bridgekit 0.3.5__tar.gz → 0.3.6__tar.gz

{bridgekit-0.3.5/bridgekit.egg-info → bridgekit-0.3.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: bridgekit
-Version: 0.3.5
+Version: 0.3.6
 Summary: AI tools that make you a better data scientist, not a redundant one.
 License: MIT
 Project-URL: Homepage, https://usebridgekit.com
@@ -21,6 +21,10 @@ 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: openai
+Requires-Dist: openai>=1.0.0; extra == "openai"
+Provides-Extra: gemini
+Requires-Dist: google-generativeai>=0.3.0; extra == "gemini"
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0.0; extra == "dev"
 Requires-Dist: pytest-mock>=3.0.0; extra == "dev"
@@ -63,12 +67,26 @@ pip install bridgekit
 !pip install bridgekit
 ```
 
-Requires an Anthropic API key:
+Requires an API key for your chosen provider:
 
+**Anthropic (default):**
 ```bash
+pip install bridgekit
 export ANTHROPIC_API_KEY=your_key_here
 ```
 
+**OpenAI:**
+```bash
+pip install bridgekit[openai]
+export OPENAI_API_KEY=your_key_here
+```
+
+**Google Gemini:**
+```bash
+pip install bridgekit[gemini]
+export GOOGLE_API_KEY=your_key_here
+```
+
 ---
 
 ## Getting Started
@@ -369,6 +387,45 @@ willing to commit to — and what's your confidence interval on that estimate?"
 
 ---
 
+## Multi-Provider Support
+
+Bridgekit now supports multiple AI providers so you're not locked into one API. You can use Anthropic, OpenAI, or Google Gemini models with any tool.
+
+**Using different providers:**
+
+```python
+from bridgekit import evaluate, plan, ask, redteam
+
+# Use OpenAI (default model: gpt-4o)
+print(evaluate("Your analysis here", provider="openai"))
+
+# Use Google Gemini (default model: gemini-1.5-pro)
+print(plan("Your question here", provider="gemini"))
+
+# Use specific model
+print(redteam("Your analysis here", model="gpt-4-turbo"))
+print(ask("Your question here", source="reports/", model="claude-3-opus-20240229"))
+```
+
+**Provider auto-detection:**
+Bridgekit automatically detects the provider from model names:
+- Models starting with "claude" → Anthropic
+- Models starting with "gpt" → OpenAI  
+- Models starting with "gemini" → Google Gemini
+
+**Default models by provider:**
+- Anthropic: `claude-3-5-sonnet-20241022`
+- OpenAI: `gpt-4o`
+- Gemini: `gemini-1.5-pro`
+
+All tools support the same `provider` and `model` parameters:
+- `evaluate(text, provider=None, model=None)`
+- `plan(question, provider=None, model=None, ...)`
+- `ask(question, provider=None, model=None, ...)`
+- `redteam(text, provider=None, model=None, ...)`
+
+---
+
 ## 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.
@@ -389,7 +446,7 @@ Bridgekit is a suite, not a one-off. Four tools are live — more are coming:
 
 - **Stakeholder translator** — turn your technical findings into a narrative a non-technical audience will actually follow
 - **Assumption checker** — state your analytical assumptions, get the ones you missed
-- **Multi-model support** — use any LLM provider (OpenAI, Gemini, open source models via OpenRouter) instead of being tied to Anthropic
+- **More specialized tools** — focused on specific data science workflows and challenges
 
 Each tool is small, focused, and built for the way data scientists actually work.
 

bridgekit-0.3.5/PKG-INFO → bridgekit-0.3.6/README.md

@@ -1,31 +1,3 @@
-Metadata-Version: 2.4
-Name: bridgekit
-Version: 0.3.5
-Summary: AI tools that make you a better data scientist, not a redundant one.
-License: MIT
-Project-URL: Homepage, https://usebridgekit.com
-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
-
 <p align="center">
   <img src="https://raw.githubusercontent.com/getbridgekit/bridgekit/main/assets/logo.png" alt="Bridgekit" width="200"/>
 </p>
@@ -63,12 +35,26 @@ pip install bridgekit
 !pip install bridgekit
 ```
 
-Requires an Anthropic API key:
+Requires an API key for your chosen provider:
 
+**Anthropic (default):**
 ```bash
+pip install bridgekit
 export ANTHROPIC_API_KEY=your_key_here
 ```
 
+**OpenAI:**
+```bash
+pip install bridgekit[openai]
+export OPENAI_API_KEY=your_key_here
+```
+
+**Google Gemini:**
+```bash
+pip install bridgekit[gemini]
+export GOOGLE_API_KEY=your_key_here
+```
+
 ---
 
 ## Getting Started
@@ -369,6 +355,45 @@ willing to commit to — and what's your confidence interval on that estimate?"
 
 ---
 
+## Multi-Provider Support
+
+Bridgekit now supports multiple AI providers so you're not locked into one API. You can use Anthropic, OpenAI, or Google Gemini models with any tool.
+
+**Using different providers:**
+
+```python
+from bridgekit import evaluate, plan, ask, redteam
+
+# Use OpenAI (default model: gpt-4o)
+print(evaluate("Your analysis here", provider="openai"))
+
+# Use Google Gemini (default model: gemini-1.5-pro)
+print(plan("Your question here", provider="gemini"))
+
+# Use specific model
+print(redteam("Your analysis here", model="gpt-4-turbo"))
+print(ask("Your question here", source="reports/", model="claude-3-opus-20240229"))
+```
+
+**Provider auto-detection:**
+Bridgekit automatically detects the provider from model names:
+- Models starting with "claude" → Anthropic
+- Models starting with "gpt" → OpenAI  
+- Models starting with "gemini" → Google Gemini
+
+**Default models by provider:**
+- Anthropic: `claude-3-5-sonnet-20241022`
+- OpenAI: `gpt-4o`
+- Gemini: `gemini-1.5-pro`
+
+All tools support the same `provider` and `model` parameters:
+- `evaluate(text, provider=None, model=None)`
+- `plan(question, provider=None, model=None, ...)`
+- `ask(question, provider=None, model=None, ...)`
+- `redteam(text, provider=None, model=None, ...)`
+
+---
+
 ## 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.
@@ -389,7 +414,7 @@ Bridgekit is a suite, not a one-off. Four tools are live — more are coming:
 
 - **Stakeholder translator** — turn your technical findings into a narrative a non-technical audience will actually follow
 - **Assumption checker** — state your analytical assumptions, get the ones you missed
-- **Multi-model support** — use any LLM provider (OpenAI, Gemini, open source models via OpenRouter) instead of being tied to Anthropic
+- **More specialized tools** — focused on specific data science workflows and challenges
 
 Each tool is small, focused, and built for the way data scientists actually work.
 

bridgekit-0.3.6/bridgekit/config.py

@@ -0,0 +1,83 @@
+import os
+from enum import Enum
+from typing import Optional
+
+
+class Provider(Enum):
+    ANTHROPIC = "anthropic"
+    OPENAI = "openai"
+    GEMINI = "gemini"
+
+
+# Default models for each provider
+DEFAULT_MODELS = {
+    Provider.ANTHROPIC: "claude-opus-4-6",
+    Provider.OPENAI: "gpt-4o",
+    Provider.GEMINI: "gemini-1.5-pro"
+}
+
+# Legacy support
+DEFAULT_MODEL = DEFAULT_MODELS[Provider.ANTHROPIC]
+
+
+def require_api_key(provider: Provider = Provider.ANTHROPIC) -> str:
+    """Return the API key for the specified provider from the environment, or raise a clear error.
+
+    Each Bridgekit tool calls this before constructing a client so
+    users get the same friendly message instead of whatever the SDK surfaces
+    when the key is missing.
+    """
+    if provider == Provider.ANTHROPIC:
+        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"
+            )
+        return api_key
+    elif provider == Provider.OPENAI:
+        api_key = os.environ.get("OPENAI_API_KEY")
+        if not api_key:
+            raise EnvironmentError(
+                "OPENAI_API_KEY not found. Set it with: export OPENAI_API_KEY=your_key_here"
+            )
+        return api_key
+    elif provider == Provider.GEMINI:
+        api_key = os.environ.get("GOOGLE_API_KEY")
+        if not api_key:
+            raise EnvironmentError(
+                "GOOGLE_API_KEY not found. Set it with: export GOOGLE_API_KEY=your_key_here"
+            )
+        return api_key
+    else:
+        raise ValueError(f"Unsupported provider: {provider}")
+
+
+def require_anthropic_api_key() -> str:
+    """Legacy function for backward compatibility."""
+    return require_api_key(Provider.ANTHROPIC)
+
+
+def parse_provider(provider: Optional[str] = None, model: Optional[str] = None) -> Provider:
+    """Parse provider from provider string or model name."""
+    if provider:
+        try:
+            return Provider(provider.lower())
+        except ValueError:
+            raise ValueError(f"Unsupported provider: {provider}. Supported providers: {[p.value for p in Provider]}")
+    
+    if model:
+        # Infer provider from model name
+        if model.startswith("claude"):
+            return Provider.ANTHROPIC
+        elif model.startswith("gpt"):
+            return Provider.OPENAI
+        elif model.startswith("gemini"):
+            return Provider.GEMINI
+    
+    # Default to Anthropic for backward compatibility
+    return Provider.ANTHROPIC
+
+
+def get_default_model(provider: Provider) -> str:
+    """Get the default model for a provider."""
+    return DEFAULT_MODELS.get(provider, DEFAULT_MODELS[Provider.ANTHROPIC])

{bridgekit-0.3.5 → bridgekit-0.3.6}/bridgekit/planner.py

@@ -1,5 +1,5 @@
-import anthropic
-from .config import DEFAULT_MODEL, require_anthropic_api_key
+from .config import DEFAULT_MODEL, parse_provider, get_default_model
+from .providers import create_message
 
 SYSTEM_PROMPT = """You are a senior statistician and data scientist advising a colleague on the right analytical approach for their problem.
 
@@ -29,7 +29,7 @@ ALTERNATIVES
 """
 
 
-def plan(question: str, data_description: str = None, goal: str = None) -> str:
+def plan(question: str, data_description: str = None, goal: str = None, provider: str = None, model: str = None) -> str:
     """
     Recommend the right analytical approach for your problem.
 
@@ -38,6 +38,9 @@ def plan(question: str, data_description: str = None, goal: str = None) -> str:
         data_description: Optional. A plain text description of your available data.
         goal:             Optional. The goal of your analysis (e.g. "causal inference",
                           "prediction", "segmentation", "hypothesis testing", "exploration").
+        provider:         Optional. The AI provider to use ("anthropic", "openai", "gemini").
+                          If not specified, defaults to "anthropic" or infers from model.
+        model:            Optional. The specific model to use. If not specified, uses the provider's default.
 
     Returns:
         A structured analytical plan covering the recommended approach, assumptions,
@@ -46,7 +49,10 @@ def plan(question: str, data_description: str = None, goal: str = None) -> str:
     if not question or not question.strip():
         raise ValueError("Question cannot be empty.")
 
-    api_key = require_anthropic_api_key()
+    # Parse provider and determine model
+    provider_enum = parse_provider(provider, model)
+    if model is None:
+        model = get_default_model(provider_enum)
 
     user_message = f"Question: {question}"
     if data_description:
@@ -54,17 +60,10 @@ def plan(question: str, data_description: str = None, goal: str = None) -> str:
     if goal:
         user_message += f"\n\nGoal: {goal}"
 
-    client = anthropic.Anthropic(api_key=api_key)
-    message = client.messages.create(
-        model=DEFAULT_MODEL,
-        max_tokens=1024,
-        system=SYSTEM_PROMPT,
-        messages=[
-            {
-                "role": "user",
-                "content": user_message
-            }
-        ]
+    return create_message(
+        provider=provider_enum,
+        system_prompt=SYSTEM_PROMPT,
+        user_message=user_message,
+        model=model,
+        max_tokens=1024
     )
-
-    return message.content[0].text

bridgekit-0.3.6/bridgekit/providers.py

@@ -0,0 +1,112 @@
+"""Provider client factory for Bridgekit multi-provider support."""
+
+from typing import Union, Dict, Any, List
+from .config import Provider, require_api_key, get_default_model
+
+
+class BaseProviderClient:
+    """Base class for provider clients."""
+    
+    def __init__(self, api_key: str):
+        self.api_key = api_key
+    
+    def create_message(self, system_prompt: str, user_message: str, model: str, max_tokens: int = 1024) -> str:
+        """Create a message with the given parameters."""
+        raise NotImplementedError("Subclasses must implement create_message")
+
+
+class AnthropicClient(BaseProviderClient):
+    """Anthropic provider client."""
+    
+    def __init__(self, api_key: str):
+        super().__init__(api_key)
+        import anthropic
+        self.client = anthropic.Anthropic(api_key=api_key)
+    
+    def create_message(self, system_prompt: str, user_message: str, model: str, max_tokens: int = 1024) -> str:
+        """Create a message using Anthropic's API."""
+        message = self.client.messages.create(
+            model=model,
+            max_tokens=max_tokens,
+            system=system_prompt,
+            messages=[{
+                "role": "user",
+                "content": user_message
+            }]
+        )
+        return message.content[0].text
+
+
+class OpenAIClient(BaseProviderClient):
+    """OpenAI provider client."""
+    
+    def __init__(self, api_key: str):
+        super().__init__(api_key)
+        import openai
+        self.client = openai.OpenAI(api_key=api_key)
+    
+    def create_message(self, system_prompt: str, user_message: str, model: str, max_tokens: int = 1024) -> str:
+        """Create a message using OpenAI's API."""
+        messages = [
+            {"role": "system", "content": system_prompt},
+            {"role": "user", "content": user_message}
+        ]
+        
+        response = self.client.chat.completions.create(
+            model=model,
+            messages=messages,
+            max_tokens=max_tokens
+        )
+        
+        return response.choices[0].message.content
+
+
+class GeminiClient(BaseProviderClient):
+    """Google Gemini provider client."""
+    
+    def __init__(self, api_key: str):
+        super().__init__(api_key)
+        import google.generativeai as genai
+        genai.configure(api_key=api_key)
+    
+    def create_message(self, system_prompt: str, user_message: str, model: str, max_tokens: int = 1024) -> str:
+        """Create a message using Google's Gemini API."""
+        import google.generativeai as genai
+        
+        # Configure the model with system instruction
+        model_instance = genai.GenerativeModel(
+            model_name=model,
+            system_instruction=system_prompt,
+            generation_config=genai.types.GenerationConfig(
+                max_output_tokens=max_tokens,
+            )
+        )
+        
+        response = model_instance.generate_content(user_message)
+        return response.text
+
+
+def create_client(provider: Provider, model: str = None) -> BaseProviderClient:
+    """Create a client for the specified provider."""
+    if model is None:
+        model = get_default_model(provider)
+    
+    api_key = require_api_key(provider)
+    
+    if provider == Provider.ANTHROPIC:
+        return AnthropicClient(api_key)
+    elif provider == Provider.OPENAI:
+        return OpenAIClient(api_key)
+    elif provider == Provider.GEMINI:
+        return GeminiClient(api_key)
+    else:
+        raise ValueError(f"Unsupported provider: {provider}")
+
+
+def create_message(provider: Provider, system_prompt: str, user_message: str, model: str = None, max_tokens: int = 1024) -> str:
+    """Create a message using the specified provider."""
+    if model is None:
+        model = get_default_model(provider)
+    
+    client = create_client(provider, model)
+    return client.create_message(system_prompt, user_message, model, max_tokens)

{bridgekit-0.3.5 → bridgekit-0.3.6}/bridgekit/redteam.py

@@ -1,5 +1,5 @@
-import anthropic
-from .config import DEFAULT_MODEL, require_anthropic_api_key
+from .config import DEFAULT_MODEL, parse_provider, get_default_model
+from .providers import create_message
 
 DEFAULT_STAKEHOLDER = "a skeptical senior executive with no tolerance for weak methodology, unsupported claims, or vague business impact"
 
@@ -39,7 +39,7 @@ HARDEST QUESTION TO ANSWER
 """
 
 
-def redteam(text: str, stakeholder: str = None) -> str:
+def redteam(text: str, stakeholder: str = None, provider: str = None, model: str = None) -> str:
     """
     Red-team a data science analysis writeup from the perspective of a skeptical stakeholder.
 
@@ -48,6 +48,9 @@ def redteam(text: str, stakeholder: str = None) -> str:
         stakeholder: Optional. The skeptical stakeholder role (e.g. "VP of Finance",
                      "skeptical board member", "Chief Revenue Officer").
                      Defaults to a generic skeptical senior executive.
+        provider:    Optional. The AI provider to use ("anthropic", "openai", "gemini").
+                     If not specified, defaults to "anthropic" or infers from model.
+        model:       Optional. The specific model to use. If not specified, uses the provider's default.
 
     Returns:
         The 3-5 hardest critiques the stakeholder would make, plus the single
@@ -56,7 +59,10 @@ def redteam(text: str, stakeholder: str = None) -> str:
     if not text or not text.strip():
         raise ValueError("Text cannot be empty.")
 
-    api_key = require_anthropic_api_key()
+    # Parse provider and determine model
+    provider_enum = parse_provider(provider, model)
+    if model is None:
+        model = get_default_model(provider_enum)
 
     stakeholder_label = stakeholder if stakeholder else "Skeptical Senior Executive"
     stakeholder_desc = stakeholder if stakeholder else DEFAULT_STAKEHOLDER
@@ -66,17 +72,12 @@ def redteam(text: str, stakeholder: str = None) -> str:
         stakeholder_label=stakeholder_label
     )
 
-    client = anthropic.Anthropic(api_key=api_key)
-    message = client.messages.create(
-        model=DEFAULT_MODEL,
-        max_tokens=1024,
-        system=system_prompt,
-        messages=[
-            {
-                "role": "user",
-                "content": f"Red-team this analysis writeup:\n\n{text}"
-            }
-        ]
+    user_message = f"Red-team this analysis writeup:\n\n{text}"
+    
+    return create_message(
+        provider=provider_enum,
+        system_prompt=system_prompt,
+        user_message=user_message,
+        model=model,
+        max_tokens=1024
     )
-
-    return message.content[0].text

{bridgekit-0.3.5 → bridgekit-0.3.6}/bridgekit/reviewer.py

@@ -1,5 +1,5 @@
-import anthropic
-from .config import DEFAULT_MODEL, require_anthropic_api_key
+from .config import DEFAULT_MODEL, parse_provider, get_default_model
+from .providers import create_message
 
 SYSTEM_PROMPT = """You are a senior data scientist reviewing a colleague's analysis writeup. 
 You are direct, constructive, and specific. You do not flatter — you help people improve.
@@ -42,12 +42,15 @@ BOTTOM LINE
 [one sentence]
 """
 
-def evaluate(text: str) -> str:
+def evaluate(text: str, provider: str = None, model: str = None) -> str:
     """
     Evaluate a data science analysis writeup and return structured feedback.
 
     Args:
         text: Your analysis writeup as a plain string.
+        provider: Optional. The AI provider to use ("anthropic", "openai", "gemini").
+                 If not specified, defaults to "anthropic" or infers from model.
+        model: Optional. The specific model to use. If not specified, uses the provider's default.
 
     Returns:
         Structured feedback across four dimensions.
@@ -55,20 +58,17 @@ def evaluate(text: str) -> str:
     if not text or not text.strip():
         raise ValueError("Text cannot be empty.")
 
-    api_key = require_anthropic_api_key()
-
-    client = anthropic.Anthropic(api_key=api_key)
-
-    message = client.messages.create(
-        model=DEFAULT_MODEL,
-        max_tokens=1024,
-        system=SYSTEM_PROMPT,
-        messages=[
-            {
-                "role": "user",
-                "content": f"Please review this analysis writeup:\n\n{text}"
-            }
-        ]
+    # Parse provider and determine model
+    provider_enum = parse_provider(provider, model)
+    if model is None:
+        model = get_default_model(provider_enum)
+
+    user_message = f"Please review this analysis writeup:\n\n{text}"
+    
+    return create_message(
+        provider=provider_enum,
+        system_prompt=SYSTEM_PROMPT,
+        user_message=user_message,
+        model=model,
+        max_tokens=1024
     )
-
-    return message.content[0].text

{bridgekit-0.3.5 → bridgekit-0.3.6}/bridgekit/search.py

@@ -1,6 +1,6 @@
 from pathlib import Path
-import anthropic
-from .config import DEFAULT_MODEL, require_anthropic_api_key
+from .config import DEFAULT_MODEL, parse_provider, get_default_model
+from .providers import create_message
 import chromadb
 from chromadb.utils.embedding_functions import SentenceTransformerEmbeddingFunction
 
@@ -49,7 +49,7 @@ def _chunk(text: str) -> list[str]:
     return [c for c in chunks if c.strip()]
 
 
-def ask(question: str, source: str = None, text: str = None) -> str:
+def ask(question: str, source: str = None, text: str = None, provider: str = None, model: str = None) -> str:
     """
     Ask a question across a collection of analysis documents or raw text.
 
@@ -57,6 +57,9 @@ def ask(question: str, source: str = None, text: str = None) -> str:
         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.
+        provider: Optional. The AI provider to use ("anthropic", "openai", "gemini").
+                  If not specified, defaults to "anthropic" or infers from model.
+        model:    Optional. The specific model to use. If not specified, uses the provider's default.
 
     Returns:
         An answer grounded in the provided documents.
@@ -64,7 +67,10 @@ def ask(question: str, source: str = None, text: str = None) -> str:
     if not source and not text:
         raise ValueError("Provide either 'source' (folder path) or 'text'.")
 
-    api_key = require_anthropic_api_key()
+    # Parse provider and determine model
+    provider_enum = parse_provider(provider, model)
+    if model is None:
+        model = get_default_model(provider_enum)
 
     # Collect chunks
     chunks = []
@@ -99,20 +105,17 @@ def ask(question: str, source: str = None, text: str = None) -> str:
     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=DEFAULT_MODEL,
-        max_tokens=1024,
-        system=(
+    # Generate answer with specified provider
+    user_message = f"Context from analysis reports:\n\n{context}\n\nQuestion: {question}"
+    
+    return create_message(
+        provider=provider_enum,
+        system_prompt=(
             "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}"
-        }]
+        user_message=user_message,
+        model=model,
+        max_tokens=1024
     )
-
-    return message.content[0].text

bridgekit-0.3.5/README.md → bridgekit-0.3.6/bridgekit.egg-info/PKG-INFO

@@ -1,3 +1,35 @@
+Metadata-Version: 2.4
+Name: bridgekit
+Version: 0.3.6
+Summary: AI tools that make you a better data scientist, not a redundant one.
+License: MIT
+Project-URL: Homepage, https://usebridgekit.com
+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: openai
+Requires-Dist: openai>=1.0.0; extra == "openai"
+Provides-Extra: gemini
+Requires-Dist: google-generativeai>=0.3.0; extra == "gemini"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-mock>=3.0.0; extra == "dev"
+Dynamic: license-file
+
 <p align="center">
   <img src="https://raw.githubusercontent.com/getbridgekit/bridgekit/main/assets/logo.png" alt="Bridgekit" width="200"/>
 </p>
@@ -35,12 +67,26 @@ pip install bridgekit
 !pip install bridgekit
 ```
 
-Requires an Anthropic API key:
+Requires an API key for your chosen provider:
 
+**Anthropic (default):**
 ```bash
+pip install bridgekit
 export ANTHROPIC_API_KEY=your_key_here
 ```
 
+**OpenAI:**
+```bash
+pip install bridgekit[openai]
+export OPENAI_API_KEY=your_key_here
+```
+
+**Google Gemini:**
+```bash
+pip install bridgekit[gemini]
+export GOOGLE_API_KEY=your_key_here
+```
+
 ---
 
 ## Getting Started
@@ -341,6 +387,45 @@ willing to commit to — and what's your confidence interval on that estimate?"
 
 ---
 
+## Multi-Provider Support
+
+Bridgekit now supports multiple AI providers so you're not locked into one API. You can use Anthropic, OpenAI, or Google Gemini models with any tool.
+
+**Using different providers:**
+
+```python
+from bridgekit import evaluate, plan, ask, redteam
+
+# Use OpenAI (default model: gpt-4o)
+print(evaluate("Your analysis here", provider="openai"))
+
+# Use Google Gemini (default model: gemini-1.5-pro)
+print(plan("Your question here", provider="gemini"))
+
+# Use specific model
+print(redteam("Your analysis here", model="gpt-4-turbo"))
+print(ask("Your question here", source="reports/", model="claude-3-opus-20240229"))
+```
+
+**Provider auto-detection:**
+Bridgekit automatically detects the provider from model names:
+- Models starting with "claude" → Anthropic
+- Models starting with "gpt" → OpenAI  
+- Models starting with "gemini" → Google Gemini
+
+**Default models by provider:**
+- Anthropic: `claude-3-5-sonnet-20241022`
+- OpenAI: `gpt-4o`
+- Gemini: `gemini-1.5-pro`
+
+All tools support the same `provider` and `model` parameters:
+- `evaluate(text, provider=None, model=None)`
+- `plan(question, provider=None, model=None, ...)`
+- `ask(question, provider=None, model=None, ...)`
+- `redteam(text, provider=None, model=None, ...)`
+
+---
+
 ## 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.
@@ -361,7 +446,7 @@ Bridgekit is a suite, not a one-off. Four tools are live — more are coming:
 
 - **Stakeholder translator** — turn your technical findings into a narrative a non-technical audience will actually follow
 - **Assumption checker** — state your analytical assumptions, get the ones you missed
-- **Multi-model support** — use any LLM provider (OpenAI, Gemini, open source models via OpenRouter) instead of being tied to Anthropic
+- **More specialized tools** — focused on specific data science workflows and challenges
 
 Each tool is small, focused, and built for the way data scientists actually work.
 

{bridgekit-0.3.5 → bridgekit-0.3.6}/bridgekit.egg-info/SOURCES.txt

@@ -4,6 +4,7 @@ pyproject.toml
 bridgekit/__init__.py
 bridgekit/config.py
 bridgekit/planner.py
+bridgekit/providers.py
 bridgekit/redteam.py
 bridgekit/reviewer.py
 bridgekit/search.py
@@ -14,5 +15,6 @@ bridgekit.egg-info/requires.txt
 bridgekit.egg-info/top_level.txt
 tests/test_config.py
 tests/test_planner.py
+tests/test_providers.py
 tests/test_reviewer.py
 tests/test_search.py

{bridgekit-0.3.5 → bridgekit-0.3.6}/bridgekit.egg-info/requires.txt

@@ -9,3 +9,9 @@ nbformat>=5.0.0
 [dev]
 pytest>=7.0.0
 pytest-mock>=3.0.0
+
+[gemini]
+google-generativeai>=0.3.0
+
+[openai]
+openai>=1.0.0

{bridgekit-0.3.5 → bridgekit-0.3.6}/pyproject.toml

@@ -7,7 +7,7 @@ include = ["bridgekit*"]
 
 [project]
 name = "bridgekit"
-version = "0.3.5"
+version = "0.3.6"
 description = "AI tools that make you a better data scientist, not a redundant one."
 readme = "README.md"
 requires-python = ">=3.9"
@@ -31,6 +31,8 @@ dependencies = [
 ]
 
 [project.optional-dependencies]
+openai = ["openai>=1.0.0"]
+gemini = ["google-generativeai>=0.3.0"]
 dev = [
     "pytest>=7.0.0",
     "pytest-mock>=3.0.0",

bridgekit-0.3.6/tests/test_providers.py

@@ -0,0 +1,71 @@
+import os
+import pytest
+from unittest.mock import patch
+
+from bridgekit.config import parse_provider, require_api_key, Provider
+
+
+class TestParseProvider:
+    """parse_provider() returns the correct Provider enum."""
+
+    def test_explicit_anthropic(self):
+        assert parse_provider(provider="anthropic") == Provider.ANTHROPIC
+
+    def test_explicit_openai(self):
+        assert parse_provider(provider="openai") == Provider.OPENAI
+
+    def test_explicit_gemini(self):
+        assert parse_provider(provider="gemini") == Provider.GEMINI
+
+    def test_infer_anthropic_from_model(self):
+        assert parse_provider(model="claude-opus-4-6") == Provider.ANTHROPIC
+
+    def test_infer_openai_from_model(self):
+        assert parse_provider(model="gpt-4o") == Provider.OPENAI
+
+    def test_infer_gemini_from_model(self):
+        assert parse_provider(model="gemini-1.5-pro") == Provider.GEMINI
+
+    def test_defaults_to_anthropic(self):
+        assert parse_provider() == Provider.ANTHROPIC
+
+    def test_raises_on_unsupported_provider(self):
+        with pytest.raises(ValueError, match="Unsupported provider"):
+            parse_provider(provider="cohere")
+
+    def test_provider_takes_precedence_over_model(self):
+        assert parse_provider(provider="openai", model="claude-opus-4-6") == Provider.OPENAI
+
+
+class TestRequireApiKey:
+    """require_api_key() returns the correct key or raises EnvironmentError."""
+
+    def test_returns_anthropic_key(self):
+        with patch.dict(os.environ, {"ANTHROPIC_API_KEY": "sk-ant-test"}, clear=True):
+            assert require_api_key(Provider.ANTHROPIC) == "sk-ant-test"
+
+    def test_returns_openai_key(self):
+        with patch.dict(os.environ, {"OPENAI_API_KEY": "sk-openai-test"}, clear=True):
+            assert require_api_key(Provider.OPENAI) == "sk-openai-test"
+
+    def test_returns_gemini_key(self):
+        with patch.dict(os.environ, {"GOOGLE_API_KEY": "gemini-test"}, clear=True):
+            assert require_api_key(Provider.GEMINI) == "gemini-test"
+
+    def test_raises_when_anthropic_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):
+            with pytest.raises(EnvironmentError, match="ANTHROPIC_API_KEY"):
+                require_api_key(Provider.ANTHROPIC)
+
+    def test_raises_when_openai_key_missing(self):
+        env = {k: v for k, v in os.environ.items() if k != "OPENAI_API_KEY"}
+        with patch.dict(os.environ, env, clear=True):
+            with pytest.raises(EnvironmentError, match="OPENAI_API_KEY"):
+                require_api_key(Provider.OPENAI)
+
+    def test_raises_when_gemini_key_missing(self):
+        env = {k: v for k, v in os.environ.items() if k != "GOOGLE_API_KEY"}
+        with patch.dict(os.environ, env, clear=True):
+            with pytest.raises(EnvironmentError, match="GOOGLE_API_KEY"):
+                require_api_key(Provider.GEMINI)

bridgekit-0.3.5/bridgekit/config.py

@@ -1,18 +0,0 @@
-import os
-
-DEFAULT_MODEL = "claude-opus-4-6"
-
-
-def require_anthropic_api_key() -> str:
-    """Return the Anthropic API key from the environment, or raise a clear error.
-
-    Each Bridgekit tool calls this before constructing an Anthropic client so
-    users get the same friendly message instead of whatever the SDK surfaces
-    when the key is missing.
-    """
-    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"
-        )
-    return api_key