Skip to main content

Python SDK for LangWatch for monitoring your LLMs

Project description

LangWatch Python SDK

Go to https://langwatch.ai to setup your account.

To trace OpenAI calls:

from openai import OpenAI
+ import langwatch.openai

client = OpenAI()

+ with langwatch.openai.OpenAITracer(client):
    completion = client.chat.completions.create(
        model="gpt-3.5-turbo",
        messages=[
            {
                "role": "system",
                "content": "You are a helpful assistant that only reply in short tweet-like responses, using lots of emojis.",
            },
            {"role": "user", "content": message},
        ],
        stream=True,
    )

To trace LangChain agent:

+ import langwatch.langchain

  # ...

  chain = LLMChain(
      llm=ChatOpenAI(),
      prompt=chat_prompt,
      output_parser=CommaSeparatedListOutputParser(),
  )
+ with langwatch.langchain.LangChainTracer() as langWatchCallback:
-   result = chain.run(text="colors")
+   result = chain.run(text="colors", callbacks=[langWatchCallback])

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

langwatch-0.0.14.tar.gz (10.6 kB view details)

Uploaded Source

Built Distribution

langwatch-0.0.14-py3-none-any.whl (12.7 kB view details)

Uploaded Python 3

File details

Details for the file langwatch-0.0.14.tar.gz.

File metadata

  • Download URL: langwatch-0.0.14.tar.gz
  • Upload date:
  • Size: 10.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.9.19

File hashes

Hashes for langwatch-0.0.14.tar.gz
Algorithm Hash digest
SHA256 a9cf949d6857467cfe7179c8baabbd6cdadaf3c917d2f684a48275b75481505d
MD5 21e872cdd4f22444ec2efb23bc7fde3d
BLAKE2b-256 4275425da6fa3eb7c7d4f2f7ae8c10d2fcea5274a443c9547f812a2883e85675

See more details on using hashes here.

File details

Details for the file langwatch-0.0.14-py3-none-any.whl.

File metadata

  • Download URL: langwatch-0.0.14-py3-none-any.whl
  • Upload date:
  • Size: 12.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.9.19

File hashes

Hashes for langwatch-0.0.14-py3-none-any.whl
Algorithm Hash digest
SHA256 f685a597abdfd1d88d3ca1426ac577a7b0bbb4c0a55a1d2c40ffff26181776b5
MD5 eecd782a0a7532141e15758e9f20bdd2
BLAKE2b-256 75df97faff84e1c3034e1133bb989b9427af7ea9eef572f3cdf106ebd8fed92c

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page