| Name | condy JSON |
| Version |
0.3.9
JSON |
| download |
| home_page | None |
| Summary | Python client for the Condensation.ai API |
| upload_time | 2024-10-30 20:05:38 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.8 |
| license | None |
| keywords |
ai
api-client
condensation
rag
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Condy: Python Client for Condensation.ai
A modern, async Python client library for interacting with the Condensation.ai API, providing seamless access to document processing and RAG (Retrieval-Augmented Generation) capabilities.
## Features
- 🚀 Fully async implementation using `httpx`
- 📄 Document processing and chunking
- 🔍 RAG (Retrieval-Augmented Generation) querying
- 💪 Type hints and modern Python practices
- ⚡ Efficient markdown processing and page management
- 🛡️ Comprehensive error handling
- 📝 Rich document metadata support
## Installation
```bash
pip install condy
```
## Quick Start
```python
import asyncio
from condy import CondyClient
async def main():
# Initialize the client
client = CondyClient(api_key="your-api-key")
# Process a document from URL with metadata
doc_output = await client.process_document(
url="https://example.com/document.md",
filename="document.md",
file_key="custom-key",
public_url="https://example.com/document.md"
)
# Query the document using RAG
response = await client.query_rag(
question="What are the key points?",
document_id=doc_output.document_id
)
print(response.answer)
asyncio.run(main())
```
## Core Features
### Document Processing
```python
# Upload pages directly with metadata
pages = {
1: "Page 1 content",
2: "Page 2 content"
}
doc_output = await client.upload_pages(
pages=pages,
filename="document.txt",
file_key="unique-identifier",
public_url="https://example.com/document.txt"
)
# Or process markdown from URL with metadata
doc_output = await client.process_document(
url="https://example.com/document.md",
filename="document.md",
file_key="doc-123",
public_url="https://example.com/document.md"
)
```
### RAG Queries
```python
# Query a document
response = await client.query_rag(
question="What does the document say about X?",
document_id="doc-id",
max_chunks=5
)
# Access the response
print(response.answer)
print(response.source_pages) # List of source pages used
```
### Chunk Management
```python
# Fetch document chunks
chunks = await client.fetch_chunks(
document_id="doc-id",
include_embeddings=False # Set to True to include vector embeddings
)
```
## Configuration
The client can be configured with custom settings:
```python
client = CondyClient(
api_key="your-api-key",
base_url="https://custom-url.example.com", # Optional
timeout=60.0 # Custom timeout in seconds
)
```
## Document Metadata
The library supports rich document metadata:
```python
# Process document with full metadata
doc_output = await client.process_document(
url="https://example.com/doc.pdf",
content_type="pdf",
filename="important-doc.pdf", # Optional: Custom filename
file_key="doc-2023-01", # Optional: Unique identifier
public_url="https://example.com/doc.pdf" # Optional: Public access URL
)
```
## Error Handling
The library provides specific exceptions for different error cases:
- `NetworkError`: For connection and network-related issues
- `TimeoutError`: For request timeout issues
- `APIError`: For API-specific errors with status codes and details
```python
from condy import NetworkError, TimeoutError, APIError
try:
response = await client.query_rag(question="...", document_id="...")
except TimeoutError:
print("Request timed out")
except NetworkError:
print("Network error occurred")
except APIError as e:
print(f"API error: {e.status_code} - {e.detail}")
```
## Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
## License
The usage of the library is subject to the [Condensation.ai Terms of Service](https://condensation.ai/terms-and-conditions).
## Support
For support, please contact support@condensation.ai.
Raw data
{
"_id": null,
"home_page": null,
"name": "condy",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "ai, api-client, condensation, rag",
"author": null,
"author_email": "Rach Pradhan <rach@condensation.ai>",
"download_url": "https://files.pythonhosted.org/packages/d6/25/de10286d3727bea91c38c26a19e9fe0a3845c544e317245e373edccc8d92/condy-0.3.9.tar.gz",
"platform": null,
"description": "# Condy: Python Client for Condensation.ai\n\nA modern, async Python client library for interacting with the Condensation.ai API, providing seamless access to document processing and RAG (Retrieval-Augmented Generation) capabilities.\n\n## Features\n\n- \ud83d\ude80 Fully async implementation using `httpx`\n- \ud83d\udcc4 Document processing and chunking\n- \ud83d\udd0d RAG (Retrieval-Augmented Generation) querying\n- \ud83d\udcaa Type hints and modern Python practices\n- \u26a1 Efficient markdown processing and page management\n- \ud83d\udee1\ufe0f Comprehensive error handling\n- \ud83d\udcdd Rich document metadata support\n\n## Installation\n\n```bash\npip install condy\n```\n\n## Quick Start\n\n```python\nimport asyncio\nfrom condy import CondyClient\n\nasync def main():\n # Initialize the client\n client = CondyClient(api_key=\"your-api-key\")\n \n # Process a document from URL with metadata\n doc_output = await client.process_document(\n url=\"https://example.com/document.md\",\n filename=\"document.md\",\n file_key=\"custom-key\",\n public_url=\"https://example.com/document.md\"\n )\n \n # Query the document using RAG\n response = await client.query_rag(\n question=\"What are the key points?\",\n document_id=doc_output.document_id\n )\n \n print(response.answer)\n\nasyncio.run(main())\n```\n\n## Core Features\n\n### Document Processing\n\n```python\n# Upload pages directly with metadata\npages = {\n 1: \"Page 1 content\",\n 2: \"Page 2 content\"\n}\ndoc_output = await client.upload_pages(\n pages=pages,\n filename=\"document.txt\",\n file_key=\"unique-identifier\",\n public_url=\"https://example.com/document.txt\"\n)\n\n# Or process markdown from URL with metadata\ndoc_output = await client.process_document(\n url=\"https://example.com/document.md\",\n filename=\"document.md\",\n file_key=\"doc-123\",\n public_url=\"https://example.com/document.md\"\n)\n```\n\n### RAG Queries\n\n```python\n# Query a document\nresponse = await client.query_rag(\n question=\"What does the document say about X?\",\n document_id=\"doc-id\",\n max_chunks=5\n)\n\n# Access the response\nprint(response.answer)\nprint(response.source_pages) # List of source pages used\n```\n\n### Chunk Management\n\n```python\n# Fetch document chunks\nchunks = await client.fetch_chunks(\n document_id=\"doc-id\",\n include_embeddings=False # Set to True to include vector embeddings\n)\n```\n\n## Configuration\n\nThe client can be configured with custom settings:\n\n```python\nclient = CondyClient(\n api_key=\"your-api-key\",\n base_url=\"https://custom-url.example.com\", # Optional\n timeout=60.0 # Custom timeout in seconds\n)\n```\n\n## Document Metadata\n\nThe library supports rich document metadata:\n\n```python\n# Process document with full metadata\ndoc_output = await client.process_document(\n url=\"https://example.com/doc.pdf\",\n content_type=\"pdf\",\n filename=\"important-doc.pdf\", # Optional: Custom filename\n file_key=\"doc-2023-01\", # Optional: Unique identifier\n public_url=\"https://example.com/doc.pdf\" # Optional: Public access URL\n)\n```\n\n## Error Handling\n\nThe library provides specific exceptions for different error cases:\n\n- `NetworkError`: For connection and network-related issues\n- `TimeoutError`: For request timeout issues\n- `APIError`: For API-specific errors with status codes and details\n\n```python\nfrom condy import NetworkError, TimeoutError, APIError\n\ntry:\n response = await client.query_rag(question=\"...\", document_id=\"...\")\nexcept TimeoutError:\n print(\"Request timed out\")\nexcept NetworkError:\n print(\"Network error occurred\")\nexcept APIError as e:\n print(f\"API error: {e.status_code} - {e.detail}\")\n```\n\n## Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\n## License\n\nThe usage of the library is subject to the [Condensation.ai Terms of Service](https://condensation.ai/terms-and-conditions).\n\n## Support\n\nFor support, please contact support@condensation.ai.",
"bugtrack_url": null,
"license": null,
"summary": "Python client for the Condensation.ai API",
"version": "0.3.9",
"project_urls": {
"Documentation": "https://justrach/condy",
"Homepage": "https://github.com/yourusername/condy",
"Repository": "https://github.com/justrach/condy.git",
"bug tracker": "https://github.com/yourusername/condy/issues"
},
"split_keywords": [
"ai",
" api-client",
" condensation",
" rag"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "b3c087c952536bff60c67dbe3567113689b8ab0d30139e2cb77f937dd9bc2e84",
"md5": "0a968580a365c376a491e3a51f8a86c8",
"sha256": "eb0db26e0e85c752084aaa1286e1a0d7c8ed57a8d1ff8899c0e8226729a0aeb4"
},
"downloads": -1,
"filename": "condy-0.3.9-py3-none-any.whl",
"has_sig": false,
"md5_digest": "0a968580a365c376a491e3a51f8a86c8",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 9840,
"upload_time": "2024-10-30T20:05:36",
"upload_time_iso_8601": "2024-10-30T20:05:36.747911Z",
"url": "https://files.pythonhosted.org/packages/b3/c0/87c952536bff60c67dbe3567113689b8ab0d30139e2cb77f937dd9bc2e84/condy-0.3.9-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "d625de10286d3727bea91c38c26a19e9fe0a3845c544e317245e373edccc8d92",
"md5": "8e6d48bc7438943ea9445a4847dce6b3",
"sha256": "b30de1ac23242307a1c194b4c3880c043fa09d7780be75e73ebae3d752d9c4f1"
},
"downloads": -1,
"filename": "condy-0.3.9.tar.gz",
"has_sig": false,
"md5_digest": "8e6d48bc7438943ea9445a4847dce6b3",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 9755,
"upload_time": "2024-10-30T20:05:38",
"upload_time_iso_8601": "2024-10-30T20:05:38.175720Z",
"url": "https://files.pythonhosted.org/packages/d6/25/de10286d3727bea91c38c26a19e9fe0a3845c544e317245e373edccc8d92/condy-0.3.9.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-10-30 20:05:38",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "yourusername",
"github_project": "condy",
"github_not_found": true,
"lcname": "condy"
}
