Skip to main content

langchain-duel

This package connects Duel Agents to LangChain.

Duel Agents routes each prompt against multiple models and bills the cheapest answer that still wins. The proxy is OpenAI wire compatible, so ChatDuel builds on langchain-openai and just points at the Duel proxy with sensible defaults.

Installation

pip install -U langchain-duel

Set your Duel API key (create one at duelagents.com/dashboard/settings):

export DUEL_API_KEY="duel_<prefix>_<secret>"

Chat models

from langchain_duel import ChatDuel

llm = ChatDuel(model="duel-auto", temperature=0)
print(llm.invoke("Explain concurrent agents in one sentence.").content)

duel-auto lets the router pick the model. You can also pass a specific model name (for example gpt-4o-mini or claude-3-5-haiku-latest) and Duel will route to that provider.

Streaming

for chunk in llm.stream("Write a haiku about routing."):
    print(chunk.content, end="", flush=True)

Configuration

Argument Env var Default
api_key DUEL_API_KEY required
base_url DUEL_PROXY_URL https://duelagents.com/v1
model - duel-auto

License

MIT

Metadata

Release files for langchain-duel 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for langchain-duel 0.1.0
File Size Uploaded Provenance
langchain_duel-0.1.0.tar.gz 3.5 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for langchain-duel 0.1.0
File Interpreter ABI Platform
langchain_duel-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 7.7 kB

Release files / langchain_duel-0.1.0.tar.gz

Download URL langchain_duel-0.1.0.tar.gz
Size 3.5 kB
Tags Source
SHA-256 checksum
How to use checksums
463b0ba53ad14bba905a70a1f3d94aa778f2e2faccbe00ab9897bab1c53ad2e1
BLAKE2b-256 checksum
How to use checksums
49d318e4632a3926ea875543d60699353d74e81753690b80c931bf975725ed37
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.10

Release files / langchain_duel-0.1.0-py3-none-any.whl

Download URL langchain_duel-0.1.0-py3-none-any.whl
Size 4.2 kB
Tags Python 3
SHA-256 checksum
How to use checksums
6cd2f12ac385ef776783550511f78e8f66b480b873b06e8f6635086eca38133d
BLAKE2b-256 checksum
How to use checksums
821087fe5006deac6a112967e2d9e65ecf228bffb7db347c20a2dfd784dd3fa1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.10

Security for langchain-duel 0.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page