Eval Models

class OpenAIModel:
    api_key: Optional[str] = field(repr=False, default=None)
    """Your OpenAI key. If not provided, will be read from the environment variable"""
    organization: Optional[str] = field(repr=False, default=None)
    """
    The organization to use for the OpenAI API. If not provided, will default
    to what's configured in OpenAI
    """
    base_url: Optional[str] = field(repr=False, default=None)
    """
    An optional base URL to use for the OpenAI API. If not provided, will default
    to what's configured in OpenAI
    """
    model: str = "gpt-4"
    """Model name to use. In of azure, this is the deployment name such as gpt-35-instant"""
    temperature: float = 0.0
    """What sampling temperature to use."""
    max_tokens: int = 256
    """The maximum number of tokens to generate in the completion.
    -1 returns as many tokens as possible given the prompt and
    the models maximal context size."""
    top_p: float = 1
    """Total probability mass of tokens to consider at each step."""
    frequency_penalty: float = 0
    """Penalizes repeated tokens according to frequency."""
    presence_penalty: float = 0
    """Penalizes repeated tokens."""
    n: int = 1
    """How many completions to generate for each prompt."""
    model_kwargs: Dict[str, Any] = field(default_factory=dict)
    """Holds any model parameters valid for `create` call not explicitly specified."""
    batch_size: int = 20
    """Batch size to use when passing multiple documents to generate."""
    request_timeout: Optional[Union[float, Tuple[float, float]]] = None
    """Timeout for requests to OpenAI completion API. Default is 600 seconds."""

model = OpenAI()
model("Hello there, this is a test if you are working?")
# Output: "Hello! I'm working perfectly. How can I assist you today?"

model = OpenAIModel(
    model="gpt-35-turbo-16k",
    azure_endpoint="https://arize-internal-llm.openai.azure.com/",
    api_version="2023-09-15-preview",
)

api_version: str = field(default=None)
"""
The verion of the API that is provisioned
https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#rest-api-versioning
"""
azure_endpoint: Optional[str] = field(default=None)
"""
The endpoint to use for azure openai. Available in the azure portal.
https://learn.microsoft.com/en-us/azure/cognitive-services/openai/how-to/create-resource?pivots=web-portal#create-a-resource
"""
azure_deployment: Optional[str] = field(default=None)
azure_ad_token: Optional[str] = field(default=None)
azure_ad_token_provider: Optional[Callable[[], str]] = field(default=None)

class VertexAIModel:
    project: Optional[str] = None
    location: Optional[str] = None
    credentials: Optional["Credentials"] = None
    model: str = "text-bison"
    tuned_model: Optional[str] = None
    temperature: float = 0.0
    max_tokens: int = 256
    top_p: float = 0.95
    top_k: int = 40

project = "my-project-id"
location = "us-central1" # as an example
model = VertexAIModel(project=project, location=location)
model("Hello there, this is a tesst if you are working?")
# Output: "Hello world, I am working!"

class GeminiModel:
    project: Optional[str] = None
    location: Optional[str] = None
    credentials: Optional["Credentials"] = None
    model: str = "gemini-pro"
    default_concurrency: int = 5
    temperature: float = 0.0
    max_tokens: int = 256
    top_p: float = 1
    top_k: int = 32

class GoogleGenAIModel:
    model: str = "gemini-2.5-flash"
    """The model name to use."""
    vertexai: Optional[bool] = None
    """Whether to use VertexAI instead of the Developer API."""
    api_key: Optional[str] = None
    """Your Google API key. If not provided, will be read from environment variables."""
    credentials: Optional["Credentials"] = None
    """Google Cloud credentials for VertexAI access."""
    project: Optional[str] = None
    """Google Cloud project ID for VertexAI."""
    location: Optional[str] = None
    """Google Cloud location for VertexAI."""
    initial_rate_limit: int = 5
    """Initial rate limit for API calls per second."""

export GOOGLE_API_KEY=your_api_key_here

from phoenix.evals import GoogleGenAIModel

# API key will be read from environment
model = GoogleGenAIModel()

model = GoogleGenAIModel(
    vertexai=True,
    project="your-project-id",
    location="us-central1"
)

from phoenix.evals import GoogleGenAIModel

# Initialize with default settings
model = GoogleGenAIModel(model="gemini-2.5-flash")

# Simple text generation
response = model("What is the capital of France?")
print(response)  # "The capital of France is Paris."

import base64
from phoenix.evals.templates import MultimodalPrompt, PromptPart, PromptPartContentType

# Load and encode an image
with open("image.jpg", "rb") as f:
    image_bytes = f.read()
image_base64 = base64.b64encode(image_bytes).decode("utf-8")

# Create multimodal prompt
prompt = MultimodalPrompt(
    parts=[
        PromptPart(content_type=PromptPartContentType.TEXT, content="What's in this image?"),
        PromptPart(content_type=PromptPartContentType.IMAGE, content=image_base64)
    ]
)

response = model._generate(prompt=prompt)
print(response)

# Load and encode audio
with open("audio.wav", "rb") as f:
    audio_bytes = f.read()
audio_base64 = base64.b64encode(audio_bytes).decode("utf-8")

prompt = MultimodalPrompt(
    parts=[
        PromptPart(content_type=PromptPartContentType.AUDIO, content=audio_base64)
    ]
)

response = model._generate(prompt=prompt)
print(response)

class AnthropicModel(BaseModel):
    model: str = "claude-2.1"
    """The model name to use."""
    temperature: float = 0.0
    """What sampling temperature to use."""
    max_tokens: int = 256
    """The maximum number of tokens to generate in the completion."""
    top_p: float = 1
    """Total probability mass of tokens to consider at each step."""
    top_k: int = 256
    """The cutoff where the model no longer selects the words."""
    stop_sequences: List[str] = field(default_factory=list)
    """If the model encounters a stop sequence, it stops generating further tokens."""
    extra_parameters: Dict[str, Any] = field(default_factory=dict)
    """Any extra parameters to add to the request body (e.g., countPenalty for a21 models)"""
    max_content_size: Optional[int] = None
    """If you're using a fine-tuned model, set this to the maximum content size"""

class BedrockModel:
    model_id: str = "anthropic.claude-v2"
    """The model name to use."""
    temperature: float = 0.0
    """What sampling temperature to use."""
    max_tokens: int = 256
    """The maximum number of tokens to generate in the completion."""
    top_p: float = 1
    """Total probability mass of tokens to consider at each step."""
    top_k: int = 256
    """The cutoff where the model no longer selects the words"""
    stop_sequences: List[str] = field(default_factory=list)
    """If the model encounters a stop sequence, it stops generating further tokens. """
    session: Any = None
    """A bedrock session. If provided, a new bedrock client will be created using this session."""
    client = None
    """The bedrock session client. If unset, a new one is created with boto3."""
    max_content_size: Optional[int] = None
    """If you're using a fine-tuned model, set this to the maximum content size"""
    extra_parameters: Dict[str, Any] = field(default_factory=dict)
    """Any extra parameters to add to the request body (e.g., countPenalty for a21 models)"""

import boto3

# Create a Boto3 session
session = boto3.session.Session(
    aws_access_key_id='ACCESS_KEY',
    aws_secret_access_key='SECRET_KEY',
    region_name='us-east-1'  # change to your preferred AWS region
)

#If you need to assume a role
# Creating an STS client
sts_client = session.client('sts')

# (optional - if needed) Assuming a role
response = sts_client.assume_role(
    RoleArn="arn:aws:iam::......",
    RoleSessionName="AssumeRoleSession1",
    #(optional) if MFA Required
    SerialNumber='arn:aws:iam::...',
    #Insert current token, needs to be run within x seconds of generation
    TokenCode='PERIODIC_TOKEN'
)

# Your temporary credentials will be available in the response dictionary
temporary_credentials = response['Credentials']

# Creating a new Boto3 session with the temporary credentials
assumed_role_session = boto3.Session(
    aws_access_key_id=temporary_credentials['AccessKeyId'],
    aws_secret_access_key=temporary_credentials['SecretAccessKey'],
    aws_session_token=temporary_credentials['SessionToken'],
    region_name='us-east-1'
)

client_bedrock = assumed_role_session.client("bedrock-runtime")
# Arize Model Object - Bedrock ClaudV2 by default
model = BedrockModel(client=client_bedrock)

```python
class MistralAIModel(BaseModel):
    model: str = "mistral-large-latest"
    temperature: float = 0
    top_p: Optional[float] = None
    random_seed: Optional[int] = None
    response_format: Optional[Dict[str, str]] = None
    safe_mode: bool = False
    safe_prompt: bool = False

class LiteLLMModel(BaseEvalModel):
    model: str = "gpt-3.5-turbo"
    """The model name to use."""
    temperature: float = 0.0
    """What sampling temperature to use."""
    max_tokens: int = 256
    """The maximum number of tokens to generate in the completion."""
    top_p: float = 1
    """Total probability mass of tokens to consider at each step."""
    num_retries: int = 6
    """Maximum number to retry a model if an RateLimitError, OpenAIError, or
    ServiceUnavailableError occurs."""
    request_timeout: int = 60
    """Maximum number of seconds to wait when retrying."""
    model_kwargs: Dict[str, Any] = field(default_factory=dict)
    """Model specific params"""

import os

from phoenix.evals import LiteLLMModel

os.environ["OLLAMA_API_BASE"] = "http://localhost:11434"

model = LiteLLMModel(model="ollama/llama3")

# model = Instantiate your model here
model("Hello there, how are you?")
# Output: "As an artificial intelligence, I don't have feelings, 
#          but I'm here and ready to assist you. How can I help you today?"