ChatNVIDIA

import getpass
import os

if not os.getenv("NVIDIA_API_KEY"):
    # Note: the API key should start with "nvapi-"
    os.environ["NVIDIA_API_KEY"] = getpass.getpass("Enter your NVIDIA API key: ")

os.environ["LANGSMITH_TRACING"] = "true"
os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")

pip install -qU langchain-nvidia-ai-endpoints

## Core LC Chat Interface
from langchain_nvidia_ai_endpoints import ChatNVIDIA

llm = ChatNVIDIA(model="mistralai/mixtral-8x7b-instruct-v0.1")

result = llm.invoke("Write a ballad about LangChain.")
print(result.content)

from langchain_nvidia_ai_endpoints import ChatNVIDIA

# connect to an embedding NIM running at localhost:8000, specifying a specific model
llm = ChatNVIDIA(base_url="http://localhost:8000/v1", model="meta/llama3-8b-instruct")

print(llm.batch(["What's 2*3?", "What's 2*6?"]))
# Or via the async API
# await llm.abatch(["What's 2*3?", "What's 2*6?"])

for chunk in llm.stream("How far can a seagull fly in one day?"):
    # Show the token separations
    print(chunk.content, end="|")

async for chunk in llm.astream(
    "How long does it take for monarch butterflies to migrate?"
):
    print(chunk.content, end="|")

ChatNVIDIA.get_available_models()
# llm.get_available_models()

from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_nvidia_ai_endpoints import ChatNVIDIA

prompt = ChatPromptTemplate.from_messages(
    [("system", "You are a helpful AI assistant named Fred."), ("user", "{input}")]
)
chain = prompt | ChatNVIDIA(model="meta/llama3-8b-instruct") | StrOutputParser()

for txt in chain.stream({"input": "What's your name?"}):
    print(txt, end="")

prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "You are an expert coding AI. Respond only in valid python; no narration whatsoever.",
        ),
        ("user", "{input}"),
    ]
)
chain = prompt | ChatNVIDIA(model="meta/codellama-70b") | StrOutputParser()

for txt in chain.stream({"input": "How do I solve this fizz buzz problem?"}):
    print(txt, end="")

import IPython
import requests

image_url = "https://www.nvidia.com/content/dam/en-zz/Solutions/research/ai-playground/[email protected]"  ## Large Image
image_content = requests.get(image_url).content

IPython.display.Image(image_content)

from langchain_nvidia_ai_endpoints import ChatNVIDIA

llm = ChatNVIDIA(model="nvidia/neva-22b")

from langchain.messages import HumanMessage

llm.invoke(
    [
        HumanMessage(
            content=[
                {"type": "text", "text": "Describe this image:"},
                {"type": "image_url", "image_url": {"url": image_url}},
            ]
        )
    ]
)

import IPython
import requests

image_url = "https://picsum.photos/seed/kitten/300/200"
image_content = requests.get(image_url).content

IPython.display.Image(image_content)

import base64

from langchain.messages import HumanMessage

## Works for simpler images. For larger images, see actual implementation
b64_string = base64.b64encode(image_content).decode("utf-8")

llm.invoke(
    [
        HumanMessage(
            content=[
                {"type": "text", "text": "Describe this image:"},
                {
                    "type": "image_url",
                    "image_url": {"url": f"data:image/png;base64,{b64_string}"},
                },
            ]
        )
    ]
)

base64_with_mime_type = f"data:image/png;base64,{b64_string}"
llm.invoke(f'What\'s in this image?\n<img src="{base64_with_mime_type}" />')

pip install -qU langchain

from langchain_core.chat_history import InMemoryChatMessageHistory
from langchain_core.runnables.history import RunnableWithMessageHistory

# store is a dictionary that maps session IDs to their corresponding chat histories.
store = {}  # memory is maintained outside the chain


# A function that returns the chat history for a given session ID.
def get_session_history(session_id: str) -> InMemoryChatMessageHistory:
    if session_id not in store:
        store[session_id] = InMemoryChatMessageHistory()
    return store[session_id]


chat = ChatNVIDIA(
    model="mistralai/mixtral-8x22b-instruct-v0.1",
    temperature=0.1,
    max_tokens=100,
    top_p=1.0,
)

#  Define a RunnableConfig object, with a `configurable` key. session_id determines thread
config = {"configurable": {"session_id": "1"}}

conversation = RunnableWithMessageHistory(
    chat,
    get_session_history,
)

conversation.invoke(
    "Hi I'm Srijan Dubey.",  # input or query
    config=config,
)

conversation.invoke(
    "I'm doing well! Just having a conversation with an AI.",
    config=config,
)

conversation.invoke(
    "Tell me about yourself.",
    config=config,
)

tool_models = [
    model for model in ChatNVIDIA.get_available_models() if model.supports_tools
]
tool_models

from langchain.tools import tool
from pydantic import Field


@tool
def get_current_weather(
    location: str = Field(..., description="The location to get the weather for."),
):
    """Get the current weather for a location."""
    ...


llm = ChatNVIDIA(model=tool_models[0].id).bind_tools(tools=[get_current_weather])
response = llm.invoke("What is the weather in Boston?")
response.tool_calls