OpenAI

Setup:

Install langchain-openai and set environment variable OPENAI_API_KEY.

pip install -U langchain-openai
export OPENAI_API_KEY="your-api-key"

Key init args — completion params: model: Name of OpenAI model to use. temperature: Sampling temperature. max_tokens: Max number of tokens to generate. logprobs: Whether to return logprobs. stream_options: Configure streaming outputs, like whether to return token usage when streaming ({"include_usage": True}).

Key init args — client params: timeout: Timeout for requests. max_retries: Max number of retries. api_key: OpenAI API key. If not passed in will be read from env var OPENAI_API_KEY. base_url: Base URL for API requests. Only specify if using a proxy or service emulator. organization: OpenAI organization ID. If not passed in will be read from env var OPENAI_ORG_ID.

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

Instantiate:

from langchain_openai import OpenAI

model = OpenAI(
    model="gpt-3.5-turbo-instruct",
    temperature=0,
    max_retries=2,
    # api_key="...",
    # base_url="...",
    # organization="...",
    # other params...
)

Invoke:

input_text = "The meaning of life is "
model.invoke(input_text)

"a philosophical question that has been debated by thinkers and scholars for centuries."

Stream:

for chunk in model.stream(input_text):
    print(chunk, end="|")

a| philosophical| question| that| has| been| debated| by| thinkers| and| scholars| for| centuries|.

"".join(model.stream(input_text))

"a philosophical question that has been debated by thinkers and scholars for centuries."

Async:

await model.ainvoke(input_text)

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

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

"a philosophical question that has been debated by thinkers and scholars for centuries."