ChatOllama integration

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

pip install -qU langchain-ollama

from langchain_ollama import ChatOllama

llm = ChatOllama(
    model="llama3.1",
    temperature=0,
    # other params...
)

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

AIMessage(content='The translation of "I love programming" in French is:\n\n"J\'adore la programmation."', additional_kwargs={}, response_metadata={'model': 'llama3.1', 'created_at': '2025-06-25T18:43:00.483666Z', 'done': True, 'done_reason': 'stop', 'total_duration': 619971208, 'load_duration': 27793125, 'prompt_eval_count': 35, 'prompt_eval_duration': 36354583, 'eval_count': 22, 'eval_duration': 555182667, 'model_name': 'llama3.1'}, id='run--348bb5ef-9dd9-4271-bc7e-a9ddb54c28c1-0', usage_metadata={'input_tokens': 35, 'output_tokens': 22, 'total_tokens': 57})

print(ai_msg.content)

The translation of "I love programming" in French is:

"J'adore le programmation."

ollama pull gpt-oss:20b

from typing import List

from langchain.messages import AIMessage
from langchain.tools import tool
from langchain_ollama import ChatOllama


@tool
def validate_user(user_id: int, addresses: List[str]) -> bool:
    """Validate user using historical addresses.

    Args:
        user_id (int): the user ID.
        addresses (List[str]): Previous addresses as a list of strings.
    """
    return True


llm = ChatOllama(
    model="gpt-oss:20b",
    validate_model_on_init=True,
    temperature=0,
).bind_tools([validate_user])

result = llm.invoke(
    "Could you validate user 123? They previously lived at "
    "123 Fake St in Boston MA and 234 Pretend Boulevard in "
    "Houston TX."
)

if isinstance(result, AIMessage) and result.tool_calls:
    print(result.tool_calls)

[{'name': 'validate_user', 'args': {'addresses': ['123 Fake St, Boston, MA', '234 Pretend Boulevard, Houston, TX'], 'user_id': '123'}, 'id': 'aef33a32-a34b-4b37-b054-e0d85584772f', 'type': 'tool_call'}]

pip install pillow

import base64
from io import BytesIO

from IPython.display import HTML, display
from PIL import Image


def convert_to_base64(pil_image):
    """
    Convert PIL images to Base64 encoded strings

    :param pil_image: PIL image
    :return: Re-sized Base64 string
    """

    buffered = BytesIO()
    pil_image.save(buffered, format="JPEG")  # You can change the format if needed
    img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
    return img_str


def plt_img_base64(img_base64):
    """
    Display base64 encoded string as image

    :param img_base64:  Base64 string
    """
    # Create an HTML img tag with the base64 string as the source
    image_html = f'<img src="data:image/jpeg;base64,{img_base64}" />'
    # Display the image by rendering the HTML
    display(HTML(image_html))


file_path = "../../../static/img/ollama_example_img.jpg"
pil_image = Image.open(file_path)

image_b64 = convert_to_base64(pil_image)
plt_img_base64(image_b64)

<img src="data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAgGBgcGBQgHBwcJ..." />

from langchain.messages import HumanMessage
from langchain_ollama import ChatOllama

llm = ChatOllama(model="bakllava", temperature=0)


def prompt_func(data):
    text = data["text"]
    image = data["image"]

    image_part = {
        "type": "image_url",
        "image_url": f"data:image/jpeg;base64,{image}",
    }

    content_parts = []

    text_part = {"type": "text", "text": text}

    content_parts.append(image_part)
    content_parts.append(text_part)

    return [HumanMessage(content=content_parts)]


from langchain_core.output_parsers import StrOutputParser

chain = prompt_func | llm | StrOutputParser()

query_chain = chain.invoke(
    {"text": "What is the Dollar-based gross retention rate?", "image": image_b64}
)

print(query_chain)

90%

from langchain_ollama import ChatOllama

llm = ChatOllama(model="llama3.1", logprobs=True)

response = llm.invoke("What color is the sky?")
logprobs = response.response_metadata["logprobs"]
for entry in logprobs[:5]:
    print(f"Token: {entry['token']!r:>15}  logprob: {entry['logprob']:.4f}")

Token:           'The'  logprob: -0.1094
Token:       ' answer'  logprob: -1.7309
Token:             ','  logprob: -1.5854
Token:           ' of'  logprob: -0.4066
Token:       ' course'  logprob: -0.0000

llm = ChatOllama(model="llama3.1", logprobs=True, top_logprobs=3)

response = llm.invoke("The capital of France is")
logprobs = response.response_metadata["logprobs"]
for entry in logprobs[:3]:
    print(f"Chosen: {entry['token']!r}")
    if entry.get("top_logprobs"):
        for alt in entry["top_logprobs"]:
            print(f"    {alt['token']!r:>12}  logprob: {alt['logprob']:.4f}")

Chosen: 'Paris'
         'Paris'  logprob: -0.5567
           'The'  logprob: -0.9152
            '**'  logprob: -4.0410
Chosen: '.'
             '.'  logprob: -0.3831
    '<|eot_id|>'  logprob: -1.5511
             '!'  logprob: -2.3379

from langchain.messages import HumanMessage
from langchain_core.messages import ChatMessage
from langchain_ollama import ChatOllama

llm = ChatOllama(model="granite3.2:8b")

messages = [
    ChatMessage(role="control", content="thinking"),
    HumanMessage("What is 3^3?"),
]

response = llm.invoke(messages)
print(response.content)

Here is my thought process:
The user is asking for the value of 3 raised to the power of 3, which is a basic exponentiation operation.

Here is my response:

3^3 (read as "3 to the power of 3") equals 27.

This calculation is performed by multiplying 3 by itself three times: 3*3*3 = 27.