dial-langchain

Official LangChain tools for Dial — phone numbers, SMS, WhatsApp, and AI voice calls for AI agents.

Install

pip install dial-langchain
# or
uv add dial-langchain

This pulls in dial-sdk and langchain-core automatically. Requires Python 3.11+.

Quickstart

Build one DialClient, hand it to DialToolkit, and call get_tools() to give an agent the full set — no per-tool imports. Every tool shares that one client (a single connection pool):

from dial_sdk import DialClient, DialConfig
from dial_langchain import DialToolkit
from langchain.chat_models import init_chat_model
from langgraph.prebuilt import create_react_agent

model = init_chat_model("claude-sonnet-4-6", model_provider="anthropic")

dial = DialClient(DialConfig(api_key="sk_live_..."))
toolkit = DialToolkit(client=dial)
agent = create_react_agent(model, toolkit.get_tools())

DialToolkit is a standard LangChain BaseToolkit, so get_tools() works anywhere a list of tools is expected. DialConfig also takes an optional base_url (defaults to https://api.getdial.ai; override it for local or self-hosted setups).

Pick individual tools

When you only want a subset, import the tools directly and pass them the same client. Each Dial capability is a LangChain BaseTool:

from dial_sdk import DialClient, DialConfig
from dial_langchain import (
    ListNumbersTool,
    SendMessageTool,
    MakeCallTool,
    ListCallsTool,
    GetCallTool,
    WaitForMessageTool,
)

dial = DialClient(DialConfig(api_key="sk_live_..."))
tools = [
    ListNumbersTool(client=dial),
    SendMessageTool(client=dial),
    MakeCallTool(client=dial),
]

# Drop into any LangChain agent:
from langchain.agents import create_react_agent
agent = create_react_agent(model, tools, prompt)

The tools are async — LangChain calls them via ainvoke.

Available tools

Tool	Tool name (for the LLM)
`ListNumbersTool`	`list_numbers`
`PurchaseNumberTool`	`purchase_number`
`SetNumberPropertiesTool`	`set_number_properties`
`ListMessagesTool`	`list_messages`
`ListContactsTool`	`list_contacts`
`SendMessageTool`	`send_message`
`ReplyToMessageTool`	`reply_to_message`
`ListCallsTool`	`list_calls`
`MakeCallTool`	`make_call`
`GetCallTool`	`get_call`
`WaitForMessageTool`	`wait_for_message`

Each tool wraps the corresponding dial-sdk call under the hood. DialToolkit.get_tools() returns all of them.

dial-sdk — the underlying async Python SDK.
Documentation

Metadata

Release files for dial-langchain 0.28.0

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

Source distribution (sdist)

Source distribution for dial-langchain 0.28.0
File	Size	Uploaded
dial_langchain-0.28.0.tar.gz	140.1 kB	Oct 12, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for dial-langchain 0.28.0
File	Interpreter	ABI	Platform	Reset
dial_langchain-0.28.0-py3-none-any.whl 12.3 kB Oct 12, 2026	Python 3	none	any	Details

Total release size: 152.5 kB

Release files / dial_langchain-0.28.0.tar.gz

Download URL	dial_langchain-0.28.0.tar.gz
Size	140.1 kB
Tags	Source
SHA-256 checksum How to use checksums	`59ad42300f4dd934304f263f7f0cfe9e52d8869102acb9899161ab2fecfe4a11`
BLAKE2b-256 checksum How to use checksums	`22dc297368984010dc20509c226c3682ef573789f3adf7272754a6903f419a98`
Upload date	Oct 12, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

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.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/GENWAY-AI/dial
Publishing commit: github.com/GENWAY-AI/dial/tree/b26b47a2ef128f801cc04508b342a54e8cfb32e3

Workflow

Publishing configuration: github.com/GENWAY-AI/dial/blob/b26b47a2ef128f801cc04508b342a54e8cfb32e3/.github/workflows/publish-sdk-langchain.yml
Publishing logs: github.com/GENWAY-AI/dial/actions/runs/38226806271/attempts/1

Artifact

Subject: dial_langchain-0.28.0.tar.gz
SHA-256 checksum: 59ad42300f4dd934304f263f7f0cfe9e52d8869102acb9899161ab2fecfe4a11 Verifying attestations

Release files / dial_langchain-0.28.0-py3-none-any.whl

Download URL	dial_langchain-0.28.0-py3-none-any.whl
Size	12.3 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`3784ce5fcfec4b90d5abe9e0d855a104939edef66a8eefda0e8fecc725364bf3`
BLAKE2b-256 checksum How to use checksums	`2ca435b69b6bb420002ea53985111957408e991948a2a9d730acab74a3312020`
Upload date	Oct 12, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/GENWAY-AI/dial
Publishing commit: github.com/GENWAY-AI/dial/tree/b26b47a2ef128f801cc04508b342a54e8cfb32e3

Workflow

Publishing configuration: github.com/GENWAY-AI/dial/blob/b26b47a2ef128f801cc04508b342a54e8cfb32e3/.github/workflows/publish-sdk-langchain.yml
Publishing logs: github.com/GENWAY-AI/dial/actions/runs/38226806271/attempts/1

Artifact

Subject: dial_langchain-0.28.0-py3-none-any.whl
SHA-256 checksum: 3784ce5fcfec4b90d5abe9e0d855a104939edef66a8eefda0e8fecc725364bf3 Verifying attestations