Skip to main content

LangChain tools for Japanese financial data — EDINET filings, XBRL, company analysis (Axiora API)

Project description

langchain-axiora

LangChain tools for Japanese financial data — EDINET filings, XBRL, and company analysis.

Give your LangChain / LangGraph agents access to 4,000+ Japanese listed companies: financials from EDINET filings, health scores, screening, and English translations of annual reports. Powered by the Axiora API.

Install

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

Quick Start

from langchain_axiora import AxioraToolkit
from langchain_anthropic import ChatAnthropic
from langgraph.prebuilt import create_react_agent

toolkit = AxioraToolkit(api_key="ax_live_...")
agent = create_react_agent(ChatAnthropic(model="claude-sonnet-4-20250514"), toolkit.get_tools())

result = agent.invoke({
    "messages": [{"role": "user", "content": "Compare Toyota and Honda financials"}]
})

Configuration

The API key can be provided three ways (in priority order):

# 1. Explicit
toolkit = AxioraToolkit(api_key="ax_live_...")

# 2. Environment variable
import os
os.environ["AXIORA_API_KEY"] = "ax_live_..."
toolkit = AxioraToolkit()

# 3. .env file (with python-dotenv)
from dotenv import load_dotenv
load_dotenv()
toolkit = AxioraToolkit()

Using a Subset of Tools

18 tools can be noisy for simple agents. Pass selected_tools to limit:

toolkit = AxioraToolkit(
    api_key="ax_live_...",
    selected_tools=[
        "axiora_search_companies",
        "axiora_get_financials",
        "axiora_compare_companies",
    ],
)

Using Individual Tools

Tools accept api_key directly — no wrapper needed:

from langchain_axiora import GetFinancialsTool

tool = GetFinancialsTool(api_key="ax_live_...")
result = tool.invoke({"code": "7203", "years": 3})

# Or use AXIORA_API_KEY env var
tool = GetFinancialsTool()

# Async
result = await tool.ainvoke({"code": "7203"})

Available Tools (18)

Tool Description
axiora_search_companies Search companies by name or code
axiora_get_company Get detailed company info
axiora_get_financials Revenue, income, assets, ROE over time
axiora_get_growth YoY growth rates and CAGRs
axiora_get_ranking Rank companies by any metric
axiora_get_sector_overview Sector stats and company counts
axiora_compare_companies Side-by-side comparison (2-5 companies)
axiora_screen_companies Filter by revenue, ROE, PE ratio, sector
axiora_get_health_score Financial health score (0-100)
axiora_get_health_ranking Rank by health score
axiora_get_peers Find similar companies in same sector
axiora_get_timeseries Chart-ready metric time series
axiora_list_filings List annual/quarterly filings
axiora_get_translations English translations of filings
axiora_search_translations Full-text search across translations
axiora_get_filing_calendar Filing activity per day
axiora_search_companies_batch Bulk company lookup
axiora_get_coverage Data coverage statistics

Error Handling

All tools use handle_tool_error=True. When the API returns an error, the agent receives a helpful message instead of crashing:

Axiora API error 404. Company not found. Use axiora_search_companies to find the correct code.

This lets the agent self-correct (e.g., search for the right code, then retry).

Get an API Key

Sign up at axiora.dev to get your API key.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

langchain_axiora-0.1.1.tar.gz (76.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

langchain_axiora-0.1.1-py3-none-any.whl (11.5 kB view details)

Uploaded Python 3

File details

Details for the file langchain_axiora-0.1.1.tar.gz.

File metadata

  • Download URL: langchain_axiora-0.1.1.tar.gz
  • Upload date:
  • Size: 76.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.8.22

File hashes

Hashes for langchain_axiora-0.1.1.tar.gz
Algorithm Hash digest
SHA256 2f9c9accb41733052e66fc5783d88b03db281bee5f17539da66aad0211ccf388
MD5 387b4505afd6c14ac4bf33eddeba5fbc
BLAKE2b-256 c97834a243a9178706be8bacab09468d9203af4dc76f938588b9d860a86635da

See more details on using hashes here.

File details

Details for the file langchain_axiora-0.1.1-py3-none-any.whl.

File metadata

File hashes

Hashes for langchain_axiora-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 88f20d4147c5a7819c56e0388af14c006ce8cfb82900b8e7b844b17bce85adbb
MD5 2047f5662b21841e1d246aacbc24d034
BLAKE2b-256 374d49b25464e799340e742382c455e94a21d40972e897c529486b31912dcf57

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page