# 🎓 ReAG Python SDK
## Installation
1. Ensure Python 3.9+ is installed.
2. Install using pip or poetry:
```bash
pip install reag
# or
poetry add reag
```
## Quick Start
```python
from reag.client import ReagClient, Document
async with ReagClient(
model="ollama/deepseek-r1:7b",
model_kwargs={"api_base": "http://localhost:11434"}
) as client:
docs = [
Document(
name="Superagent",
content="Superagent is a workspace for AI-agents that learn, perform work, and collaborate.",
metadata={
"url": "https://superagent.sh",
"source": "web",
},
),
]
response = await client.query("What is Superagent?", documents=docs)
```
## API Reference
### Initialization
Initialize the client by providing required configuration options:
```typescript
client = new ReagClient(
model: "gpt-4o-mini", // LiteLLM model name
system: Optional[str] // Optional system prompt
batchSize: Optional[Number] // Optional batch size
schema: Optional[BaseModel] // Optional Pydantic schema
);
```
### Document Structure
Documents should follow this structure:
```python
document = Document(
name="Superagent",
content="Superagent is a workspace for AI-agents that learn, perform work, and collaborate.",
metadata={
"url": "https://superagent.sh",
"source": "web",
},
)
```
### Querying
Query documents with optional filters:
```python
docs = [
Document(
name="Superagent",
content="Superagent is a workspace for AI-agents that learn, perform work, and collaborate.",
metadata={
"url": "https://superagent.sh",
"source": "web",
"id": "sa-1",
},
),
Document(
name="Superagent",
content="Superagent is a workspace for AI-agents that learn, perform work, and collaborate.",
metadata={
"url": "https://superagent.sh",
"source": "web",
"id": "sa-2",
},
),
]
options = {"filter": [{"key": "id", "value": "sa-1", "operator": "equals"}]}
response = await client.query(
"What is Superagent?", documents=docs, options=options
)
```
Response structure:
```python
content: str
reasoning: str
is_irrelevant: bool
document: Document
```
Example filters:
- Filter by metadata field:
```python
options = {"filter": [{"key": "id", "value": "sa-1", "operator": "equals"}]}
```
- Filter by numeric values:
```python
options = {
"filter": [{"key": "version", "value": 2, "operator": "greaterThanOrEqual"}]
}
```
## Contributing
We welcome contributions from the community. Please refer to the [CONTRIBUTING.md](CONTRIBUTING.md) file for guidelines on reporting issues, suggesting improvements, and submitting pull requests.
## License
This project is licensed under the [MIT License](LICENSE).
## Additional Resources
- [ReAG Blog Post](https://www.superagent.sh/blog/reag-reasoning-augmented-generation) - A deep dive into ReAG.
## Contact
For support or inquiries, please contact:
- [Create Issue](https://github.com/superagent-ai/reag/issues)
- X: [@superagent_ai](https://x.com/superagent_ai)
Raw data
{
"_id": null,
"home_page": "https://github.com/superagent-ai/reag",
"name": "reag",
"maintainer": null,
"docs_url": null,
"requires_python": "<3.13,>=3.9",
"maintainer_email": null,
"keywords": "llm, ai, reasoning, generation, nlp",
"author": "Ismail Pelaseyed",
"author_email": "ismail@superagent.sh",
"download_url": "https://files.pythonhosted.org/packages/66/2e/9ff6c4b9a0fbef992c6909b24b5e8840c68616563cdf70d43cdfe92334f8/reag-0.0.6.tar.gz",
"platform": null,
"description": "# \ud83c\udf93 ReAG Python SDK\n\n## Installation\n1. Ensure Python 3.9+ is installed.\n2. Install using pip or poetry:\n ```bash\n pip install reag\n # or\n poetry add reag\n ```\n\n## Quick Start\n```python\nfrom reag.client import ReagClient, Document\n\nasync with ReagClient(\n model=\"ollama/deepseek-r1:7b\",\n model_kwargs={\"api_base\": \"http://localhost:11434\"}\n ) as client:\n docs = [\n Document(\n name=\"Superagent\",\n content=\"Superagent is a workspace for AI-agents that learn, perform work, and collaborate.\",\n metadata={\n \"url\": \"https://superagent.sh\",\n \"source\": \"web\",\n },\n ),\n ]\n response = await client.query(\"What is Superagent?\", documents=docs)\n\n```\n\n## API Reference\n\n### Initialization\nInitialize the client by providing required configuration options:\n\n```typescript\nclient = new ReagClient(\n model: \"gpt-4o-mini\", // LiteLLM model name\n system: Optional[str] // Optional system prompt\n batchSize: Optional[Number] // Optional batch size\n schema: Optional[BaseModel] // Optional Pydantic schema\n);\n```\n\n### Document Structure\nDocuments should follow this structure:\n```python\ndocument = Document(\n name=\"Superagent\",\n content=\"Superagent is a workspace for AI-agents that learn, perform work, and collaborate.\",\n metadata={\n \"url\": \"https://superagent.sh\",\n \"source\": \"web\",\n },\n)\n```\n\n### Querying\nQuery documents with optional filters:\n\n```python\ndocs = [\n Document(\n name=\"Superagent\",\n content=\"Superagent is a workspace for AI-agents that learn, perform work, and collaborate.\",\n metadata={\n \"url\": \"https://superagent.sh\",\n \"source\": \"web\",\n \"id\": \"sa-1\",\n },\n ),\n Document(\n name=\"Superagent\",\n content=\"Superagent is a workspace for AI-agents that learn, perform work, and collaborate.\",\n metadata={\n \"url\": \"https://superagent.sh\",\n \"source\": \"web\",\n \"id\": \"sa-2\",\n },\n ),\n]\noptions = {\"filter\": [{\"key\": \"id\", \"value\": \"sa-1\", \"operator\": \"equals\"}]}\nresponse = await client.query(\n \"What is Superagent?\", documents=docs, options=options\n)\n```\n\nResponse structure:\n```python\ncontent: str\nreasoning: str\nis_irrelevant: bool\ndocument: Document\n```\n\nExample filters:\n- Filter by metadata field:\n ```python\n options = {\"filter\": [{\"key\": \"id\", \"value\": \"sa-1\", \"operator\": \"equals\"}]}\n ```\n- Filter by numeric values:\n ```python\n options = {\n \"filter\": [{\"key\": \"version\", \"value\": 2, \"operator\": \"greaterThanOrEqual\"}]\n }\n ```\n\n## Contributing\n\nWe welcome contributions from the community. Please refer to the [CONTRIBUTING.md](CONTRIBUTING.md) file for guidelines on reporting issues, suggesting improvements, and submitting pull requests.\n\n## License\n\nThis project is licensed under the [MIT License](LICENSE).\n\n## Additional Resources\n- [ReAG Blog Post](https://www.superagent.sh/blog/reag-reasoning-augmented-generation) - A deep dive into ReAG.\n\n## Contact\n\nFor support or inquiries, please contact:\n- [Create Issue](https://github.com/superagent-ai/reag/issues)\n- X: [@superagent_ai](https://x.com/superagent_ai)\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "ReAG SDK - Reasoning Augmented Generation framework for Python",
"version": "0.0.6",
"project_urls": {
"Documentation": "https://github.com/superagent-ai/reag#readme",
"Homepage": "https://github.com/superagent-ai/reag",
"Repository": "https://github.com/superagent-ai/reag"
},
"split_keywords": [
"llm",
" ai",
" reasoning",
" generation",
" nlp"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "d6a3c0a2f12b8b447de2f1b80fc35babf96b6cdca50f33ca6d1501ad214b53b7",
"md5": "9dc137ac8ce1f2cc236514d5b0679a6b",
"sha256": "973ae5fac72be8b6857800772acaf7a86a783ee6dfa0b0de4724b858efb51350"
},
"downloads": -1,
"filename": "reag-0.0.6-py3-none-any.whl",
"has_sig": false,
"md5_digest": "9dc137ac8ce1f2cc236514d5b0679a6b",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.13,>=3.9",
"size": 5726,
"upload_time": "2025-02-12T15:26:24",
"upload_time_iso_8601": "2025-02-12T15:26:24.362297Z",
"url": "https://files.pythonhosted.org/packages/d6/a3/c0a2f12b8b447de2f1b80fc35babf96b6cdca50f33ca6d1501ad214b53b7/reag-0.0.6-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "662e9ff6c4b9a0fbef992c6909b24b5e8840c68616563cdf70d43cdfe92334f8",
"md5": "87ce513d71890cfd4ba86b37c35614d7",
"sha256": "121a93bb9262ebd2acd20faf2ac68b42ff762a85f3915fad5b32a6144a0dd06c"
},
"downloads": -1,
"filename": "reag-0.0.6.tar.gz",
"has_sig": false,
"md5_digest": "87ce513d71890cfd4ba86b37c35614d7",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.13,>=3.9",
"size": 5189,
"upload_time": "2025-02-12T15:26:25",
"upload_time_iso_8601": "2025-02-12T15:26:25.562650Z",
"url": "https://files.pythonhosted.org/packages/66/2e/9ff6c4b9a0fbef992c6909b24b5e8840c68616563cdf70d43cdfe92334f8/reag-0.0.6.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-02-12 15:26:25",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "superagent-ai",
"github_project": "reag",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "reag"
}
JSON
