https://github.com/aleph-alpha/pharia-data-sdk
https://github.com/aleph-alpha/pharia-data-sdk
Last synced: 4 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/aleph-alpha/pharia-data-sdk
- Owner: Aleph-Alpha
- License: apache-2.0
- Created: 2025-06-17T12:15:19.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-06-24T16:28:24.000Z (about 1 year ago)
- Last Synced: 2025-06-24T16:48:43.981Z (about 1 year ago)
- Language: Python
- Homepage: https://pharia-data-sdk.readthedocs.io/en/latest/
- Size: 204 KB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
Awesome Lists containing this project
README
# pharia-data-sdk
Formerly the `intelligence_layer/connectors/data`, `intelligence_layer/connectors/document_index` and `intelligence_layer/connectors/retrievers` modules.
## Overview
This module provides connectors for interacting with the Pharia Data Platform and Pharia Search (a.k.a. Document Index), you can use it to semantically search, access and manage data, documents.
## Installation
```bash
pip install pharia-data-sdk
```
## Usage
### Data Platform Connector
```python
from pharia_data_sdk.connectors.data import DataClient
client = DataClient(token="", base_url="")
repositories = client.list_repositories()
repository = repositories[0]
datasets = client.list_datasets(repository.repository_id)
dataset = datasets[0]
```
### Document Index Connector
```python
from pharia_data_sdk.connectors.document_index.document_index import DocumentIndexClient, SearchQuery
client = DocumentIndexClient(token="", base_url="")
namespaces = client.list_namespaces()
collections = client.list_collections(namespaces[0])
indexes = client.list_indexes(namespaces[0])
client.search(collections[0], indexes[0].index, SearchQuery(query="What fish is most common in swedish lakes?"))
```
### Retrievers
```python
from pharia_data_sdk.connectors.retrievers.document_index_retriever import DocumentIndexRetriever
from pharia_data_sdk.connectors.document_index.document_index import DocumentIndexClient
retriever = DocumentIndexRetriever(
document_index=DocumentIndexClient(token="", base_url=""),
index_name="",
namespace="",
collection="",
)
retriever.get_relevant_documents_with_scores("What fish is most common in swedish lakes?")
```
## Contributing
We welcome contributions! Please see our [Contributing Guide](https://github.com/Aleph-Alpha/pharia-data-sdk/blob/main/CONTRIBUTING.md) for details on how to set up the development environment and submit changes.