This will help you get started with the Box retriever.

Overview

The BoxRetriever class helps you get your unstructured content from Box in LangChain’s Document format. You can do this by searching for files based on a full-text search or using Box AI to retrieve a Document containing the result of an AI query against files. This requires including a List[str] containing Box file ids, i.e. ["12345","67890"]

Box AI requires an Enterprise Plus license

Files without a text representation will be skipped.

Integration details

1: Bring-your-own data (i.e., index and search a custom corpus of documents):

Retriever	Self-host	Cloud offering	Package
`BoxRetriever`	❌	✅	`langchain-box`

Setup

In order to use the Box package, you will need a few things:

A Box account — If you are not a current Box customer or want to test outside of your production Box instance, you can use a free developer account.
A Box app — This is configured in the developer console, and for Box AI, must have the Manage AI scope enabled. Here you will also select your authentication method
The app must be enabled by the administrator. For free developer accounts, this is whomever signed up for the account.

Credentials

For these examples, we will use token authentication. This can be used with any authentication method. Just get the token with whatever methodology. If you want to learn more about how to use other authentication types with langchain-box, visit the Box provider document.

import getpass
import os

box_developer_token = getpass.getpass("Enter your Box Developer Token: ")

If you want to get automated tracing from individual queries, you can also set your LangSmith API key by uncommenting below:

os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
os.environ["LANGSMITH_TRACING"] = "true"

Installation

This retriever lives in the langchain-box package:

pip install -qU langchain-box

Instantiation

Now we can instantiate our retriever:

Search

from langchain_box import BoxRetriever

retriever = BoxRetriever(box_developer_token=box_developer_token)

For more granular search, we offer a series of options to help you filter down the results. This uses the langchain_box.utilities.SearchOptions in conjunction with the langchain_box.utilities.SearchTypeFilter and langchain_box.utilities.DocumentFiles enums to filter on things like created date, which part of the file to search, and even to limit the search scope to a specific folder. For more information, check out the API reference.

from langchain_box.utilities import BoxSearchOptions, DocumentFiles, SearchTypeFilter

box_folder_id = "260931903795"

box_search_options = BoxSearchOptions(
    ancestor_folder_ids=[box_folder_id],
    search_type_filter=[SearchTypeFilter.FILE_CONTENT],
    created_date_range=["2023-01-01T00:00:00-07:00", "2024-08-01T00:00:00-07:00,"],
    k=200,
    size_range=[1, 1000000],
    updated_data_range=None,
)

retriever = BoxRetriever(
    box_developer_token=box_developer_token, box_search_options=box_search_options
)

retriever.invoke("AstroTech Solutions")

[Document(metadata={'source': 'https://dl.boxcloud.com/api/2.0/internal_files/1514555423624/versions/1663171610024/representations/extracted_text/content/', 'title': 'Invoice-A5555_txt'}, page_content='Vendor: AstroTech Solutions\nInvoice Number: A5555\n\nLine Items:\n    - Gravitational Wave Detector Kit: $800\n    - Exoplanet Terrarium: $120\nTotal: $920')]

Box AI

from langchain_box import BoxRetriever

box_file_ids = ["1514555423624", "1514553902288"]

retriever = BoxRetriever(
    box_developer_token=box_developer_token, box_file_ids=box_file_ids
)

Usage

query = "What was the most expensive item purchased"

retriever.invoke(query)

[Document(metadata={'source': 'Box AI', 'title': 'Box AI What was the most expensive item purchased'}, page_content='The most expensive item purchased is the **Gravitational Wave Detector Kit** from AstroTech Solutions, which costs **$800**.')]

Citations

With Box AI and the BoxRetriever, you can return the answer to your prompt, return the citations used by Box to get that answer, or both. No matter how you choose to use Box AI, the retriever returns a List[Document] object. We offer this flexibility with two bool arguments, answer and citations. Answer defaults to True and citations defaults to False, do you can omit both if you just want the answer. If you want both, you can just include citations=True and if you only want citations, you would include answer=False and citations=True

Get both

retriever = BoxRetriever(
    box_developer_token=box_developer_token, box_file_ids=box_file_ids, citations=True
)

retriever.invoke(query)

[Document(metadata={'source': 'Box AI', 'title': 'Box AI What was the most expensive item purchased'}, page_content='The most expensive item purchased is the **Gravitational Wave Detector Kit** from AstroTech Solutions, which costs **$800**.'),
 Document(metadata={'source': 'Box AI What was the most expensive item purchased', 'file_name': 'Invoice-A5555.txt', 'file_id': '1514555423624', 'file_type': 'file'}, page_content='Vendor: AstroTech Solutions\nInvoice Number: A5555\n\nLine Items:\n    - Gravitational Wave Detector Kit: $800\n    - Exoplanet Terrarium: $120\nTotal: $920')]

Citations only

retriever = BoxRetriever(
    box_developer_token=box_developer_token,
    box_file_ids=box_file_ids,
    answer=False,
    citations=True,
)

retriever.invoke(query)

[Document(metadata={'source': 'Box AI What was the most expensive item purchased', 'file_name': 'Invoice-A5555.txt', 'file_id': '1514555423624', 'file_type': 'file'}, page_content='Vendor: AstroTech Solutions\nInvoice Number: A5555\n\nLine Items:\n    - Gravitational Wave Detector Kit: $800\n    - Exoplanet Terrarium: $120\nTotal: $920')]

Use as an agent tool

Like other retrievers, BoxRetriever can be also be added to a LangGraph agent as a tool.

pip install -U langsmith

from langchain_classic import hub
from langchain.agents import AgentExecutor, create_openai_tools_agent
from langchain.tools.retriever import create_retriever_tool

box_search_options = BoxSearchOptions(
    ancestor_folder_ids=[box_folder_id],
    search_type_filter=[SearchTypeFilter.FILE_CONTENT],
    created_date_range=["2023-01-01T00:00:00-07:00", "2024-08-01T00:00:00-07:00,"],
    k=200,
    size_range=[1, 1000000],
    updated_data_range=None,
)

retriever = BoxRetriever(
    box_developer_token=box_developer_token, box_search_options=box_search_options
)

box_search_tool = create_retriever_tool(
    retriever,
    "box_search_tool",
    "This tool is used to search Box and retrieve documents that match the search criteria",
)
tools = [box_search_tool]

prompt = hub.pull("hwchase17/openai-tools-agent")
prompt.messages

llm = ChatOpenAI(temperature=0, openai_api_key=openai_key)

agent = create_openai_tools_agent(llm, tools, prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools)

/Users/shurrey/local/langchain/.venv/lib/python3.11/site-packages/langsmith/client.py:312: LangSmithMissingAPIKeyWarning: API key must be provided when using hosted LangSmith API
  warnings.warn(

result = agent_executor.invoke(
    {
        "input": "list the items I purchased from AstroTech Solutions from most expensive to least expensive"
    }
)

print(f"result {result['output']}")

result The items you purchased from AstroTech Solutions from most expensive to least expensive are:

1. Gravitational Wave Detector Kit: $800
2. Exoplanet Terrarium: $120

Total: $920

Extra fields

All Box connectors offer the ability to select additional fields from the Box FileFull object to return as custom LangChain metadata. Each object accepts an optional List[str] called extra_fields containing the json key from the return object, like extra_fields=["shared_link"]. The connector will add this field to the list of fields the integration needs to function and then add the results to the metadata returned in the Document or Blob, like "metadata" : { "source" : "source, "shared_link" : "shared_link" }. If the field is unavailable for that file, it will be returned as an empty string, like "shared_link" : "".

Help

If you have questions, you can check out our developer documentation or reach out to use in our developer community.

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

Edit this page on GitHub or file an issue.

Popular Providers

Integrations by component

BoxRetriever integration

Overview

Integration details

Setup

Credentials

Installation

Instantiation

Search

Box AI

Usage

Citations

Get both

Citations only

Use as an agent tool

Extra fields

Help

​Overview

​Integration details

​Setup

​Credentials

​Installation

​Instantiation

​Search

​Box AI

​Usage

​Citations

​Get both

​Citations only

​Use as an agent tool

​Extra fields

​Help

Overview

Integration details

Setup

Credentials

Installation

Instantiation

Search

Box AI

Usage

Citations

Get both

Citations only

Use as an agent tool

Extra fields

Help