Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://python.langchain.com/docs/integrations/llms/outlines below:

Outlines | 🦜️🔗 LangChain

This will help you get started with Outlines LLM. For detailed documentation of all Outlines features and configurations head to the API reference.

Outlines is a library for constrained language generation. It allows you to use large language models (LLMs) with various backends while applying constraints to the generated output.

To access Outlines models you'll need to have an internet connection to download the model weights from huggingface. Depending on the backend you need to install the required dependencies (see Outlines docs)

There is no built-in auth mechanism for Outlines.

The LangChain Outlines integration lives in the langchain-community package and requires the outlines library:

%pip install -qU langchain-community outlines

Now we can instantiate our model object and generate chat completions:

from langchain_community.llms import Outlines


model = Outlines(model="microsoft/Phi-3-mini-4k-instruct", backend="llamacpp")


model = Outlines(model="microsoft/Phi-3-mini-4k-instruct", backend="vllm")


model = Outlines(model="microsoft/Phi-3-mini-4k-instruct", backend="mlxlm")


model = Outlines(
    model="microsoft/Phi-3-mini-4k-instruct"
)  

model.invoke("Hello how are you?")

from langchain_core.prompts import PromptTemplate

prompt = PromptTemplate.from_template("How to say {input} in {output_language}:\n")

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

Outlines supports streaming of tokens:

for chunk in model.stream("Count to 10 in French:"):
    print(chunk, end="", flush=True)

Outlines allows you to apply various constraints to the generated output:

model.regex = r"((25[0-5]|2[0-4]\d|[01]?\d\d?)\.){3}(25[0-5]|2[0-4]\d|[01]?\d\d?)"
response = model.invoke("What is the IP address of Google's DNS server?")

response

model.type_constraints = int
response = model.invoke("What is the answer to life, the universe, and everything?")

from pydantic import BaseModel


class Person(BaseModel):
    name: str


model.json_schema = Person
response = model.invoke("Who is the author of LangChain?")
person = Person.model_validate_json(response)

person

model.grammar = """
?start: expression
?expression: term (("+" | "-") term)
?term: factor (("" | "/") factor)
?factor: NUMBER | "-" factor | "(" expression ")"
%import common.NUMBER
%import common.WS
%ignore WS
"""
response = model.invoke("Give me a complex arithmetic expression:")

response

For detailed documentation of all ChatOutlines features and configurations head to the API reference: https://python.langchain.com/api_reference/community/chat_models/langchain_community.chat_models.outlines.ChatOutlines.html

https://dottxt-ai.github.io/outlines/latest/

• LLM conceptual guide
• LLM how-to guides

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4