AzureChatOpenAI

Setup:

Head to the Azure OpenAI quickstart guide to create your Azure OpenAI deployment.

Then install langchain-openai and set environment variables AZURE_OPENAI_API_KEY and AZURE_OPENAI_ENDPOINT:

pip install -U langchain-openai

export AZURE_OPENAI_API_KEY="your-api-key"
export AZURE_OPENAI_ENDPOINT="https://your-endpoint.openai.azure.com/"

Key init args — completion params: azure_deployment: Name of Azure OpenAI deployment to use. temperature: Sampling temperature. max_tokens: Max number of tokens to generate. logprobs: Whether to return logprobs.

Key init args — client params: api_version: Azure OpenAI REST API version to use (distinct from the version of the underlying model). See more on the different versions. timeout: Timeout for requests. max_retries: Max number of retries. organization: OpenAI organization ID. If not passed in will be read from env var OPENAI_ORG_ID. model: The name of the underlying OpenAI model. Used for tracing and token counting. Does not affect completion. E.g. 'gpt-4', 'gpt-35-turbo', etc. model_version: The version of the underlying OpenAI model. Used for tracing and token counting. Does not affect completion. E.g., '0125', '0125-preview', etc.

See full list of supported init args and their descriptions in the params section.

Instantiate:

from langchain_openai import AzureChatOpenAI

model = AzureChatOpenAI(
    azure_deployment="your-deployment",
    api_version="2024-05-01-preview",
    temperature=0,
    max_tokens=None,
    timeout=None,
    max_retries=2,
    # organization="...",
    # model="gpt-35-turbo",
    # model_version="0125",
    # other params...
)

Any param which is not explicitly supported will be passed directly to the openai.AzureOpenAI.chat.completions.create(...) API every time to the model is invoked.

For example:

from langchain_openai import AzureChatOpenAI
import openai

AzureChatOpenAI(..., logprobs=True).invoke(...)

# results in underlying API call of:

openai.AzureOpenAI(..).chat.completions.create(..., logprobs=True)

# which is also equivalent to:

AzureChatOpenAI(...).invoke(..., logprobs=True)

Invoke:

messages = [
    (
        "system",
        "You are a helpful translator. Translate the user sentence to French.",
    ),
    ("human", "I love programming."),
]
model.invoke(messages)

AIMessage(
    content="J'adore programmer.",
    usage_metadata={
        "input_tokens": 28,
        "output_tokens": 6,
        "total_tokens": 34,
    },
    response_metadata={
        "token_usage": {
            "completion_tokens": 6,
            "prompt_tokens": 28,
            "total_tokens": 34,
        },
        "model_name": "gpt-4",
        "system_fingerprint": "fp_7ec89fabc6",
        "prompt_filter_results": [
            {
                "prompt_index": 0,
                "content_filter_results": {
                    "hate": {"filtered": False, "severity": "safe"},
                    "self_harm": {"filtered": False, "severity": "safe"},
                    "sexual": {"filtered": False, "severity": "safe"},
                    "violence": {"filtered": False, "severity": "safe"},
                },
            }
        ],
        "finish_reason": "stop",
        "logprobs": None,
        "content_filter_results": {
            "hate": {"filtered": False, "severity": "safe"},
            "self_harm": {"filtered": False, "severity": "safe"},
            "sexual": {"filtered": False, "severity": "safe"},
            "violence": {"filtered": False, "severity": "safe"},
        },
    },
    id="run-6d7a5282-0de0-4f27-9cc0-82a9db9a3ce9-0",
)

Stream:

for chunk in model.stream(messages):
    print(chunk.text, end="")

AIMessageChunk(content="", id="run-a6f294d3-0700-4f6a-abc2-c6ef1178c37f")
AIMessageChunk(content="J", id="run-a6f294d3-0700-4f6a-abc2-c6ef1178c37f")
AIMessageChunk(content="'", id="run-a6f294d3-0700-4f6a-abc2-c6ef1178c37f")
AIMessageChunk(content="ad", id="run-a6f294d3-0700-4f6a-abc2-c6ef1178c37f")
AIMessageChunk(content="ore", id="run-a6f294d3-0700-4f6a-abc2-c6ef1178c37f")
AIMessageChunk(content=" la", id="run-a6f294d3-0700-4f6a-abc2-c6ef1178c37f")
AIMessageChunk(
    content=" programm", id="run-a6f294d3-0700-4f6a-abc2-c6ef1178c37f"
)
AIMessageChunk(content="ation", id="run-a6f294d3-0700-4f6a-abc2-c6ef1178c37f")
AIMessageChunk(content=".", id="run-a6f294d3-0700-4f6a-abc2-c6ef1178c37f")
AIMessageChunk(
    content="",
    response_metadata={
        "finish_reason": "stop",
        "model_name": "gpt-4",
        "system_fingerprint": "fp_811936bd4f",
    },
    id="run-a6f294d3-0700-4f6a-abc2-c6ef1178c37f",
)

stream = model.stream(messages)
full = next(stream)
for chunk in stream:
    full += chunk
full

AIMessageChunk(
    content="J'adore la programmation.",
    response_metadata={
        "finish_reason": "stop",
        "model_name": "gpt-4",
        "system_fingerprint": "fp_811936bd4f",
    },
    id="run-ba60e41c-9258-44b8-8f3a-2f10599643b3",
)

Async:

await model.ainvoke(messages)

# stream:
# async for chunk in (await model.astream(messages))

# batch:
# await model.abatch([messages])

Tool calling:

from pydantic import BaseModel, Field

class GetWeather(BaseModel):
    '''Get the current weather in a given location'''

    location: str = Field(
        ..., description="The city and state, e.g. San Francisco, CA"
    )

class GetPopulation(BaseModel):
    '''Get the current population in a given location'''

    location: str = Field(
        ..., description="The city and state, e.g. San Francisco, CA"
    )

model_with_tools = model.bind_tools([GetWeather, GetPopulation])
ai_msg = model_with_tools.invoke(
    "Which city is hotter today and which is bigger: LA or NY?"
)
ai_msg.tool_calls

[
    {
        "name": "GetWeather",
        "args": {"location": "Los Angeles, CA"},
        "id": "call_6XswGD5Pqk8Tt5atYr7tfenU",
    },
    {
        "name": "GetWeather",
        "args": {"location": "New York, NY"},
        "id": "call_ZVL15vA8Y7kXqOy3dtmQgeCi",
    },
    {
        "name": "GetPopulation",
        "args": {"location": "Los Angeles, CA"},
        "id": "call_49CFW8zqC9W7mh7hbMLSIrXw",
    },
    {
        "name": "GetPopulation",
        "args": {"location": "New York, NY"},
        "id": "call_6ghfKxV264jEfe1mRIkS3PE7",
    },
]

Structured output:

from typing import Optional

from pydantic import BaseModel, Field

class Joke(BaseModel):
    '''Joke to tell user.'''

    setup: str = Field(description="The setup of the joke")
    punchline: str = Field(description="The punchline to the joke")
    rating: int | None = Field(
        description="How funny the joke is, from 1 to 10"
    )

structured_model = model.with_structured_output(Joke)
structured_model.invoke("Tell me a joke about cats")

Joke(
    setup="Why was the cat sitting on the computer?",
    punchline="To keep an eye on the mouse!",
    rating=None,
)

See AzureChatOpenAI.with_structured_output() for more.

JSON mode:

json_model = model.bind(response_format={"type": "json_object"})
ai_msg = json_model.invoke(
    "Return a JSON object with key 'random_ints' and a value of 10 random ints in [0-99]"
)
ai_msg.content

'\\n{\\n  "random_ints": [23, 87, 45, 12, 78, 34, 56, 90, 11, 67]\\n}'

Image input:

import base64
import httpx
from langchain_core.messages import HumanMessage

image_url = "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
image_data = base64.b64encode(httpx.get(image_url).content).decode("utf-8")
message = HumanMessage(
    content=[
        {"type": "text", "text": "describe the weather in this image"},
        {
            "type": "image_url",
            "image_url": {"url": f"data:image/jpeg;base64,{image_data}"},
        },
    ]
)
ai_msg = model.invoke([message])
ai_msg.content

"The weather in the image appears to be quite pleasant. The sky is mostly clear"

Token usage:

ai_msg = model.invoke(messages)
ai_msg.usage_metadata

{"input_tokens": 28, "output_tokens": 5, "total_tokens": 33}

Logprobs:

logprobs_model = model.bind(logprobs=True)
ai_msg = logprobs_model.invoke(messages)
ai_msg.response_metadata["logprobs"]

{
    "content": [
        {
            "token": "J",
            "bytes": [74],
            "logprob": -4.9617593e-06,
            "top_logprobs": [],
        },
        {
            "token": "'adore",
            "bytes": [39, 97, 100, 111, 114, 101],
            "logprob": -0.25202933,
            "top_logprobs": [],
        },
        {
            "token": " la",
            "bytes": [32, 108, 97],
            "logprob": -0.20141791,
            "top_logprobs": [],
        },
        {
            "token": " programmation",
            "bytes": [
                32,
                112,
                114,
                111,
                103,
                114,
                97,
                109,
                109,
                97,
                116,
                105,
                111,
                110,
            ],
            "logprob": -1.9361265e-07,
            "top_logprobs": [],
        },
        {
            "token": ".",
            "bytes": [46],
            "logprob": -1.2233183e-05,
            "top_logprobs": [],
        },
    ]
}

Response metadata

ai_msg = model.invoke(messages)
ai_msg.response_metadata

{
    "token_usage": {
        "completion_tokens": 6,
        "prompt_tokens": 28,
        "total_tokens": 34,
    },
    "model_name": "gpt-35-turbo",
    "system_fingerprint": None,
    "prompt_filter_results": [
        {
            "prompt_index": 0,
            "content_filter_results": {
                "hate": {"filtered": False, "severity": "safe"},
                "self_harm": {"filtered": False, "severity": "safe"},
                "sexual": {"filtered": False, "severity": "safe"},
                "violence": {"filtered": False, "severity": "safe"},
            },
        }
    ],
    "finish_reason": "stop",
    "logprobs": None,
    "content_filter_results": {
        "hate": {"filtered": False, "severity": "safe"},
        "self_harm": {"filtered": False, "severity": "safe"},
        "sexual": {"filtered": False, "severity": "safe"},
        "violence": {"filtered": False, "severity": "safe"},
    },
}