Calls¶
If you haven't already, we recommend first reading the section on writing Prompts
When working with Large Language Model (LLM) APIs in Mirascope, a "call" refers to making a request to a LLM provider's API with a particular setting and prompt.
The call decorator is a core feature of the Mirascope library, designed to simplify and streamline interactions with various LLM providers. This powerful tool allows you to transform prompt templates written as Python functions into LLM API calls with minimal boilerplate code while providing type safety and consistency across different providers.
We currently support OpenAI, Anthropic, Mistral, Gemini, Groq, Cohere, LiteLLM, Azure AI, and Vertex AI
If there are any providers we don't yet support that you'd like to see supported, let us know!
API Documentation
Basic Usage and Syntax¶
Provider-Specific Usage¶
Let's take a look at a basic example using Mirascope vs. official provider SDKs:
Mirascope
from mirascope.core import BaseMessageParam, bedrock
@bedrock.call("anthropic.claude-3-haiku-20240307-v1:0")
def recommend_book(genre: str) -> list[BaseMessageParam]:
return [BaseMessageParam(role="user", content=f"Recommend a {genre} book")]
response = recommend_book("fantasy")
print(response.content)
Official SDK
from openai import OpenAI
client = OpenAI()
def recommend_book(genre: str) -> str:
completion = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": f"Recommend a {genre} book"}],
)
return str(completion.choices[0].message.content)
output = recommend_book("fantasy")
print(output)
from anthropic import Anthropic
client = Anthropic()
def recommend_book(genre: str) -> str:
message = client.messages.create(
model="claude-3-5-sonnet-20240620",
messages=[{"role": "user", "content": f"Recommend a {genre} book"}],
max_tokens=1024,
)
block = message.content[0]
return block.text if block.type == "text" else ""
output = recommend_book("fantasy")
print(output)
from mistralai.client import MistralClient
client = MistralClient()
def recommend_book(genre: str) -> str:
completion = client.chat(
model="mistral-large-latest",
messages=[{"role": "user", "content": f"Recommend a {genre} book"}],
)
return completion.choices[0].message.content
output = recommend_book("fantasy")
print(output)
from google.generativeai import GenerativeModel
client = GenerativeModel("gemini-1.5-flash")
def recommend_book(genre: str) -> str:
generation = client.generate_content(
contents=[{"role": "user", "parts": f"Recommend a {genre} book"}] # pyright: ignore [reportArgumentType]
)
return generation.candidates[0].content.parts[0].text
output = recommend_book("fantasy")
print(output)
from groq import Groq
client = Groq()
def recommend_book(genre: str) -> str:
completion = client.chat.completions.create(
model="llama-3.1-70b-versatile",
messages=[{"role": "user", "content": f"Recommend a {genre} book"}],
)
return str(completion.choices[0].message.content)
output = recommend_book("fantasy")
print(output)
from azure.ai.inference import ChatCompletionsClient
from azure.ai.inference.models import ChatRequestMessage
from azure.core.credentials import AzureKeyCredential
client = ChatCompletionsClient(
endpoint="YOUR_ENDPOINT", credential=AzureKeyCredential("YOUR_KEY")
)
def recommend_book(genre: str) -> str:
completion = client.complete(
model="gpt-4o-mini",
messages=[
ChatRequestMessage({"role": "user", "content": f"Recommend a {genre} book"})
],
)
message = completion.choices[0].message
return message.content if message.content is not None else ""
output = recommend_book("fantasy")
print(output)
from vertexai.generative_models import GenerativeModel
client = GenerativeModel("gemini-1.5-flash")
def recommend_book(genre: str) -> str:
generation = client.generate_content(
contents=[{"role": "user", "parts": f"Recommend a {genre} book"}]
)
return generation.candidates[0].content.parts[0].text # type: ignore
output = recommend_book("fantasy")
print(output)
import boto3
bedrock_client = boto3.client(service_name="bedrock-runtime")
def recommend_book(genre: str) -> str:
messages = [{"role": "user", "content": [{"text": f"Recommend a {genre} book"}]}]
response = bedrock_client.converse(
modelId="anthropic.claude-3-haiku-20240307-v1:0",
messages=messages,
inferenceConfig={"maxTokens": 1024},
)
output_message = response["output"]["message"]
content = ""
for content_piece in output_message["content"]:
if "text" in content_piece:
content += content_piece["text"]
return content
output = recommend_book("fantasy")
print(output)
Notice how Mirascope makes calls more readable by reducing boilerplate and standardizing interactions with LLM providers.
In these above Mirascope examples, we are directly tying the prompt to a specific provider and call setting (provider-specific prompt engineering). In these cases, the @prompt_template decorator becomes optional unless you're using string templates.
Provider-Agnostic Usage¶
We've implemented calls as decorators so that they work for both provider-specific cases (as seen above) as well as provider-agnostic cases.
Let's take a look at a basic example using Mirascope to call both OpenAI and Anthropic with the same prompt:
from mirascope.core import anthropic, openai, prompt_template
@prompt_template()
def recommend_book_prompt(genre: str) -> str:
return f"Recommend a {genre} book"
# OpenAI
openai_model = "gpt-4o-mini"
openai_recommend_book = openai.call(openai_model)(recommend_book_prompt)
openai_response = openai_recommend_book("fantasy")
print(openai_response.content)
# Anthropic
anthropic_model = "claude-3-5-sonnet-20240620"
anthropic_recommend_book = anthropic.call(anthropic_model)(recommend_book_prompt)
anthropic_response = anthropic_recommend_book("fantasy")
print(anthropic_response.content)
from mirascope.core import Messages, anthropic, openai, prompt_template
@prompt_template()
def recommend_book_prompt(genre: str) -> Messages.Type:
return Messages.User(f"Recommend a {genre} book")
# OpenAI
openai_model = "gpt-4o-mini"
openai_recommend_book = openai.call(openai_model)(recommend_book_prompt)
openai_response = openai_recommend_book("fantasy")
print(openai_response.content)
# Anthropic
anthropic_model = "claude-3-5-sonnet-20240620"
anthropic_recommend_book = anthropic.call(anthropic_model)(recommend_book_prompt)
anthropic_response = anthropic_recommend_book("fantasy")
print(anthropic_response.content)
from mirascope.core import anthropic, openai, prompt_template
@prompt_template("Recommend a {genre} book")
def recommend_book_prompt(genre: str): ...
# OpenAI
openai_model = "gpt-4o-mini"
openai_recommend_book = openai.call(openai_model)(recommend_book_prompt)
openai_response = openai_recommend_book("fantasy")
print(openai_response.content)
# Anthropic
anthropic_model = "claude-3-5-sonnet-20240620"
anthropic_recommend_book = anthropic.call(anthropic_model)(recommend_book_prompt)
anthropic_response = anthropic_recommend_book("fantasy")
print(anthropic_response.content)
from mirascope.core import BaseMessageParam, anthropic, openai, prompt_template
@prompt_template()
def recommend_book_prompt(genre: str) -> list[BaseMessageParam]:
return [BaseMessageParam(role="user", content=f"Recommend a {genre} book")]
# OpenAI
openai_model = "gpt-4o-mini"
openai_recommend_book = openai.call(openai_model)(recommend_book_prompt)
openai_response = openai_recommend_book("fantasy")
print(openai_response.content)
# Anthropic
anthropic_model = "claude-3-5-sonnet-20240620"
anthropic_recommend_book = anthropic.call(anthropic_model)(recommend_book_prompt)
anthropic_response = anthropic_recommend_book("fantasy")
print(anthropic_response.content)
Handling Responses¶
Common Response Properties and Methods¶
API Documentation
All BaseCallResponse objects share these common properties:
content: The main text content of the response. If no content is present, this will be the empty string.finish_reasons: A list of reasons why the generation finished (e.g., "stop", "length"). These will be typed specifically for the provider used. If no finish reasons are present, this will beNone.model: The name of the model used for generation.id: A unique identifier for the response if available. Otherwise this will beNone.usage: Information about token usage for the call if available. Otherwise this will beNone.input_tokens: The number of input tokens used if available. Otherwise this will beNone.output_tokens: The number of output tokens generated if available. Otherwise this will beNone.cost: An estimated cost of the API call if available. Otherwise this will beNone.message_param: The assistant's response formatted as a message parameter.tools: A list of provider-specific tools used in the response, if any. Otherwise this will beNone. Check out theToolsdocumentation for more details.tool: The first tool used in the response, if any. Otherwise this will beNone. Check out theToolsdocumentation for more details.tool_types: A list of tool types used in the call, if any. Otherwise this will beNone.prompt_template: The prompt template used for the call.fn_args: The arguments passed to the function.dynamic_config: The dynamic configuration used for the call.metadata: Any metadata provided using the dynamic configuration.messages: The list of messages sent in the request.call_params: The call parameters provided to thecalldecorator.call_kwargs: The finalized keyword arguments used to make the API call.user_message_param: The most recent user message, if any. Otherwise this will beNone.start_time: The timestamp when the call started.end_time: The timestamp when the call ended.
There are also two common methods:
__str__: Returns thecontentproperty of the response for easy printing.tool_message_params: Creates message parameters for tool call results. Check out theToolsdocumentation for more information.
Provider-Specific Response Details¶
API Documentation
mirascope.core.openai.call_response
mirascope.core.anthropic.call_response
mirascope.core.mistral.call_response
mirascope.core.gemini.call_response
mirascope.core.groq.call_response
mirascope.core.cohere.call_response
mirascope.core.litellm.call_response
mirascope.core.azure.call_response
While Mirascope provides a consistent interface, you can also always access the full, provider-specific response object if needed. This is available through the response property of the BaseCallResponse object.
from mirascope.core import BaseMessageParam, anthropic
@anthropic.call("claude-3-5-sonnet-20240620")
def recommend_book(genre: str) -> list[BaseMessageParam]:
return [BaseMessageParam(role="user", content=f"Recommend a {genre} book")]
response = recommend_book("fantasy")
original_response = response.response
from mirascope.core import BaseMessageParam, bedrock
@bedrock.call("anthropic.claude-3-haiku-20240307-v1:0")
def recommend_book(genre: str) -> list[BaseMessageParam]:
return [BaseMessageParam(role="user", content=f"Recommend a {genre} book")]
response = recommend_book("fantasy")
original_response = response.response
Reasoning For Provider-Specific BaseCallResponse Objects
The reason that we have provider-specific response objects (e.g. OpenAICallResponse) is to provide proper type hints and safety when accessing the original response.
Multi-Modal Outputs¶
While most LLM providers focus on text outputs, some providers support additional output modalities like audio. The availability of multi-modal outputs varies among providers:
| Provider | Text | Audio | Image |
|---|---|---|---|
| OpenAI | ✓ | ✓ | - |
| Anthropic | ✓ | - | - |
| Mistral | ✓ | - | - |
| Gemini | ✓ | - | - |
| Groq | ✓ | - | - |
| Cohere | ✓ | - | - |
| LiteLLM | ✓ | - | - |
| Azure AI | ✓ | - | - |
| Vertex AI | ✓ | - | - |
Legend: ✓ (Supported), - (Not Supported)
Audio Outputs¶
audio: Configuration for the audio output (voice, format, etc.)modalities: List of output modalities to receive (e.g.["text", "audio"])
For providers that support audio outputs, you can receive both text and audio responses from your calls:
import io
import wave
from pydub.playback import play
from pydub import AudioSegment
from mirascope.core import openai
@openai.call(
"gpt-4o-audio-preview",
call_params={
"audio": {"voice": "alloy", "format": "wav"},
"modalities": ["text", "audio"],
},
)
def recommend_book(genre: str) -> str:
return f"Recommend a {genre} book"
response = recommend_book(genre="fantasy")
print(response.audio_transcript)
if audio := response.audio:
audio_io = io.BytesIO(audio)
with wave.open(audio_io, "rb") as f:
audio_segment = AudioSegment.from_raw(
audio_io,
sample_width=f.getsampwidth(),
frame_rate=f.getframerate(),
channels=f.getnchannels(),
)
play(audio_segment)
import io
import wave
from pydub.playback import play
from pydub import AudioSegment
from mirascope.core import openai, Messages
@openai.call(
"gpt-4o-audio-preview",
call_params={
"audio": {"voice": "alloy", "format": "wav"},
"modalities": ["text", "audio"],
},
)
def recommend_book(genre: str) -> Messages.Type:
return Messages.User(f"Recommend a {genre} book")
response = recommend_book(genre="fantasy")
print(response.audio_transcript)
if audio := response.audio:
audio_io = io.BytesIO(audio)
with wave.open(audio_io, "rb") as f:
audio_segment = AudioSegment.from_raw(audio_io)
play(audio_segment)
import io
import wave
from pydub.playback import play
from pydub import AudioSegment
from mirascope.core import openai, prompt_template
@openai.call(
"gpt-4o-audio-preview",
call_params={
"audio": {"voice": "alloy", "format": "wav"},
"modalities": ["text", "audio"],
},
)
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str): ...
response = recommend_book(genre="fantasy")
print(response.audio_transcript)
if audio := response.audio:
audio_io = io.BytesIO(audio)
with wave.open(audio_io, "rb") as f:
audio_segment = AudioSegment.from_raw(
audio_io,
sample_width=f.getsampwidth(),
frame_rate=f.getframerate(),
channels=f.getnchannels(),
)
play(audio_segment)
import io
import wave
from pydub.playback import play
from pydub import AudioSegment
from mirascope.core import openai, BaseMessageParam
@openai.call(
"gpt-4o-audio-preview",
call_params={
"audio": {"voice": "alloy", "format": "wav"},
"modalities": ["text", "audio"],
},
)
def recommend_book(genre: str) -> list[BaseMessageParam]:
return [BaseMessageParam(role="user", content=f"Recommend a {genre} book")]
response = recommend_book(genre="fantasy")
print(response.audio_transcript)
if audio := response.audio:
audio_io = io.BytesIO(audio)
with wave.open(audio_io, "rb") as f:
audio_segment = AudioSegment.from_raw(
audio_io,
sample_width=f.getsampwidth(),
frame_rate=f.getframerate(),
channels=f.getnchannels(),
)
play(audio_segment)
When using models that support audio outputs, you'll have access to:
content: The text content of the responseaudio: The raw audio bytes of the responseaudio_transcript: The transcript of the audio response
Audio Playback Requirements
The example above uses pydub and ffmpeg for audio playback, but you can use any audio processing libraries or media players that can handle WAV format audio data. Choose the tools that best fit your needs and environment.
If you decide to use pydub:
- Install pydub: pip install pydub
- Install ffmpeg: Available from ffmpeg.org or through system package managers
Voice Options
For providers that support audio outputs, refer to their documentation for available voice options and configurations:
- OpenAI: Text to Speech Guide
Common Parameters Across Providers¶
While each LLM provider has its own specific parameters, there are several common parameters that you'll find across all providers when using the call decorator. These parameters allow you to control various aspects of the LLM call:
model: The only required parameter for all providers, which may be passed in as a standard argument (whereas all others are optional and must be provided as keyword arguments). It specifies which language model to use for the generation. Each provider has its own set of available models.stream: A boolean that determines whether the response should be streamed or returned as a complete response. We cover this in more detail in theStreamsdocumentation.response_model: A PydanticBaseModeltype that defines how to structure the response. We cover this in more detail in theResponse Modelsdocumentation.output_parser: A function for parsing the response output. We cover this in more detail in theOutput Parsersdocumentation.json_mode: A boolean that deterines whether to use JSON mode or not. We cover this in more detail in theJSON Modedocumentation.tools: A list of tools that the model may request to use in its response. We cover this in more detail in theToolsdocumentation.client: A custom client to use when making the call to the LLM. We cover this in more detail in theCustom Clientsection below.call_params: The provider-specific parameters to use when making the call to that provider's API. We cover this in more detail in theProvider-Specific Parameterssection below.
These common parameters provide a consistent way to control the behavior of LLM calls across different providers. Keep in mind that while these parameters are widely supported, there might be slight variations in how they're implemented or their exact effects across different providers (and the documentation should cover any such differences).
Provider-Specific Parameters¶
API Documentation
mirascope.core.openai.call_params
mirascope.core.anthropic.call_params
mirascope.core.mistral.call_params
mirascope.core.gemini.call_params
mirascope.core.groq.call_params
mirascope.core.cohere.call_params
mirascope.core.litellm.call_params
mirascope.core.azure.call_params
While Mirascope provides a consistent interface across different LLM providers, each provider has its own set of specific parameters that can be used to further configure the behavior of the model. These parameters are passed to the call decorator through the call_params argument.
For all providers, we have only included additional call parameters that are not already covered as shared arguments to the call decorator (e.g. model). We have also opted to exclude currently deprecated parameters entirely. However, since call_params is just a TypedDict, you can always include any additional keys at the expense of type errors (and potentially unknown behavior).
from mirascope.core import BaseMessageParam, anthropic
@anthropic.call("claude-3-5-sonnet-20240620", call_params={"max_tokens": 512})
def recommend_book(genre: str) -> list[BaseMessageParam]:
return [BaseMessageParam(role="user", content=f"Recommend a {genre} book")]
response = recommend_book("fantasy")
Dynamic Configuration¶
Often you will want (or need) to configure your calls dynamically at runtime. Mirascope supports returning a BaseDynamicConfig from your prompt template, which will then be used to dynamically update the settings of the call.
In all cases, you will need to return your prompt messages through the messages keyword of the dynamic config unless you're using string templates.
Call Params¶
from mirascope.core import BaseDynamicConfig, Messages, openai
@openai.call("gpt-4o-mini")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, anthropic
@anthropic.call("claude-3-5-sonnet-20240620")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, mistral
@mistral.call("mistral-large-latest")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, gemini
@gemini.call("gemini-1.5-flash")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, groq
@groq.call("llama-3.1-70b-versatile")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, cohere
@cohere.call("command-r-plus")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, litellm
@litellm.call("gpt-4o-mini")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, azure
@azure.call("gpt-4o-mini")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, vertex
@vertex.call("gemini-1.5-flash")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, bedrock
@bedrock.call("anthropic.claude-3-haiku-20240307-v1:0")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, openai
@openai.call("gpt-4o-mini")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, anthropic
@anthropic.call("claude-3-5-sonnet-20240620")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, mistral
@mistral.call("mistral-large-latest")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, gemini
@gemini.call("gemini-1.5-flash")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, groq
@groq.call("llama-3.1-70b-versatile")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, cohere
@cohere.call("command-r-plus")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, litellm
@litellm.call("gpt-4o-mini")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, azure
@azure.call("gpt-4o-mini")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, vertex
@vertex.call("gemini-1.5-flash")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, bedrock
@bedrock.call("anthropic.claude-3-haiku-20240307-v1:0")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, openai, prompt_template
@openai.call("gpt-4o-mini")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, anthropic, prompt_template
@anthropic.call("claude-3-5-sonnet-20240620")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, mistral, prompt_template
@mistral.call("mistral-large-latest")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, gemini, prompt_template
@gemini.call("gemini-1.5-flash")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, groq, prompt_template
@groq.call("llama-3.1-70b-versatile")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, cohere, prompt_template
@cohere.call("command-r-plus")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, litellm, prompt_template
@litellm.call("gpt-4o-mini")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, azure, prompt_template
@azure.call("gpt-4o-mini")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, prompt_template, vertex
@vertex.call("gemini-1.5-flash")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, bedrock, prompt_template
@bedrock.call("anthropic.claude-3-haiku-20240307-v1:0")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, BaseMessageParam, openai
@openai.call("gpt-4o-mini")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, BaseMessageParam, anthropic
@anthropic.call("claude-3-5-sonnet-20240620")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, BaseMessageParam, mistral
@mistral.call("mistral-large-latest")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, BaseMessageParam, gemini
@gemini.call("gemini-1.5-flash")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, BaseMessageParam, groq
@groq.call("llama-3.1-70b-versatile")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, BaseMessageParam, cohere
@cohere.call("command-r-plus")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, BaseMessageParam, litellm
@litellm.call("gpt-4o-mini")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, BaseMessageParam, azure
@azure.call("gpt-4o-mini")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, BaseMessageParam, vertex
@vertex.call("gemini-1.5-flash")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, BaseMessageParam, bedrock
@bedrock.call("anthropic.claude-3-haiku-20240307-v1:0")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
Metadata¶
from mirascope.core import BaseDynamicConfig, Messages, openai
@openai.call("gpt-4o-mini")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, anthropic
@anthropic.call("claude-3-5-sonnet-20240620")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, mistral
@mistral.call("mistral-large-latest")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, gemini
@gemini.call("gemini-1.5-flash")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, groq
@groq.call("llama-3.1-70b-versatile")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, cohere
@cohere.call("command-r-plus")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, litellm
@litellm.call("gpt-4o-mini")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, azure
@azure.call("gpt-4o-mini")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, vertex
@vertex.call("gemini-1.5-flash")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, bedrock
@bedrock.call("anthropic.claude-3-haiku-20240307-v1:0")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, openai
@openai.call("gpt-4o-mini")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, anthropic
@anthropic.call("claude-3-5-sonnet-20240620")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, mistral
@mistral.call("mistral-large-latest")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, gemini
@gemini.call("gemini-1.5-flash")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, groq
@groq.call("llama-3.1-70b-versatile")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, cohere
@cohere.call("command-r-plus")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, litellm
@litellm.call("gpt-4o-mini")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, azure
@azure.call("gpt-4o-mini")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, vertex
@vertex.call("gemini-1.5-flash")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, Messages, bedrock
@bedrock.call("anthropic.claude-3-haiku-20240307-v1:0")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, openai, prompt_template
@openai.call("gpt-4o-mini")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, anthropic, prompt_template
@anthropic.call("claude-3-5-sonnet-20240620")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, mistral, prompt_template
@mistral.call("mistral-large-latest")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, gemini, prompt_template
@gemini.call("gemini-1.5-flash")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, groq, prompt_template
@groq.call("llama-3.1-70b-versatile")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, cohere, prompt_template
@cohere.call("command-r-plus")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, litellm, prompt_template
@litellm.call("gpt-4o-mini")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, azure, prompt_template
@azure.call("gpt-4o-mini")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, prompt_template, vertex
@vertex.call("gemini-1.5-flash")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, bedrock, prompt_template
@bedrock.call("anthropic.claude-3-haiku-20240307-v1:0")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, BaseMessageParam, openai
@openai.call("gpt-4o-mini")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, BaseMessageParam, anthropic
@anthropic.call("claude-3-5-sonnet-20240620")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, BaseMessageParam, mistral
@mistral.call("mistral-large-latest")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, BaseMessageParam, gemini
@gemini.call("gemini-1.5-flash")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, BaseMessageParam, groq
@groq.call("llama-3.1-70b-versatile")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, BaseMessageParam, cohere
@cohere.call("command-r-plus")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, BaseMessageParam, litellm
@litellm.call("gpt-4o-mini")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, BaseMessageParam, azure
@azure.call("gpt-4o-mini")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, BaseMessageParam, vertex
@vertex.call("gemini-1.5-flash")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import BaseDynamicConfig, BaseMessageParam, bedrock
@bedrock.call("anthropic.claude-3-haiku-20240307-v1:0")
def recommend_book(genre: str) -> BaseDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"call_params": {"max_tokens": 512},
"metadata": {"tags": {"version:0001"}},
}
response = recommend_book("fantasy")
print(response.content)
Custom Messages¶
You can also always return the original message types for any provider. To do so, simply return the provider-specific dynamic config:
from mirascope.core import mistral
from mistralai.models.chat_completion import ChatMessage
@mistral.call("mistral-large-latest")
def recommend_book(genre: str) -> mistral.MistralDynamicConfig:
return {"messages": [ChatMessage(role="user", content=f"Recommend a {genre} book")]}
response = recommend_book("fantasy")
print(response.content)
from cohere.types.chat_message import ChatMessage
from mirascope.core import cohere
@cohere.call("command-r-plus")
def recommend_book(genre: str) -> cohere.CohereDynamicConfig:
return {"messages": [ChatMessage(role="user", message=f"Recommend a {genre} book")]} # pyright: ignore [reportCallIssue, reportReturnType]
response = recommend_book("fantasy")
print(response.content)
from azure.ai.inference.models import UserMessage
from mirascope.core import azure
@azure.call("gpt-4o-mini")
def recommend_book(genre: str) -> azure.AzureDynamicConfig:
return {"messages": [UserMessage(content=f"Recommend a {genre} book")]}
response = recommend_book("fantasy")
print(response.content)
from mirascope.core import vertex
from vertexai.generative_models import Content, Part
@vertex.call("gemini-1.5-flash")
def recommend_book(genre: str) -> vertex.VertexDynamicConfig:
return {
"messages": [
Content(role="user", parts=[Part.from_text(f"Recommend a {genre} book")])
]
}
response = recommend_book("fantasy")
print(response.content)
Custom Client¶
Mirascope allows you to use custom clients when making calls to LLM providers. This feature is particularly useful when you need to use specific client configurations, handle authentication in a custom way, or work with self-hosted models.
Decorator Parameter:
You can pass a client to the call decorator using the client parameter:
from azure.ai.inference import ChatCompletionsClient
from azure.core.credentials import AzureKeyCredential
from mirascope.core import azure
@azure.call(
"gpt-4o-mini",
client=ChatCompletionsClient(
endpoint="your-endpoint", credential=AzureKeyCredential("your-credentials")
),
)
def recommend_book(genre: str) -> str:
return f"Recommend a {genre} book"
from azure.ai.inference import ChatCompletionsClient
from azure.core.credentials import AzureKeyCredential
from mirascope.core import Messages, azure
@azure.call(
"gpt-4o-mini",
client=ChatCompletionsClient(
endpoint="your-endpoint", credential=AzureKeyCredential("your-credentials")
),
)
def recommend_book(genre: str) -> Messages.Type:
return Messages.User(f"Recommend a {genre} book")
from azure.ai.inference import ChatCompletionsClient
from azure.core.credentials import AzureKeyCredential
from mirascope.core import azure, prompt_template
@azure.call(
"gpt-4o-mini",
client=ChatCompletionsClient(
endpoint="your-endpoint", credential=AzureKeyCredential("your-credentials")
),
)
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str): ...
from google.generativeai import GenerativeModel
from mirascope.core import BaseMessageParam, gemini
@gemini.call("", client=GenerativeModel(model_name="gemini-1.5-flash"))
def recommend_book(genre: str) -> list[BaseMessageParam]:
return [BaseMessageParam(role="user", content=f"Recommend a {genre} book")]
from azure.ai.inference import ChatCompletionsClient
from azure.core.credentials import AzureKeyCredential
from mirascope.core import BaseMessageParam, azure
@azure.call(
"gpt-4o-mini",
client=ChatCompletionsClient(
endpoint="your-endpoint", credential=AzureKeyCredential("your-credentials")
),
)
def recommend_book(genre: str) -> list[BaseMessageParam]:
return [BaseMessageParam(role="user", content=f"Recommend a {genre} book")]
from mirascope.core import BaseMessageParam, vertex
from vertexai.generative_models import GenerativeModel
@vertex.call("", client=GenerativeModel(model_name="gemini-1.5-flash"))
def recommend_book(genre: str) -> list[BaseMessageParam]:
return [BaseMessageParam(role="user", content=f"Recommend a {genre} book")]
Dynamic Configuration:
You can also configure the client dynamically at runtime through the dynamic configuration:
from azure.ai.inference import ChatCompletionsClient
from azure.core.credentials import AzureKeyCredential
from mirascope.core import azure, Messages
@azure.call("gpt-4o-mini")
def recommend_book(genre: str) -> azure.AzureDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"client": ChatCompletionsClient(
endpoint="your-endpoint", credential=AzureKeyCredential("your-credentials")
),
}
from mirascope.core import vertex, Messages
from vertexai.generative_models import GenerativeModel
@vertex.call("")
def recommend_book(genre: str) -> vertex.VertexDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"client": GenerativeModel(model_name="gemini-1.5-flash"),
}
from azure.ai.inference import ChatCompletionsClient
from azure.core.credentials import AzureKeyCredential
from mirascope.core import Messages, azure
@azure.call("gpt-4o-mini")
def recommend_book(genre: str) -> azure.AzureDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"client": ChatCompletionsClient(
endpoint="your-endpoint", credential=AzureKeyCredential("your-credentials")
),
}
from mirascope.core import Messages, vertex
from vertexai.generative_models import GenerativeModel
@vertex.call("")
def recommend_book(genre: str) -> vertex.VertexDynamicConfig:
return {
"messages": [Messages.User(f"Recommend a {genre} book")],
"client": GenerativeModel(model_name="gemini-1.5-flash"),
}
from azure.ai.inference import ChatCompletionsClient
from azure.core.credentials import AzureKeyCredential
from mirascope.core import azure, prompt_template
@azure.call("gpt-4o-mini")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str) -> azure.AzureDynamicConfig:
return {
"client": ChatCompletionsClient(
endpoint="your-endpoint", credential=AzureKeyCredential("your-credentials")
),
}
from anthropic import Anthropic
from mirascope.core import BaseMessageParam, anthropic
@anthropic.call("claude-3-5-sonnet-20240620")
def recommend_book(genre: str) -> anthropic.AnthropicDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"client": Anthropic(),
}
from mirascope.core import BaseMessageParam, mistral
from mistralai.client import MistralClient
@mistral.call("mistral-large-latest")
def recommend_book(genre: str) -> mistral.MistralDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"client": MistralClient(),
}
from google.generativeai import GenerativeModel
from mirascope.core import BaseMessageParam, gemini
@gemini.call("")
def recommend_book(genre: str) -> gemini.GeminiDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"client": GenerativeModel(model_name="gemini-1.5-flash"),
}
from azure.ai.inference import ChatCompletionsClient
from azure.core.credentials import AzureKeyCredential
from mirascope.core import BaseMessageParam, azure
@azure.call("gpt-4o-mini")
def recommend_book(genre: str) -> azure.AzureDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"client": ChatCompletionsClient(
endpoint="your-endpoint", credential=AzureKeyCredential("your-credentials")
),
}
from mirascope.core import BaseMessageParam, vertex
from vertexai.generative_models import GenerativeModel
@vertex.call("")
def recommend_book(genre: str) -> vertex.VertexDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"client": GenerativeModel(model_name="gemini-1.5-flash"),
}
from mirascope.core import BaseMessageParam, bedrock
import boto3
@bedrock.call("anthropic.claude-3-haiku-20240307-v1:0")
def recommend_book(genre: str) -> bedrock.BedrockDynamicConfig:
return {
"messages": [
BaseMessageParam(role="user", content=f"Recommend a {genre} book")
],
"client": boto3.client("bedrock-runtime"),
}
Make sure to use the correct client!
A common mistake is to use the synchronous client with async calls. Read the section on Async Custom Client to see how to use a custom client with asynchronous calls.
Error Handling¶
When making LLM calls, it's important to handle potential errors. Mirascope preserves the original error messages from providers, allowing you to catch and handle them appropriately:
from anthropic import AnthropicError
from mirascope.core import anthropic
@anthropic.call("claude-3-5-sonnet-20240620")
def recommend_book(genre: str) -> str:
return f"Recommend a {genre} book"
try:
response = recommend_book("fantasy")
print(response.content)
except AnthropicError as e:
print(f"Error: {str(e)}")
from mirascope.core import mistral
from mistralai import models
@mistral.call("mistral-large-latest")
def recommend_book(genre: str) -> str:
return f"Recommend a {genre} book"
try:
response = recommend_book("fantasy")
print(response.content)
except models.HTTPValidationError as e: # pyright: ignore [reportAttributeAccessIssue]
# handle e.data: models.HTTPValidationErrorData
raise (e)
except models.SDKError as e: # pyright: ignore [reportAttributeAccessIssue]
# handle exception
raise (e)
from cohere.errors import BadRequestError
from mirascope.core import cohere
@cohere.call(model="command-r-plus")
def recommend_book(genre: str) -> str:
return f"Recommend a {genre} book"
try:
response = recommend_book("fantasy")
print(response.content)
except BadRequestError as e:
print(f"Error: {str(e)}")
from litellm.exceptions import BadRequestError
from mirascope.core import litellm
@litellm.call(model="gpt-4o-mini")
def recommend_book(genre: str) -> str:
return f"Recommend a {genre} book"
try:
response = recommend_book("fantasy")
print(response.content)
except BadRequestError as e:
print(f"Error: {str(e)}")
from mirascope.core import bedrock
from botocore.exceptions import ClientError
@bedrock.call(model="anthropic.claude-3-haiku-20240307-v1:0")
def recommend_book(genre: str) -> str:
return f"Recommend a {genre} book"
try:
response = recommend_book("fantasy")
print(response.content)
except ClientError as e:
print(f"Error: {str(e)}")
from mirascope.core import Messages, openai
from openai import OpenAIError
@openai.call("gpt-4o-mini")
def recommend_book(genre: str) -> Messages.Type:
return Messages.User(f"Recommend a {genre} book")
try:
response = recommend_book("fantasy")
print(response.content)
except OpenAIError as e:
print(f"Error: {str(e)}")
from anthropic import AnthropicError
from mirascope.core import Messages, anthropic
@anthropic.call("claude-3-5-sonnet-20240620")
def recommend_book(genre: str) -> Messages.Type:
return Messages.User(f"Recommend a {genre} book")
try:
response = recommend_book("fantasy")
print(response.content)
except AnthropicError as e:
print(f"Error: {str(e)}")
from mirascope.core import Messages, mistral
from mistralai import models
@mistral.call("mistral-large-latest")
def recommend_book(genre: str) -> Messages.Type:
return Messages.User(f"Recommend a {genre} book")
try:
response = recommend_book("fantasy")
print(response.content)
except models.HTTPValidationError as e: # pyright: ignore [reportAttributeAccessIssue]
# handle e.data: models.HTTPValidationErrorData
raise (e)
except models.SDKError as e: # pyright: ignore [reportAttributeAccessIssue]
# handle exception
raise (e)
from groq import GroqError
from mirascope.core import Messages, groq
@groq.call("llama-3.1-70b-versatile")
def recommend_book(genre: str) -> Messages.Type:
return Messages.User(f"Recommend a {genre} book")
try:
response = recommend_book("fantasy")
print(response.content)
except GroqError as e:
print(f"Error: {str(e)}")
from cohere.errors import BadRequestError
from mirascope.core import Messages, cohere
@cohere.call("command-r-plus")
def recommend_book(genre: str) -> Messages.Type:
return Messages.User(f"Recommend a {genre} book")
try:
response = recommend_book("fantasy")
print(response.content)
except BadRequestError as e:
print(f"Error: {str(e)}")
from litellm.exceptions import BadRequestError
from mirascope.core import Messages, litellm
@litellm.call("gpt-4o-mini")
def recommend_book(genre: str) -> Messages.Type:
return Messages.User(f"Recommend a {genre} book")
try:
response = recommend_book("fantasy")
print(response.content)
except BadRequestError as e:
print(f"Error: {str(e)}")
from mirascope.core import Messages, bedrock
from botocore.exceptions import ClientError
@bedrock.call("anthropic.claude-3-haiku-20240307-v1:0")
def recommend_book(genre: str) -> Messages.Type:
return Messages.User(f"Recommend a {genre} book")
try:
response = recommend_book("fantasy")
print(response.content)
except ClientError as e:
print(f"Error: {str(e)}")
from mirascope.core import openai, prompt_template
from openai import OpenAIError
@openai.call("gpt-4o-mini")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str): ...
try:
response = recommend_book("fantasy")
print(response.content)
except OpenAIError as e:
print(f"Error: {str(e)}")
from anthropic import AnthropicError
from mirascope.core import anthropic, prompt_template
@anthropic.call("claude-3-5-sonnet-20240620")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str): ...
try:
response = recommend_book("fantasy")
print(response.content)
except AnthropicError as e:
print(f"Error: {str(e)}")
from mirascope.core import mistral, prompt_template
from mistralai import models
@mistral.call("mistral-large-latest")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str): ...
try:
response = recommend_book("fantasy")
print(response.content)
except models.HTTPValidationError as e: # pyright: ignore [reportAttributeAccessIssue]
# handle e.data: models.HTTPValidationErrorData
raise (e)
except models.SDKError as e: # pyright: ignore [reportAttributeAccessIssue]
# handle exception
raise (e)
from groq import GroqError
from mirascope.core import groq, prompt_template
@groq.call("llama-3.1-70b-versatile")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str): ...
try:
response = recommend_book("fantasy")
print(response.content)
except GroqError as e:
print(f"Error: {str(e)}")
from cohere.errors import BadRequestError
from mirascope.core import cohere, prompt_template
@cohere.call("command-r-plus")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str): ...
try:
response = recommend_book("fantasy")
print(response.content)
except BadRequestError as e:
print(f"Error: {str(e)}")
from litellm.exceptions import BadRequestError
from mirascope.core import litellm, prompt_template
@litellm.call("gpt-4o-mini")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str): ...
try:
response = recommend_book("fantasy")
print(response.content)
except BadRequestError as e:
print(f"Error: {str(e)}")
from mirascope.core import bedrock, prompt_template
from botocore.exceptions import ClientError
@bedrock.call("anthropic.claude-3-haiku-20240307-v1:0")
@prompt_template("Recommend a {genre} book")
def recommend_book(genre: str): ...
try:
response = recommend_book("fantasy")
print(response.content)
except ClientError as e:
print(f"Error: {str(e)}")
from mirascope.core import BaseMessageParam, openai
from openai import OpenAIError
@openai.call("gpt-4o-mini")
def recommend_book(genre: str) -> list[BaseMessageParam]:
return [BaseMessageParam(role="user", content=f"Recommend a {genre} book")]
try:
response = recommend_book("fantasy")
print(response.content)
except OpenAIError as e:
print(f"Error: {str(e)}")
from anthropic import AnthropicError
from mirascope.core import BaseMessageParam, anthropic
@anthropic.call("claude-3-5-sonnet-20240620")
def recommend_book(genre: str) -> list[BaseMessageParam]:
return [BaseMessageParam(role="user", content=f"Recommend a {genre} book")]
try:
response = recommend_book("fantasy")
print(response.content)
except AnthropicError as e:
print(f"Error: {str(e)}")
from mirascope.core import BaseMessageParam, mistral
from mistralai import models
@mistral.call("mistral-large-latest")
def recommend_book(genre: str) -> list[BaseMessageParam]:
return [BaseMessageParam(role="user", content=f"Recommend a {genre} book")]
try:
response = recommend_book("fantasy")
print(response.content)
except models.HTTPValidationError as e: # pyright: ignore [reportAttributeAccessIssue]
# handle e.data: models.HTTPValidationErrorData
raise (e)
except models.SDKError as e: # pyright: ignore [reportAttributeAccessIssue]
# handle exception
raise (e)
from mirascope.core import BaseMessageParam, gemini
@gemini.call("gemini-1.5-flash")
def recommend_book(genre: str) -> list[BaseMessageParam]:
return [BaseMessageParam(role="user", content=f"Recommend a {genre} book")]
try:
response = recommend_book("fantasy")
print(response.content)
except Exception as e:
print(f"Error: {str(e)}")
from groq import GroqError
from mirascope.core import BaseMessageParam, groq
@groq.call("llama-3.1-70b-versatile")
def recommend_book(genre: str) -> list[BaseMessageParam]:
return [BaseMessageParam(role="user", content=f"Recommend a {genre} book")]
try:
response = recommend_book("fantasy")
print(response.content)
except GroqError as e:
print(f"Error: {str(e)}")
from cohere.errors import BadRequestError
from mirascope.core import BaseMessageParam, cohere
@cohere.call("command-r-plus")
def recommend_book(genre: str) -> list[BaseMessageParam]:
return [BaseMessageParam(role="user", content=f"Recommend a {genre} book")]
try:
response = recommend_book("fantasy")
print(response.content)
except BadRequestError as e:
print(f"Error: {str(e)}")
from litellm.exceptions import BadRequestError
from mirascope.core import BaseMessageParam, litellm
@litellm.call("gpt-4o-mini")
def recommend_book(genre: str) -> list[BaseMessageParam]:
return [BaseMessageParam(role="user", content=f"Recommend a {genre} book")]
try:
response = recommend_book("fantasy")
print(response.content)
except BadRequestError as e:
print(f"Error: {str(e)}")
from mirascope.core import BaseMessageParam, azure
@azure.call("gpt-4o-mini")
def recommend_book(genre: str) -> list[BaseMessageParam]:
return [BaseMessageParam(role="user", content=f"Recommend a {genre} book")]
try:
response = recommend_book("fantasy")
print(response.content)
except Exception as e:
print(f"Error: {str(e)}")
from mirascope.core import BaseMessageParam, vertex
@vertex.call("gemini-1.5-flash")
def recommend_book(genre: str) -> list[BaseMessageParam]:
return [BaseMessageParam(role="user", content=f"Recommend a {genre} book")]
try:
response = recommend_book("fantasy")
print(response.content)
except Exception as e:
print(f"Error: {str(e)}")
from mirascope.core import BaseMessageParam, bedrock
from botocore.exceptions import ClientError
@bedrock.call("anthropic.claude-3-haiku-20240307-v1:0")
def recommend_book(genre: str) -> list[BaseMessageParam]:
return [BaseMessageParam(role="user", content=f"Recommend a {genre} book")]
try:
response = recommend_book("fantasy")
print(response.content)
except ClientError as e:
print(f"Error: {str(e)}")
By catching provider-specific errors, you can implement appropriate error handling and fallback strategies in your application. You can of course always catch the base Exception instead of provider-specific exceptions (which we needed to do in some of our examples due to not being able to find the right exceptions to catch for those providers...).
Next Steps¶
By mastering calls in Mirascope, you'll be well-equipped to build robust, flexible, and reusable LLM applications.
Next, we recommend choosing one of:
- Streams to see how to stream call responses for a more real-time interaction.
- Chaining to see how to chain calls together.
- Response Models to see how to generate structured outputs.
- Tools to see how to give LLMs access to custom tools to extend their capabilities.
- Async to see how to better take advantage of asynchronous programming and parallelization for improved performance.
Pick whichever path aligns best with what you're hoping to get from Mirascope.