arize-phoenix 7.8.1__tar.gz → 7.9.0__tar.gz

{arize_phoenix-7.8.1 → arize_phoenix-7.9.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: arize-phoenix
-Version: 7.8.1
+Version: 7.9.0
 Summary: AI Observability and Evaluation
 Project-URL: Documentation, https://docs.arize.com/phoenix/
 Project-URL: Issues, https://github.com/Arize-ai/phoenix/issues
@@ -127,7 +127,7 @@ Description-Content-Type: text/markdown
 
 <p align="center">
     <a target="_blank" href="https://phoenix.arize.com" style="background:none">
-        <img alt="phoenix banner" src="https://github.com/Arize-ai/phoenix-assets/blob/main/images/socal/github-large-banner-phoenix.jpg?raw=true" width="auto" height="auto"></img>
+        <img alt="phoenix banner" src="https://github.com/Arize-ai/phoenix-assets/blob/main/images/socal/github-large-banner-phoenix-v2.jpg?raw=true" width="auto" height="auto"></img>
     </a>
     <br/>
     <br/>
@@ -160,6 +160,7 @@ Phoenix is an open-source AI observability platform designed for experimentation
 - [**_Evaluation_**](https://docs.arize.com/phoenix/evaluation/llm-evals) - Leverage LLMs to benchmark your application's performance using response and retrieval evals.
 - [**_Datasets_**](https://docs.arize.com/phoenix/datasets-and-experiments/overview-datasets) - Create versioned datasets of examples for experimentation, evaluation, and fine-tuning.
 - [**_Experiments_**](https://docs.arize.com/phoenix/datasets-and-experiments/overview-datasets#experiments) - Track and evaluate changes to prompts, LLMs, and retrieval.
+- [**_Playground_**](https://docs.arize.com/phoenix/prompt-engineering/overview-prompts)- Optemize prompts, compare models, adjust parameters, and replay traced LLM calls.
 
 Phoenix is vendor and language agnostic with out-of-the-box support for popular frameworks (🦙[LlamaIndex](https://docs.arize.com/phoenix/tracing/integrations-tracing/llamaindex), 🦜⛓[LangChain](https://docs.arize.com/phoenix/tracing/integrations-tracing/langchain), [Haystack](https://docs.arize.com/phoenix/tracing/integrations-tracing/haystack), 🧩[DSPy](https://docs.arize.com/phoenix/tracing/integrations-tracing/dspy)) and LLM providers ([OpenAI](https://docs.arize.com/phoenix/tracing/integrations-tracing/openai), [Bedrock](https://docs.arize.com/phoenix/tracing/integrations-tracing/bedrock), [MistralAI](https://docs.arize.com/phoenix/tracing/integrations-tracing/mistralai), [VertexAI](https://docs.arize.com/phoenix/tracing/integrations-tracing/vertexai), [LiteLLM](https://docs.arize.com/phoenix/tracing/integrations-tracing/litellm), and more). For details on auto-instrumentation, check out the [OpenInference](https://github.com/Arize-ai/openinference) project.
 
@@ -225,6 +226,7 @@ Phoenix is built on top of OpenTelemetry and is vendor, language, and framework
 | [Groq](https://docs.arize.com/phoenix/tracing/integrations-tracing/groq) | `openinference-instrumentation-groq` | [![PyPI Version](https://img.shields.io/pypi/v/openinference-instrumentation-groq.svg)](https://pypi.python.org/pypi/openinference-instrumentation-groq) |
 | [Instructor](https://docs.arize.com/phoenix/tracing/integrations-tracing/instructor) | `openinference-instrumentation-instructor` | [![PyPI Version](https://img.shields.io/pypi/v/openinference-instrumentation-instructor.svg)](https://pypi.python.org/pypi/openinference-instrumentation-instructor) |
 | [Anthropic](https://docs.arize.com/phoenix/tracing/integrations-tracing/anthropic) | `openinference-instrumentation-anthropic` | [![PyPI Version](https://img.shields.io/pypi/v/openinference-instrumentation-anthropic.svg)](https://pypi.python.org/pypi/openinference-instrumentation-anthropic) |
+| [Smolagents](https://huggingface.co/docs/smolagents/en/tutorials/inspect_runs) | `openinference-instrumentation-smolagents` | [![PyPI Version](https://img.shields.io/pypi/v/openinference-instrumentation-smolagents.svg)](https://pypi.python.org/pypi/openinference-instrumentation-smolagents) |
 
 ### JavaScript
 

{arize_phoenix-7.8.1 → arize_phoenix-7.9.0}/README.md

@@ -1,6 +1,6 @@
 <p align="center">
     <a target="_blank" href="https://phoenix.arize.com" style="background:none">
-        <img alt="phoenix banner" src="https://github.com/Arize-ai/phoenix-assets/blob/main/images/socal/github-large-banner-phoenix.jpg?raw=true" width="auto" height="auto"></img>
+        <img alt="phoenix banner" src="https://github.com/Arize-ai/phoenix-assets/blob/main/images/socal/github-large-banner-phoenix-v2.jpg?raw=true" width="auto" height="auto"></img>
     </a>
     <br/>
     <br/>
@@ -33,6 +33,7 @@ Phoenix is an open-source AI observability platform designed for experimentation
 - [**_Evaluation_**](https://docs.arize.com/phoenix/evaluation/llm-evals) - Leverage LLMs to benchmark your application's performance using response and retrieval evals.
 - [**_Datasets_**](https://docs.arize.com/phoenix/datasets-and-experiments/overview-datasets) - Create versioned datasets of examples for experimentation, evaluation, and fine-tuning.
 - [**_Experiments_**](https://docs.arize.com/phoenix/datasets-and-experiments/overview-datasets#experiments) - Track and evaluate changes to prompts, LLMs, and retrieval.
+- [**_Playground_**](https://docs.arize.com/phoenix/prompt-engineering/overview-prompts)- Optemize prompts, compare models, adjust parameters, and replay traced LLM calls.
 
 Phoenix is vendor and language agnostic with out-of-the-box support for popular frameworks (🦙[LlamaIndex](https://docs.arize.com/phoenix/tracing/integrations-tracing/llamaindex), 🦜⛓[LangChain](https://docs.arize.com/phoenix/tracing/integrations-tracing/langchain), [Haystack](https://docs.arize.com/phoenix/tracing/integrations-tracing/haystack), 🧩[DSPy](https://docs.arize.com/phoenix/tracing/integrations-tracing/dspy)) and LLM providers ([OpenAI](https://docs.arize.com/phoenix/tracing/integrations-tracing/openai), [Bedrock](https://docs.arize.com/phoenix/tracing/integrations-tracing/bedrock), [MistralAI](https://docs.arize.com/phoenix/tracing/integrations-tracing/mistralai), [VertexAI](https://docs.arize.com/phoenix/tracing/integrations-tracing/vertexai), [LiteLLM](https://docs.arize.com/phoenix/tracing/integrations-tracing/litellm), and more). For details on auto-instrumentation, check out the [OpenInference](https://github.com/Arize-ai/openinference) project.
 
@@ -98,6 +99,7 @@ Phoenix is built on top of OpenTelemetry and is vendor, language, and framework
 | [Groq](https://docs.arize.com/phoenix/tracing/integrations-tracing/groq) | `openinference-instrumentation-groq` | [![PyPI Version](https://img.shields.io/pypi/v/openinference-instrumentation-groq.svg)](https://pypi.python.org/pypi/openinference-instrumentation-groq) |
 | [Instructor](https://docs.arize.com/phoenix/tracing/integrations-tracing/instructor) | `openinference-instrumentation-instructor` | [![PyPI Version](https://img.shields.io/pypi/v/openinference-instrumentation-instructor.svg)](https://pypi.python.org/pypi/openinference-instrumentation-instructor) |
 | [Anthropic](https://docs.arize.com/phoenix/tracing/integrations-tracing/anthropic) | `openinference-instrumentation-anthropic` | [![PyPI Version](https://img.shields.io/pypi/v/openinference-instrumentation-anthropic.svg)](https://pypi.python.org/pypi/openinference-instrumentation-anthropic) |
+| [Smolagents](https://huggingface.co/docs/smolagents/en/tutorials/inspect_runs) | `openinference-instrumentation-smolagents` | [![PyPI Version](https://img.shields.io/pypi/v/openinference-instrumentation-smolagents.svg)](https://pypi.python.org/pypi/openinference-instrumentation-smolagents) |
 
 ### JavaScript
 

{arize_phoenix-7.8.1 → arize_phoenix-7.9.0}/src/phoenix/server/api/helpers/playground_clients.py

@@ -37,6 +37,7 @@ from phoenix.server.api.input_types.InvocationParameters import (
     InvocationParameter,
     InvocationParameterInput,
     JSONInvocationParameter,
+    StringInvocationParameter,
     StringListInvocationParameter,
     extract_parameter,
     validate_invocation_parameters,
@@ -501,6 +502,11 @@ class OpenAIO1StreamingClient(OpenAIStreamingClient):
     @classmethod
     def supported_invocation_parameters(cls) -> list[InvocationParameter]:
         return [
+            StringInvocationParameter(
+                invocation_name="reasoning_effort",
+                label="Reasoning Effort",
+                canonical_name=CanonicalParameterName.REASONING_EFFORT,
+            ),
             IntInvocationParameter(
                 invocation_name="max_completion_tokens",
                 canonical_name=CanonicalParameterName.MAX_COMPLETION_TOKENS,
@@ -523,6 +529,49 @@ class OpenAIO1StreamingClient(OpenAIStreamingClient):
             ),
         ]
 
+    async def chat_completion_create(
+        self,
+        messages: list[
+            tuple[ChatCompletionMessageRole, str, Optional[str], Optional[list[JSONScalarType]]]
+        ],
+        tools: list[JSONScalarType],
+        **invocation_parameters: Any,
+    ) -> AsyncIterator[ChatCompletionChunk]:
+        from openai import NOT_GIVEN
+
+        # Convert standard messages to OpenAI messages
+        openai_messages = []
+        for message in messages:
+            openai_message = self.to_openai_chat_completion_param(*message)
+            if openai_message is not None:
+                openai_messages.append(openai_message)
+
+        throttled_create = self.rate_limiter._alimit(self.client.chat.completions.create)
+        response = await throttled_create(
+            messages=openai_messages,
+            model=self.model_name,
+            stream=False,
+            tools=tools or NOT_GIVEN,
+            **invocation_parameters,
+        )
+
+        if response.usage is not None:
+            self._attributes.update(dict(self._llm_token_counts(response.usage)))
+
+        choice = response.choices[0]
+        if choice.message.content:
+            yield TextChunk(content=choice.message.content)
+
+        if choice.message.tool_calls:
+            for tool_call in choice.message.tool_calls:
+                yield ToolCallChunk(
+                    id=tool_call.id,
+                    function=FunctionCallChunk(
+                        name=tool_call.function.name,
+                        arguments=tool_call.function.arguments,
+                    ),
+                )
+
     def to_openai_chat_completion_param(
         self,
         role: ChatCompletionMessageRole,
@@ -532,6 +581,7 @@ class OpenAIO1StreamingClient(OpenAIStreamingClient):
     ) -> Optional["ChatCompletionMessageParam"]:
         from openai.types.chat import (
             ChatCompletionAssistantMessageParam,
+            ChatCompletionDeveloperMessageParam,
             ChatCompletionToolMessageParam,
             ChatCompletionUserMessageParam,
         )
@@ -544,7 +594,12 @@ class OpenAIO1StreamingClient(OpenAIStreamingClient):
                 }
             )
         if role is ChatCompletionMessageRole.SYSTEM:
-            return None  # System messages are not supported for o1 models
+            return ChatCompletionDeveloperMessageParam(
+                {
+                    "content": content,
+                    "role": "developer",
+                }
+            )
         if role is ChatCompletionMessageRole.AI:
             if tool_calls is None:
                 return ChatCompletionAssistantMessageParam(

{arize_phoenix-7.8.1 → arize_phoenix-7.9.0}/src/phoenix/server/api/input_types/InvocationParameters.py

@@ -15,6 +15,7 @@ class CanonicalParameterName(str, Enum):
     RANDOM_SEED = "random_seed"
     TOOL_CHOICE = "tool_choice"
     RESPONSE_FORMAT = "response_format"
+    REASONING_EFFORT = "reasoning_effort"
 
 
 @strawberry.enum

arize_phoenix-7.9.0/src/phoenix/version.py

@@ -0,0 +1 @@
+__version__ = "7.9.0"

arize_phoenix-7.8.1/src/phoenix/version.py

@@ -1 +0,0 @@
-__version__ = "7.8.1"