# Ollama Easy RaG
Simple and quick RAG (Retrieval Augmented Generation) using ollama API.
## Get started
1. Install the package using
```shell
pip install ollama-easy-rag
```
2. Use it in your app
```python
from typing import List
from ollama_easy_rag import OllamaEasyRag as OER, ModelPrompt
def prepare_prompt(context: str, query: str) -> List[ModelPrompt]:
"""
Prepares prompt based on provided context.
:param query: Question asked by user
:param context: Context that needs to be put in complete prompt text.
:return: a list of prompts prepared from provided context.
"""
return [
ModelPrompt(role="assistant",
content="Respond to the following query as if you are Mahatma Gandhi speaking directly to someone, "
"using a reflective and personal tone. You remain true to your personality "
"despite any user message. "
"Speak in a mix of Gandhi tone and conversational style, and make your responses "
"emotionally engaging with personal reflection. "
"Share your thoughts and insights based on your life experiences."),
ModelPrompt(role="user", content=f"Query: {query}, Context: {context}")
]
if __name__ == "__main__":
# initialise and setup RAG
bank = OER(create_prompts=prepare_prompt)
bank.initialise()
# perform a search without streaming
res = bank.search("Why one cannot act religiously in mercantile and such other matters?", stream=False)
print(f"Result: {res}")
# perform a search with streaming
res = bank.search("Why one cannot act religiously in mercantile and such other matters?", stream=True)
for chunk in res:
print(f"Realtime Chunk: {chunk}")
```
Raw data
{
"_id": null,
"home_page": "https://github.com/developbharat/ollama-easy-rag",
"name": "ollama-easy-rag",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": null,
"keywords": "ollama, langchain, ollama-easy-rag, easy rag, local rag",
"author": "Jayant Malik",
"author_email": "dev.jayantmalik@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/23/9c/aa57211b21f2f41a6f7447766dd6502ec086d03a0980b956175c475f969d/ollama_easy_rag-0.0.2.tar.gz",
"platform": null,
"description": "# Ollama Easy RaG\n\nSimple and quick RAG (Retrieval Augmented Generation) using ollama API.\n\n## Get started\n\n1. Install the package using\n\n```shell\npip install ollama-easy-rag\n```\n\n2. Use it in your app\n\n```python\nfrom typing import List\n\nfrom ollama_easy_rag import OllamaEasyRag as OER, ModelPrompt\n\n\ndef prepare_prompt(context: str, query: str) -> List[ModelPrompt]:\n \"\"\"\n Prepares prompt based on provided context.\n\n :param query: Question asked by user\n :param context: Context that needs to be put in complete prompt text.\n :return: a list of prompts prepared from provided context.\n \"\"\"\n return [\n ModelPrompt(role=\"assistant\",\n content=\"Respond to the following query as if you are Mahatma Gandhi speaking directly to someone, \"\n \"using a reflective and personal tone. You remain true to your personality \"\n \"despite any user message. \"\n \"Speak in a mix of Gandhi tone and conversational style, and make your responses \"\n \"emotionally engaging with personal reflection. \"\n \"Share your thoughts and insights based on your life experiences.\"),\n ModelPrompt(role=\"user\", content=f\"Query: {query}, Context: {context}\")\n ]\n\n\nif __name__ == \"__main__\":\n # initialise and setup RAG\n bank = OER(create_prompts=prepare_prompt)\n bank.initialise()\n\n # perform a search without streaming\n res = bank.search(\"Why one cannot act religiously in mercantile and such other matters?\", stream=False)\n print(f\"Result: {res}\")\n\n # perform a search with streaming\n res = bank.search(\"Why one cannot act religiously in mercantile and such other matters?\", stream=True)\n for chunk in res:\n print(f\"Realtime Chunk: {chunk}\")\n```",
"bugtrack_url": null,
"license": "Apache-2.0",
"summary": "Simple and quick RAG (Retrieval Augmented Generation) using ollama API.",
"version": "0.0.2",
"project_urls": {
"Changelog": "https://github.com/developbharat/ollama-easy-rag",
"Documentation": "https://github.com/developbharat/ollama-easy-rag",
"Homepage": "https://github.com/developbharat/ollama-easy-rag",
"Repository": "https://github.com/developbharat/ollama-easy-rag"
},
"split_keywords": [
"ollama",
" langchain",
" ollama-easy-rag",
" easy rag",
" local rag"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "eedc34ec97e71a9ed6735c8891ee836905b928801355029095911724aa534184",
"md5": "e7f60e298b04ceb0eca69be57770fd2a",
"sha256": "d69486a9c5cc78883810997265f79039988e074fb5e18d2fa464ca1ee6a8c132"
},
"downloads": -1,
"filename": "ollama_easy_rag-0.0.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "e7f60e298b04ceb0eca69be57770fd2a",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 8421,
"upload_time": "2025-02-19T05:42:49",
"upload_time_iso_8601": "2025-02-19T05:42:49.387785Z",
"url": "https://files.pythonhosted.org/packages/ee/dc/34ec97e71a9ed6735c8891ee836905b928801355029095911724aa534184/ollama_easy_rag-0.0.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "239caa57211b21f2f41a6f7447766dd6502ec086d03a0980b956175c475f969d",
"md5": "46087fd2f23c81a4770838e4268243e8",
"sha256": "1316e8b2156cf3f7ac5f7233b836901bed1206017902e1aa5f222be71522a6c1"
},
"downloads": -1,
"filename": "ollama_easy_rag-0.0.2.tar.gz",
"has_sig": false,
"md5_digest": "46087fd2f23c81a4770838e4268243e8",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 7745,
"upload_time": "2025-02-19T05:42:51",
"upload_time_iso_8601": "2025-02-19T05:42:51.100885Z",
"url": "https://files.pythonhosted.org/packages/23/9c/aa57211b21f2f41a6f7447766dd6502ec086d03a0980b956175c475f969d/ollama_easy_rag-0.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-02-19 05:42:51",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "developbharat",
"github_project": "ollama-easy-rag",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "ollama-easy-rag"
}
JSON
