asyntai-haystack

Haystack components and agent tools for Asyntai, the AI chat agent for websites.

Point Asyntai at a website. It reads the pages, the product feed and the documents, and keeps them current. This package brings that agent into Haystack: ask it questions inside a pipeline, feed it documents from an indexing pipeline, and give a Haystack Agent tools to read its leads and chats.

Install

pip install asyntai-haystack

Set the key

Create an API key in Asyntai under Settings → API. The API is available on the Starter plan and higher.

export ASYNTAI_API_KEY="your-key"

Components

Ask the website a question

from haystack_integrations.components.generators.asyntai import AsyntaiGenerator

generator = AsyntaiGenerator()
result = generator.run(prompt="How long does delivery take?")
print(result["replies"][0])

Pass the session_id from result["meta"][0] on the next call to keep the conversation going.

Teach the website agent from your files

from haystack import Pipeline
from haystack.components.converters import TextFileToDocument
from haystack_integrations.components.writers.asyntai import AsyntaiDocumentWriter

pipeline = Pipeline()
pipeline.add_component("converter", TextFileToDocument())
pipeline.add_component("writer", AsyntaiDocumentWriter())
pipeline.connect("converter.documents", "writer.documents")

pipeline.run({"converter": {"sources": ["faq.txt", "returns.txt"]}})

The title in Asyntai comes from meta["title"], then the file name. Any converter works in front of the writer: PDF, DOCX, HTML, Markdown.

To read live pages instead:

from haystack_integrations.components.writers.asyntai import AsyntaiUrlIndexer

AsyntaiUrlIndexer().run(urls=["https://example.com/shipping"])

Give an agent the Asyntai tools

from haystack.components.agents import Agent
from haystack.components.generators.chat import OpenAIChatGenerator
from haystack.dataclasses import ChatMessage
from haystack_integrations.tools.asyntai import AsyntaiToolset

agent = Agent(
    chat_generator=OpenAIChatGenerator(model="gpt-4o-mini"),
    tools=AsyntaiToolset(),
)
result = agent.run([ChatMessage.from_user("Who asked about delivery this week?")])
print(result["messages"][-1].text)

Give the agent only some of them with AsyntaiToolset(tools=["asyntai_ask_website"]).

Several websites on one account

An Asyntai account can run an agent per website. Name the one you want with website_id, which AsyntaiClient().websites() returns.

from haystack_integrations.common.asyntai import AsyntaiClient
from haystack_integrations.components.generators.asyntai import AsyntaiGenerator

for site in AsyntaiClient().websites():
    print(site["id"], site["domain"])

generator = AsyntaiGenerator(website_id=42)

Save and load pipelines

Every component serializes to YAML with pipeline.dumps(). The API key is stored as a reference to the ASYNTAI_API_KEY environment variable, never as the key itself.

Errors

Every failure raises AsyntaiError with a message you can show to a user. The writer and the URL indexer take raise_on_failure=False to log a refused item and continue.

Links

• Asyntai: https://asyntai.com
• Documentation: https://asyntai.com/documentation/integrations/haystack/
• API reference: https://asyntai.com/documentation/api-reference/

License

MIT