This guide shows developers how to:

  1. Ingest files into your SciPhi Cloud
  2. Search over the ingested files
  3. Request or stream a RAG (Retrieval-Augmented Generation) response
  4. Use the RAG Agent for more complex, interactive queries

Be sure to complete the deployment instructions before continuing with this guide. If you would prefer to start interacting with your deployment from the cloud, then refer here.

​
Installing the R2R CLI &/or SDK

PyPi is currently the primary supported method for installing the R2R client. Similarly, the javascript client can be installed through npm, though this does not yet include a CLI.

pip install r2r

We are actively working on building more lightweight CLI options. Refer to the dedicated documentation sections for further information about the currently available options:

API Reference

Python SDK

Javascript SDK

The remainder of this quickstart will proceed with CLI commands, but all of these commands are easily reproduced inside of the Javascript or Python SDK.

​
Set your environment variable

Start by clicking the copy icon next to your deployed pipeline URL (https://sciphi-9ab60cab-0ff5-4cea-9d41-80f6d7607c3e-qwpin2swwa-ue.a.run.app in the image below) and then exporting this into your local environment variable:

export SCIPHI_CLOUD_URL=https://sciphi-7c961437-...YOUR_PIPELINE...-ue.a.run.app

Next, check that you are able to communicate with the deployment from your command line:

curl $SCIPHI_CLOUD_URL/v2/health
# {"results":{"response":"ok"}}

​
Ingesting file(s)

The following command ingests a default sample file r2r/examples/data/aristotle.txt:

r2r --base-url=$SCIPHI_CLOUD_URL ingest-sample-file

To ingest your own files, replace the file path with your desired file or directory:

r2r --base-url=$SCIPHI_CLOUD_URL ingest-files /path/to/my/files

Perform a search query:

r2r --base-url=$SCIPHI_CLOUD_URL search --query="who was aristotle?" --use-hybrid-search

​
RAG Response

Generate a RAG response:

r2r --base-url=$SCIPHI_CLOUD_URL rag --query="who was aristotle?" --use-hybrid-search

​
Stream a RAG Response

Stream a RAG response:

r2r --base-url=$SCIPHI_CLOUD_URL rag --query="who was aristotle?" --stream --use-hybrid-search

​
Using the RAG Agent

The RAG Agent provides a more interactive and intelligent way to query your knowledge base. Here’s an example of how to use it:

from r2r import R2RClient

client = R2RClient(base_url=os.environ.get("SCIPHI_CLOUD_URL"))

messages = [
    {"role": "user", "content": "What was Aristotle's main contribution to philosophy?"},
    {"role": "assistant", "content": "Aristotle made numerous significant contributions to philosophy, but one of his main contributions was in the field of logic and reasoning. He developed a system of formal logic, which is considered the first comprehensive system of its kind in Western philosophy. This system, often referred to as Aristotelian logic or term logic, provided a framework for deductive reasoning and laid the groundwork for scientific thinking."},
    {"role": "user", "content": "Can you elaborate on how this influenced later thinkers?"}
]

result = client.agent(
    messages=messages,
    vector_search_settings={"use_hybrid_search":True},
    rag_generation_config={"model": "openai/gpt-4o", "temperature": 0.7}
)

print(result['choices'][0]['message']['content'])

This example shows how to use the RAG Agent for a multi-turn conversation about Aristotle’s contributions to philosophy.

Remember to replace $SCIPHI_CLOUD_URL with your actual deployed pipeline URL in all examples.

Was this page helpful?

ProjectsSecurity