variably-sdk 2.2.0__tar.gz → 2.4.0__tar.gz

{variably_sdk-2.2.0 → variably_sdk-2.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: variably-sdk
-Version: 2.2.0
+Version: 2.4.0
 Summary: Official Python SDK for Variably feature flags, LLM experimentation, and prompt optimization platform
 Author: Variably
 Author-email: Variably <support@variably.com>

{variably_sdk-2.2.0 → variably_sdk-2.4.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "variably-sdk"
-version = "2.2.0"
+version = "2.4.0"
 description = "Official Python SDK for Variably feature flags, LLM experimentation, and prompt optimization platform"
 readme = "README.md"
 requires-python = ">=3.7"

{variably_sdk-2.2.0 → variably_sdk-2.4.0}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name="variably",
-    version="1.0.0",
+    version="2.4.0",
     description="Variably Python SDK for LLM experimentation platform",
     author="Variably",
     packages=find_packages(),

{variably_sdk-2.2.0 → variably_sdk-2.4.0}/src/variably/client.py

@@ -14,6 +14,7 @@ from .types import (
     EvaluateResponse,
     Event,
     FlagResult,
+    LogResult,
     PromptVariant,
     SDKMetrics,
     StreamingEvaluateResponse,
@@ -480,8 +481,8 @@ class VariablyClient:
         experiment_key: str,
         user_context: UserContext,
         input_variables: Dict[str, Any],
-        evaluation_mode: str = "full",
         evaluation_context: Optional[Dict[str, Any]] = None,
+        **kwargs,
     ) -> EvaluateResponse:
         """Managed execution: Variably selects variant, calls LLM, evaluates."""
         if not experiment_key or not isinstance(experiment_key, str):
@@ -494,7 +495,7 @@ class VariablyClient:
             )
 
         response = self.http_client.evaluate_prompt(
-            experiment_key, dict(user_context), input_variables, evaluation_mode,
+            experiment_key, dict(user_context), input_variables,
             evaluation_context=evaluation_context,
         )
 
@@ -515,8 +516,8 @@ class VariablyClient:
         experiment_key: str,
         user_context: UserContext,
         input_variables: Dict[str, Any],
-        evaluation_mode: str = "full",
         evaluation_context: Optional[Dict[str, Any]] = None,
+        **kwargs,
     ) -> StreamingEvaluateResponse:
         """Managed execution with streaming. Yields token strings.
 
@@ -537,7 +538,7 @@ class VariablyClient:
             )
 
         raw_response = self.http_client.evaluate_prompt_stream(
-            experiment_key, dict(user_context), input_variables, evaluation_mode,
+            experiment_key, dict(user_context), input_variables,
             evaluation_context=evaluation_context,
         )
 
@@ -595,6 +596,100 @@ class VariablyClient:
 
         return SubmitResponseResult(status=result.get("status", "ok"))
 
+    def log(
+        self,
+        prompt: Union[str, List[Dict[str, Any]]],
+        response: str,
+        *,
+        conversation_history: Optional[List[Dict[str, Any]]] = None,
+        reference_materials: Optional[List[Dict[str, Any]]] = None,
+        retrieval_query: Optional[str] = None,
+        tags: Optional[List[str]] = None,
+        user_id: Optional[str] = None,
+        session_id: Optional[str] = None,
+        provider: Optional[str] = None,
+        model: Optional[str] = None,
+        latency_ms: Optional[int] = None,
+        prompt_tokens: Optional[int] = None,
+        completion_tokens: Optional[int] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> LogResult:
+        """Log a prompt/response pair for 43-dimension evaluation (Observe Mode).
+
+        Zero-friction entry point — no experiment creation needed. Just log your
+        prompts and responses and see quality scores in the dashboard.
+
+        Args:
+            prompt: The prompt sent to the LLM (str or messages list).
+            response: The LLM's response text.
+            conversation_history: Prior conversation turns for cross-turn coherence scoring.
+            reference_materials: Retrieved RAG chunks for grounding/hallucination scoring.
+            retrieval_query: The query sent to the retriever (for retrieval relevance scoring).
+            tags: Optional tags for grouping observations (e.g. ["production", "chatbot"]).
+            user_id: End-user ID for per-user analytics.
+            session_id: Session ID for multi-turn tracking.
+            provider: LLM provider name (e.g. "openai", "anthropic").
+            model: Model name (e.g. "gpt-4", "claude-3-opus").
+            latency_ms: LLM call latency in milliseconds.
+            prompt_tokens: Number of input tokens.
+            completion_tokens: Number of output tokens.
+            metadata: Arbitrary key-value metadata.
+
+        Returns:
+            LogResult with observation_id and status.
+        """
+        # Normalize prompt to string
+        prompt_str = prompt if isinstance(prompt, str) else str(prompt)
+
+        data: Dict[str, Any] = {
+            "prompt": prompt_str,
+            "response": response,
+        }
+
+        # Build evaluation_context from multi-turn/RAG params
+        evaluation_context: Dict[str, Any] = {}
+        if conversation_history:
+            evaluation_context["conversation_history"] = conversation_history
+        if reference_materials:
+            evaluation_context["reference_materials"] = reference_materials
+        if retrieval_query:
+            evaluation_context["retrieval_query"] = retrieval_query
+        if evaluation_context:
+            data["evaluation_context"] = evaluation_context
+
+        if tags:
+            data["tags"] = tags
+        if user_id:
+            data["user_id"] = user_id
+        if session_id:
+            data["session_id"] = session_id
+        if provider:
+            data["provider"] = provider
+        if model:
+            data["model"] = model
+        if latency_ms is not None:
+            data["latency_ms"] = latency_ms
+        if prompt_tokens is not None:
+            data["prompt_tokens"] = prompt_tokens
+        if completion_tokens is not None:
+            data["completion_tokens"] = completion_tokens
+        if metadata:
+            data["metadata"] = metadata
+
+        try:
+            result = self.http_client.log_observation(data)
+            return LogResult(
+                observation_id=result.get("observation_id", ""),
+                experiment_id=result.get("experiment_id", ""),
+                status=result.get("status", "queued"),
+            )
+        except Exception as error:
+            self.logger.error(
+                "Observation logging failed",
+                {"error": str(error)},
+            )
+            raise
+
     def clear_cache(self) -> None:
         """Clear the cache."""
         self.cache.clear()

{variably_sdk-2.2.0 → variably_sdk-2.4.0}/src/variably/http_client.py

@@ -60,7 +60,7 @@ class HTTPClient:
         session.headers.update({
             "Content-Type": "application/json",
             "X-API-Key": self.config.api_key,
-            "User-Agent": "Variably-Python-SDK/2.1.0",
+            "User-Agent": "Variably-Python-SDK/2.3.0",
         })
         
         return session
@@ -185,7 +185,6 @@ class HTTPClient:
     def evaluate_prompt(
         self, experiment_key: str, user_context: Dict[str, Any],
         input_variables: Dict[str, Any],
-        evaluation_mode: str = "full",
         evaluation_context: Optional[Dict[str, Any]] = None,
     ) -> Dict[str, Any]:
         """Managed execution: select variant, call LLM, evaluate."""
@@ -193,7 +192,6 @@ class HTTPClient:
             "experiment_key": experiment_key,
             "user_context": self._convert_user_context(user_context),
             "input_variables": input_variables,
-            "evaluation_mode": evaluation_mode,
         }
         if evaluation_context:
             request_data["evaluation_context"] = evaluation_context
@@ -208,7 +206,6 @@ class HTTPClient:
     def evaluate_prompt_stream(
         self, experiment_key: str, user_context: Dict[str, Any],
         input_variables: Dict[str, Any],
-        evaluation_mode: str = "full",
         evaluation_context: Optional[Dict[str, Any]] = None,
     ) -> requests.Response:
         """Managed execution with streaming: returns raw SSE response for token parsing."""
@@ -216,7 +213,6 @@ class HTTPClient:
             "experiment_key": experiment_key,
             "user_context": self._convert_user_context(user_context),
             "input_variables": input_variables,
-            "evaluation_mode": evaluation_mode,
         }
         if evaluation_context:
             request_data["evaluation_context"] = evaluation_context
@@ -247,6 +243,15 @@ class HTTPClient:
             retryable=False,
         )
 
+    def log_observation(self, data: Dict[str, Any]) -> Dict[str, Any]:
+        """Log a prompt/response pair for observe-mode evaluation."""
+        return self._make_request(
+            "POST",
+            "/api/v1/internal/sdk/observe/log",
+            json=data,
+            retryable=False,
+        )
+
     def _make_request(
         self,
         method: str,

{variably_sdk-2.2.0 → variably_sdk-2.4.0}/src/variably/types.py

@@ -346,4 +346,19 @@ class SubmitResponseResult:
         self.status = status
 
     def __repr__(self) -> str:
-        return f"SubmitResponseResult(status='{self.status}')"
+        return f"SubmitResponseResult(status='{self.status}')"
+
+
+class LogResult:
+    """Result from observe/log endpoint."""
+
+    def __init__(self, observation_id: str, experiment_id: str, status: str):
+        self.observation_id = observation_id
+        self.experiment_id = experiment_id
+        self.status = status
+
+    def __repr__(self) -> str:
+        return (
+            f"LogResult(observation_id='{self.observation_id}', "
+            f"experiment_id='{self.experiment_id}', status='{self.status}')"
+        )

{variably_sdk-2.2.0 → variably_sdk-2.4.0}/src/variably/version.py

@@ -1,3 +1,3 @@
 """Version information for Variably SDK."""
 
-__version__ = "2.1.0"
+__version__ = "2.3.0"

{variably_sdk-2.2.0 → variably_sdk-2.4.0}/src/variably_sdk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: variably-sdk
-Version: 2.2.0
+Version: 2.4.0
 Summary: Official Python SDK for Variably feature flags, LLM experimentation, and prompt optimization platform
 Author: Variably
 Author-email: Variably <support@variably.com>