# Ragbits Document Search
Ragbits Document Search is a Python package that provides tools for building RAG applications. It helps ingest, index, and search documents to retrieve relevant information for your prompts.
## Installation
You can install the latest version of Ragbits Document Search using pip:
```bash
pip install ragbits-document-search
```
## Quickstart
```python
from ragbits.core.embeddings.litellm import LiteLLMEmbedder
from ragbits.core.vector_stores.in_memory import InMemoryVectorStore
from ragbits.document_search import DocumentSearch
async def main() -> None:
"""
Run the example.
"""
embedder = LiteLLMEmbedder(
model="text-embedding-3-small",
)
vector_store = InMemoryVectorStore(embedder=embedder)
document_search = DocumentSearch(
vector_store=vector_store,
)
# Ingest all .txt files from the "biographies" directory
await document_search.ingest("file://biographies/*.txt")
# Search the documents for the query
results = await document_search.search("When was Marie Curie-Sklodowska born?")
print(results)
if __name__ == "__main__":
asyncio.run(main())
```
## Documentation
* [Quickstart 2: Adding RAG Capabilities](https://ragbits.deepsense.ai/quickstart/quickstart2_rag/)
* [How-To Guides - Document Search](https://ragbits.deepsense.ai/how-to/document_search/async_processing/)
* [API Reference - Document Search](https://ragbits.deepsense.ai/api_reference/document_search/)
Raw data
{
"_id": null,
"home_page": null,
"name": "ragbits-document-search",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "Document Search, GenAI, Generative AI, LLMs, Large Language Models, RAG, Retrieval Augmented Generation",
"author": null,
"author_email": "\"deepsense.ai\" <ragbits@deepsense.ai>",
"download_url": "https://files.pythonhosted.org/packages/75/aa/2ac1ffa5a81dc76ca081df01ea5eff33329af2a6a2778c6982d0a1700646/ragbits_document_search-1.3.0.tar.gz",
"platform": null,
"description": "# Ragbits Document Search\n\nRagbits Document Search is a Python package that provides tools for building RAG applications. It helps ingest, index, and search documents to retrieve relevant information for your prompts.\n\n## Installation\n\nYou can install the latest version of Ragbits Document Search using pip:\n\n```bash\npip install ragbits-document-search\n```\n\n## Quickstart\n```python\nfrom ragbits.core.embeddings.litellm import LiteLLMEmbedder\nfrom ragbits.core.vector_stores.in_memory import InMemoryVectorStore\nfrom ragbits.document_search import DocumentSearch\n\nasync def main() -> None:\n \"\"\"\n Run the example.\n \"\"\"\n embedder = LiteLLMEmbedder(\n model=\"text-embedding-3-small\",\n )\n vector_store = InMemoryVectorStore(embedder=embedder)\n document_search = DocumentSearch(\n vector_store=vector_store,\n )\n\n # Ingest all .txt files from the \"biographies\" directory\n await document_search.ingest(\"file://biographies/*.txt\")\n\n # Search the documents for the query\n results = await document_search.search(\"When was Marie Curie-Sklodowska born?\")\n print(results)\n\n\nif __name__ == \"__main__\":\n asyncio.run(main())\n```\n\n## Documentation\n* [Quickstart 2: Adding RAG Capabilities](https://ragbits.deepsense.ai/quickstart/quickstart2_rag/)\n* [How-To Guides - Document Search](https://ragbits.deepsense.ai/how-to/document_search/async_processing/)\n* [API Reference - Document Search](https://ragbits.deepsense.ai/api_reference/document_search/)\n",
"bugtrack_url": null,
"license": null,
"summary": "Document Search module for Ragbits",
"version": "1.3.0",
"project_urls": {
"Bug Reports": "https://github.com/deepsense-ai/ragbits/issues",
"Documentation": "https://ragbits.deepsense.ai/",
"Homepage": "https://github.com/deepsense-ai/ragbits",
"Source": "https://github.com/deepsense-ai/ragbits"
},
"split_keywords": [
"document search",
" genai",
" generative ai",
" llms",
" large language models",
" rag",
" retrieval augmented generation"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "3f183b8b84bca6b70335c0f5671e72ed28ee1987408f04c22d4463598dd8fc22",
"md5": "a1f6c401ca0faa0b386f5c89e79097e1",
"sha256": "2f7c29e642638ab9742764c4d6a88cbbfde144c59f90d83ce016c73662290808"
},
"downloads": -1,
"filename": "ragbits_document_search-1.3.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "a1f6c401ca0faa0b386f5c89e79097e1",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 49055,
"upload_time": "2025-09-11T13:58:46",
"upload_time_iso_8601": "2025-09-11T13:58:46.132812Z",
"url": "https://files.pythonhosted.org/packages/3f/18/3b8b84bca6b70335c0f5671e72ed28ee1987408f04c22d4463598dd8fc22/ragbits_document_search-1.3.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "75aa2ac1ffa5a81dc76ca081df01ea5eff33329af2a6a2778c6982d0a1700646",
"md5": "8edecae800a144cd129f5308296df0d2",
"sha256": "e510cf8aafca80cda1f0b248c9d29143810646a02ee887ff57c8822fee2889d9"
},
"downloads": -1,
"filename": "ragbits_document_search-1.3.0.tar.gz",
"has_sig": false,
"md5_digest": "8edecae800a144cd129f5308296df0d2",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 721497,
"upload_time": "2025-09-11T13:58:52",
"upload_time_iso_8601": "2025-09-11T13:58:52.921771Z",
"url": "https://files.pythonhosted.org/packages/75/aa/2ac1ffa5a81dc76ca081df01ea5eff33329af2a6a2778c6982d0a1700646/ragbits_document_search-1.3.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-09-11 13:58:52",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "deepsense-ai",
"github_project": "ragbits",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "ragbits-document-search"
}
JSON
