ChatOCIModelDeployment

import ads

# Set authentication through ads
# Use resource principal are operating within a
# OCI service that has resource principal based
# authentication configured
ads.set_auth("resource_principal")

import os

# Set authentication through environment variables
# Use API Key setup when you are working from a local
# workstation or on platform which does not support
# resource principals.
os.environ["OCI_IAM_TYPE"] = "api_key"
os.environ["OCI_CONFIG_PROFILE"] = "default"
os.environ["OCI_CONFIG_LOCATION"] = "~/.oci"

pip install -qU langchain-community langchain-openai oracle-ads

from langchain_community.chat_models import ChatOCIModelDeployment

# Create an instance of OCI Model Deployment Endpoint
# Replace the endpoint uri with your own
# Using generic class as entry point, you will be able
# to pass model parameters through model_kwargs during
# instantiation.
chat = ChatOCIModelDeployment(
    endpoint="https://modeldeployment.<region>.oci.customer-oci.com/<ocid>/predict",
    streaming=True,
    max_retries=1,
    model_kwargs={
        "temperature": 0.2,
        "max_tokens": 512,
    },  # other model params...
    default_headers={
        "route": "/v1/chat/completions",
        # other request headers ...
    },
)

from langchain_community.chat_models import ChatOCIModelDeploymentVLLM

# Create an instance of OCI Model Deployment Endpoint
# Replace the endpoint uri with your own
# Using framework specific class as entry point, you will
# be able to pass model parameters in constructor.
chat = ChatOCIModelDeploymentVLLM(
    endpoint="https://modeldeployment.<region>.oci.customer-oci.com/<md_ocid>/predict",
)

messages = [
    (
        "system",
        "You are a helpful assistant that translates English to French. Translate the user sentence.",
    ),
    ("human", "I love programming."),
]

ai_msg = chat.invoke(messages)
ai_msg

AIMessage(content="J'adore programmer.", response_metadata={'token_usage': {'prompt_tokens': 44, 'total_tokens': 52, 'completion_tokens': 8}, 'model_name': 'odsc-llm', 'system_fingerprint': '', 'finish_reason': 'stop'}, id='run-ca145168-efa9-414c-9dd1-21d10766fdd3-0')

print(ai_msg.content)

J'adore programmer.

from langchain_core.prompts import ChatPromptTemplate

prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "You are a helpful assistant that translates {input_language} to {output_language}.",
        ),
        ("human", "{input}"),
    ]
)

chain = prompt | chat
chain.invoke(
    {
        "input_language": "English",
        "output_language": "German",
        "input": "I love programming.",
    }
)

AIMessage(content='Ich liebe Programmierung.', response_metadata={'token_usage': {'prompt_tokens': 38, 'total_tokens': 48, 'completion_tokens': 10}, 'model_name': 'odsc-llm', 'system_fingerprint': '', 'finish_reason': 'stop'}, id='run-5dd936b0-b97e-490e-9869-2ad3dd524234-0')

from langchain_community.chat_models import ChatOCIModelDeployment

system = "You are a helpful translator that translates {input_language} to {output_language}."
human = "{text}"
prompt = ChatPromptTemplate.from_messages([("system", system), ("human", human)])

chat = ChatOCIModelDeployment(
    endpoint="https://modeldeployment.us-ashburn-1.oci.customer-oci.com/<ocid>/predict"
)
chain = prompt | chat

await chain.ainvoke(
    {
        "input_language": "English",
        "output_language": "Chinese",
        "text": "I love programming",
    }
)

AIMessage(content='我喜欢编程', response_metadata={'token_usage': {'prompt_tokens': 37, 'total_tokens': 50, 'completion_tokens': 13}, 'model_name': 'odsc-llm', 'system_fingerprint': '', 'finish_reason': 'stop'}, id='run-a2dc9393-f269-41a4-b908-b1d8a92cf827-0')

import os
import sys

from langchain_community.chat_models import ChatOCIModelDeployment
from langchain_core.prompts import ChatPromptTemplate

prompt = ChatPromptTemplate.from_messages(
    [("human", "List out the 5 states in the United State.")]
)

chat = ChatOCIModelDeployment(
    endpoint="https://modeldeployment.us-ashburn-1.oci.customer-oci.com/<ocid>/predict"
)

chain = prompt | chat

for chunk in chain.stream({}):
    sys.stdout.write(chunk.content)
    sys.stdout.flush()

1. California
2. Texas
3. Florida
4. New York
5. Illinois

from langchain_community.chat_models import ChatOCIModelDeployment
from pydantic import BaseModel


class Joke(BaseModel):
    """A setup to a joke and the punchline."""

    setup: str
    punchline: str


chat = ChatOCIModelDeployment(
    endpoint="https://modeldeployment.us-ashburn-1.oci.customer-oci.com/<ocid>/predict",
)
structured_llm = chat.with_structured_output(Joke, method="json_mode")
output = structured_llm.invoke(
    "Tell me a joke about cats, respond in JSON with `setup` and `punchline` keys"
)

output.dict()

{'setup': 'Why did the cat get stuck in the tree?',
 'punchline': 'Because it was chasing its tail!'}