Metadata-Version: 2.4
Name: aion-indian-market-intelligence
Version: 1.0.3
Summary: AION Indian Market Intelligence client library and MCP server for structured event intelligence and sector incidence vectors. API key required for inference.
Author: AION Analytics
License: AGPL-3.0-or-later
Project-URL: Homepage, https://github.com/AION-Analytics/aion-news-to-signal
Project-URL: Documentation, https://dashboard.aiondashboard.site/models/news-to-signal
Project-URL: Issues, https://github.com/AION-Analytics/aion-news-to-signal/issues
Keywords: india,nse,market-intelligence,structured-event-intelligence,sector-incidence,financial-news,event-intelligence,sector-analysis
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Financial and Insurance Industry
Classifier: License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Office/Business :: Financial
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: requests>=2.31
Requires-Dist: mcp>=1.27

# AION Indian Market Intelligence — Client Library

Structured event intelligence and sector incidence vectors for Indian financial markets.

Distribution name: `aion-indian-market-intelligence`.

Compatibility note: the Python import path remains `aion_news_to_signal`, and the legacy console entrypoint remains available for existing integrations.

This package provides:

- A Python client for the AION Indian Market Intelligence API
- An MCP server entrypoint for ChatGPT, Claude, Cursor, and other MCP-compatible tools
- Local data validation and output formatting utilities

This package does **NOT** contain model weights. Inference requires an API key from `https://dashboard.aiondashboard.site/access/register`.

## Quick Start

```python
from aion_news_to_signal import analyze

# Requires AION_API_KEY environment variable or explicit key
result = analyze("RBI hikes repo rate by 25 bps", api_key="YOUR_KEY")
print(result["sector_vector"])
```

## MCP Server

```bash
aion-indian-market-intelligence-mcp
```

The MCP server requires an API key for inference. Set `AION_API_KEY` in your environment. Existing users can continue to call `aion-news-to-signal-mcp`.

## API Contract

Production inference flows through the hosted AION API:

- `POST https://api.aiondashboard.site/v1/analyze`
- header:
  - `X-API-Key: <key>`

```python
import requests

headers = {"X-API-Key": "YOUR_API_KEY"}
resp = requests.post(
    "https://api.aiondashboard.site/v1/analyze",
    headers=headers,
    json={"headline": "RBI hikes repo rate by 25 bps"},
    timeout=30,
)
resp.raise_for_status()
print(resp.json()["sector_vector"])
```

## Output Contract

The core output is a structured event-intelligence object. `sector_vector` is a sector incidence vector: a scored map of which sectors are exposed, supported, or pressured by the event. It is not a directional trade instruction and it is not executable trade guidance.

```json
{
  "headline": "string",
  "event": "string|null",
  "confidence": "float",
  "vix_regime": "string",
  "sector_vector": {},
  "top_positive_sectors": {},
  "top_negative_sectors": {},
  "sector_directional_bias": {
    "positive_bias": [],
    "negative_bias": []
  },
  "stakeholder_views": {},
  "raw_assignment": {
    "resolved_event_id": "string|null",
    "cause_effect_rule_id": "string|null",
    "weather_triggered": "bool"
  }
}
```

## Important Note

⚠️ This package is a client library, not a self-contained inference engine. It requires a valid API key and internet connectivity to call the AION hosted API. For local/offline inference, contact AION Analytics about enterprise deployment options.

This package provides structured market intelligence. It does not provide investment advice, broker execution, portfolio allocation, directional trade recommendations, or order-routing logic.

## Links

- API gateway:
  - `https://dashboard.aiondashboard.site/systems/api-gateway`
- Website model page:
  - `https://dashboard.aiondashboard.site/models/news-to-signal`
- API key registration:
  - `https://dashboard.aiondashboard.site/access/register`
- GitHub:
  - `https://github.com/AION-Analytics/aion-news-to-signal`
- Hugging Face model:
  - `https://huggingface.co/AION-Analytics/aion-news-to-signal`
- Hugging Face demo:
  - `https://huggingface.co/spaces/AION-Analytics/aion-news-to-signal`
- PyPI package:
  - `https://pypi.org/project/aion-indian-market-intelligence/`
- Legacy PyPI compatibility package:
  - `https://pypi.org/project/aion-news-to-signal/`
