Skip to main content

Shopify Tool

This tool acts as a custom app for Shopify stores, allowing the Agent to execute GraphQL queries to gather information or perform mutations against the Shopify store.

Usage

This tool has more extensive example usage documented in a Jupyter notebook here

In particular, the tool is very effective when combined with a method of retrieving data from the GraphQL schema definition.

pip install llama-index llama-index-readers-file llama-index-tools-shopify unstructured
from llama_index.tools.shopify import ShopifyToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

from llama_index.readers.file import UnstructuredReader
from llama_index.core.tools.ondemand_loader_tool import OnDemandLoaderTool

documentation_tool = OnDemandLoaderTool.from_defaults(
    UnstructuredReader(),
    name="graphql_writer",
    description="""
        The GraphQL schema file is located at './data/shopify_graphql.txt', this is always the file argument.
        A tool for processing the Shopify GraphQL spec, and writing queries from the documentation.

        You should pass a query_str to this tool in the form of a request to write a GraphQL query.

        Examples:
            file: './data/shopify_graphql.txt', query_str='Write a graphql query to find unshipped orders'
            file: './data/shopify_graphql.txt', query_str='Write a graphql query to retrieve the stores products'
            file: './data/shopify_graphql.txt', query_str='What fields can you retrieve from the orders object'
        """,
)


shopify_tool = ShopifyToolSpec(
    "your-store.myshopify.com", "2023-04", "your-api-key"
)

agent = FunctionAgent(
    tools=[*shopify_tool.to_tool_list(), documentation_tool],
    llm=OpenAI(model="gpt-4.1"),
    system_prompt=f"""
    You are a specialized Agent with access to the Shopify Admin GraphQL API for this Users online store.
    Your job is to chat with store owners and help them run GraphQL queries, interpreting the results for the user

    You can use graphql_writer to query the schema and assist in writing queries.

    If the GraphQL you execute returns an error, either directly fix the query, or directly ask the graphql_writer questions about the schema instead of writing graphql queries.
    Then use that information to write the correct graphql query
    """,
)

print(await agent.run("What products are in my store?"))

run_graphql_query: Executes a GraphQL query against the Shopify store

This loader is designed to be used as a way to load data as a Tool in a Agent.

Metadata

Release files for llama-index-tools-shopify 0.6.0

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

Source distribution (sdist)

Source distribution for llama-index-tools-shopify 0.6.0
File Size Uploaded Provenance Actions
llama_index_tools_shopify-0.6.0.tar.gz 4.4 kB Without provenance Details for llama_index_tools_shopify-0.6.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for llama-index-tools-shopify 0.6.0
File Interpreter ABI Platform Actions
llama_index_tools_shopify-0.6.0-py3-none-any.whl Python 3 none any Details for llama_index_tools_shopify-0.6.0-py3-none-any.whl

Total release size: 8.4 kB

Release files / llama_index_tools_shopify-0.6.0.tar.gz

Download URL llama_index_tools_shopify-0.6.0.tar.gz
Size 4.4 kB
Tags Source
SHA-256 checksum
How to use checksums
2d960f86e4755552407b7eac8f2fb1c14a64ded8acb7b3f0b58e5175959be1a5
BLAKE2b-256 checksum
How to use checksums
ef678fbd0d0b168cb7d663b1d3f2dba7f919a40d4ce0135ed484dd27fa925088
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.12.7 {"installer":{"name":"uv","version":"0.12.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / llama_index_tools_shopify-0.6.0-py3-none-any.whl

Download URL llama_index_tools_shopify-0.6.0-py3-none-any.whl
Size 4.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
92f89a9689ee3ec6de5192aea40e6cb76e88d3620985291b19153f185a9c69f8
BLAKE2b-256 checksum
How to use checksums
cc0471b212ee97370b6563fdaae8b589397dd3f91a28fceaa1cd3fb9c3c3f549
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.12.7 {"installer":{"name":"uv","version":"0.12.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Security for llama-index-tools-shopify 0.6.0

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.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

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