Experimental wrappers that also log to LangSmith.
Project description
LangSmith API Wrappers
Some functionality to wrap common apis (e.g., openai
) with LangSmith instrumentation.
Example:
from langsmith.wrappers.openai import openai
result = openai.ChatCompletion.create(
model="gpt-3.5-turbo",
messages=[
{
"role": "user",
"content": "What's the weather like in san francisco right now?",
}
],
functions=[
{
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
},
"required": ["location"],
},
}
],
)
print(result)
You can try wrapping your own library. Function calls will be mapped as "chain" runs.
Example:
from langsmith.wrappers.base import ModuleWrapper
import transformers as transformers_base
transformers = ModuleWrapper(transformers_base)
pipe = transformers.pipeline("text2text-generation", model="google/t5-efficient-tiny")
result = pipe("This is a test")
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Close
Hashes for langsmith_wrappers-0.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 557671f126263fd8511b2a452ba07403873ad708e4f93db77c6daa7ce54d2452 |
|
MD5 | d28d86bb5a92b1d5e5125f907b7a7a6d |
|
BLAKE2b-256 | 274a7c2ec1df68333e698b1ce3ca1e32af5af652c5c8041219bec65f259c754a |