit/bridgekit/issues
-Keywords: data science,AI,analysis,evaluation,anthropic
-Classifier: Development Status :: 3 - Alpha
-Classifier: Intended Audience :: Science/Research
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: MIT License
-Requires-Python: >=3.9
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: anthropic>=0.20.0
-Dynamic: license-file
+<img src="assets/logo.png" width="150"/>
 
 # Bridgekit
 
@@ -134,6 +117,49 @@ Paste your writeup as a string and call `evaluate()` — that's it.
 
 ---
 
+## Tool #2: Analysis Search
+
+Ask questions across a collection of your past analysis documents. Point it at a folder and get answers grounded in your actual work — no digging through files manually.
+
+Uses a vector database and semantic similarity to find relevant context across your documents — not keyword matching.
+
+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
+
+print(ask("what drove churn in Q3?", source="reports/"))
+```
+
+**From raw text:**
+```python
+from bridgekit import ask
+
+text = """
+Q3 churn rose to 4.5%, driven by a product outage in August and a pricing
+change in July that increased SMB costs by 12%.
+"""
+
+print(ask("what caused the Q3 churn spike?", text=text))
+```
+
+**Output** *(based on sample data included in the repo)*:
+```
+Based on the Q3 2024 Churn Analysis, two primary factors drove the elevated
+churn rate of 4.5%:
+
+1. August Product Outage — A 14-hour outage affected 3,800 accounts. Impacted
+   accounts churned at 8.1% vs 3.2% for unaffected accounts.
+
+2. July Pricing Change — SMB costs increased by an average of 12%, causing SMB
+   churn to spike to 7.2% — the highest single-month figure in the dataset.
+```
+
+---
+
 ## Why not just use Claude?
 
 You could. But you'd need to know what to ask, how to frame it, and what a good answer looks like. Bridgekit has that baked in — it knows you're a data scientist presenting findings, so it asks the right questions automatically. No prompt engineering required. Just paste your work and run it.
@@ -156,7 +182,7 @@ Bridgekit only ever sees text you write yourself — your narrative, your conclu
 
 ## What's next?
 
-Bridgekit is a suite, not a one-off. The analysis reviewer is tool #1. Coming next:
+Bridgekit is a suite, not a one-off. Two tools are live — more are coming:
 
 - **Statistical approach suggester** — describe your problem in plain English, get the right test and why
 - **Stakeholder translator** — turn your technical findings into a narrative a non-technical audience will actually follow

bridgekit-0.2.1/bridgekit/__init__.py

@@ -0,0 +1,5 @@
+from .reviewer import evaluate
+from .search import ask
+
+__version__ = "0.2.1"
+__all__ = ["evaluate", "ask"]

{bridgekit-0.1.1 → 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-0.2.1/bridgekit/search.py

@@ -0,0 +1,122 @@
+import os
+from pathlib import Path
+import anthropic
+import chromadb
+from chromadb.utils.embedding_functions import SentenceTransformerEmbeddingFunction
+
+CHUNK_SIZE = 150  # words per chunk
+CHUNK_OVERLAP = 20
+
+
+def _load_file(path: Path) -> str:
+    suffix = path.suffix.lower()
+    if suffix == ".pdf":
+        import pypdf
+        reader = pypdf.PdfReader(str(path))
+        return "\n".join(page.extract_text() or "" for page in reader.pages)
+    elif suffix == ".docx":
+        import docx
+        doc = docx.Document(str(path))
+        return "\n".join(p.text for p in doc.paragraphs if p.text.strip())
+    elif suffix == ".pptx":
+        from pptx import Presentation
+        prs = Presentation(str(path))
+        lines = []
+        for slide in prs.slides:
+            for shape in slide.shapes:
+                if hasattr(shape, "text") and shape.text.strip():
+                    lines.append(shape.text)
+        return "\n".join(lines)
+    elif suffix == ".ipynb":
+        import nbformat
+        nb = nbformat.read(str(path), as_version=4)
+        lines = []
+        for cell in nb.cells:
+            if cell.cell_type in ("markdown", "code") and cell.source.strip():
+                lines.append(cell.source)
+        return "\n\n".join(lines)
+    else:
+        return path.read_text(encoding="utf-8")
+
+
+def _chunk(text: str) -> list[str]:
+    words = text.split()
+    chunks = []
+    i = 0
+    while i < len(words):
+        chunks.append(" ".join(words[i:i + CHUNK_SIZE]))
+        i += CHUNK_SIZE - CHUNK_OVERLAP
+    return [c for c in chunks if c.strip()]
+
+
+def ask(question: str, source: str = None, text: str = None) -> str:
+    """
+    Ask a question across a collection of analysis documents or raw text.
+
+    Args:
+        question: The question to answer.
+        source:   Path to a folder containing .txt, .md, .pdf, .docx, .pptx, or .ipynb files.
+        text:     A raw text string to search instead of a folder.
+
+    Returns:
+        An answer grounded in the provided documents.
+    """
+    if not source and not text:
+        raise ValueError("Provide either 'source' (folder path) or 'text'.")
+
+    api_key = os.environ.get("ANTHROPIC_API_KEY")
+    if not api_key:
+        raise EnvironmentError(
+            "ANTHROPIC_API_KEY not found. Set it with: export ANTHROPIC_API_KEY=your_key_here"
+        )
+
+    # Collect chunks
+    chunks = []
+
+    if text:
+        chunks.extend(_chunk(text))
+
+    if source:
+        folder = Path(source).expanduser().resolve()
+        supported = {".txt", ".md", ".pdf", ".docx", ".pptx", ".ipynb"}
+        for file in sorted(folder.iterdir()):
+            if file.suffix.lower() in supported:
+                content = _load_file(file)
+                chunks.extend(_chunk(content))
+
+    if not chunks:
+        raise ValueError("No content found. Check your source folder or text input.")
+
+    # Embed and store in ChromaDB
+    embedding_fn = SentenceTransformerEmbeddingFunction(model_name="all-MiniLM-L6-v2")
+    client = chromadb.Client()
+    collection = client.get_or_create_collection(
+        name="bridgekit_ask",
+        embedding_function=embedding_fn
+    )
+    collection.add(
+        documents=chunks,
+        ids=[f"chunk_{i}" for i in range(len(chunks))]
+    )
+
+    # Retrieve most relevant chunks
+    results = collection.query(query_texts=[question], n_results=min(8, len(chunks)))
+    context = "\n\n".join(results["documents"][0])
+
+    # Generate answer with Claude
+    anthropic_client = anthropic.Anthropic(api_key=api_key)
+    message = anthropic_client.messages.create(
+        model="claude-opus-4-5",
+        max_tokens=1024,
+        system=(
+            "You are a senior data scientist answering questions based on analysis reports. "
+            "Answer only from the provided context. Be specific and cite findings where relevant. "
+            "If the context does not contain enough information to answer, say so clearly."
+        ),
+        messages=[{
+            "role": "user",
+            "content": f"Context from analysis reports:\n\n{context}\n\nQuestion: {question}"
+        }]
+    )
+
+    return message.content[0].text

bridgekit-0.1.1/README.md → bridgekit-0.2.1/bridgekit.egg-info/PKG-INFO

@@ -1,3 +1,33 @@
+Metadata-Version: 2.4
+Name: bridgekit
+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
+Project-URL: Issues, https://github.com/getbridgekit/bridgekit/issues
+Keywords: data science,AI,analysis,evaluation,anthropic
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: anthropic>=0.20.0
+Requires-Dist: chromadb>=0.4.0
+Requires-Dist: sentence-transformers>=2.0.0
+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.**
@@ -115,6 +145,49 @@ Paste your writeup as a string and call `evaluate()` — that's it.
 
 ---
 
+## Tool #2: Analysis Search
+
+Ask questions across a collection of your past analysis documents. Point it at a folder and get answers grounded in your actual work — no digging through files manually.
+
+Uses a vector database and semantic similarity to find relevant context across your documents — not keyword matching.
+
+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
+
+print(ask("what drove churn in Q3?", source="reports/"))
+```
+
+**From raw text:**
+```python
+from bridgekit import ask
+
+text = """
+Q3 churn rose to 4.5%, driven by a product outage in August and a pricing
+change in July that increased SMB costs by 12%.
+"""
+
+print(ask("what caused the Q3 churn spike?", text=text))
+```
+
+**Output** *(based on sample data included in the repo)*:
+```
+Based on the Q3 2024 Churn Analysis, two primary factors drove the elevated
+churn rate of 4.5%:
+
+1. August Product Outage — A 14-hour outage affected 3,800 accounts. Impacted
+   accounts churned at 8.1% vs 3.2% for unaffected accounts.
+
+2. July Pricing Change — SMB costs increased by an average of 12%, causing SMB
+   churn to spike to 7.2% — the highest single-month figure in the dataset.
+```
+
+---
+
 ## Why not just use Claude?
 
 You could. But you'd need to know what to ask, how to frame it, and what a good answer looks like. Bridgekit has that baked in — it knows you're a data scientist presenting findings, so it asks the right questions automatically. No prompt engineering required. Just paste your work and run it.
@@ -137,7 +210,7 @@ Bridgekit only ever sees text you write yourself — your narrative, your conclu
 
 ## What's next?
 
-Bridgekit is a suite, not a one-off. The analysis reviewer is tool #1. Coming next:
+Bridgekit is a suite, not a one-off. Two tools are live — more are coming:
 
 - **Statistical approach suggester** — describe your problem in plain English, get the right test and why
 - **Stakeholder translator** — turn your technical findings into a narrative a non-technical audience will actually follow

{bridgekit-0.1.1 → bridgekit-0.2.1}/bridgekit.egg-info/SOURCES.txt

@@ -3,8 +3,11 @@ README.md
 pyproject.toml
 bridgekit/__init__.py
 bridgekit/reviewer.py
+bridgekit/search.py
 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-0.2.1/bridgekit.egg-info/requires.txt

@@ -0,0 +1,11 @@
+anthropic>=0.20.0
+chromadb>=0.4.0
+sentence-transformers>=2.0.0
+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-0.1.1 → bridgekit-0.2.1}/pyproject.toml

@@ -2,9 +2,12 @@
 requires = ["setuptools>=61.0"]
 build-backend = "setuptools.build_meta"
 
+[tool.setuptools.packages.find]
+include = ["bridgekit*"]
+
 [project]
 name = "bridgekit"
-version = "0.1.1"
+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"
@@ -19,6 +22,18 @@ classifiers = [
 ]
 dependencies = [
     "anthropic>=0.20.0",
+    "chromadb>=0.4.0",
+    "sentence-transformers>=2.0.0",
+    "pypdf>=3.0.0",
+    "python-docx>=1.0.0",
+    "python-pptx>=0.6.0",
+    "nbformat>=5.0.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.0.0",
+    "pytest-mock>=3.0.0",
 ]
 
 [project.urls]

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)

bridgekit-0.1.1/bridgekit/__init__.py

@@ -1,4 +0,0 @@
-from .reviewer import evaluate
-
-__version__ = "0.1.1"
-__all__ = ["evaluate"]

bridgekit-0.1.1/bridgekit.egg-info/requires.txt

@@ -1 +0,0 @@
-anthropic>=0.20.0