Quickstart

This guide shows how to use R2R to:

Ingest files into your Postgres vector database
Search over ingested files
Create a RAG (Retrieval-Augmented Generation) response

Be sure to complete the installation instructions before continuing with this guide.

Starting the server

R2R methods can be called directly r2r.method(...) instead of in a client-server architecture. See the full walkthrough for details on this and more.

You can start the R2R server using the R2R CLI, Python or Docker:

r2r serve --port=8000

r2r/examples/quickstart.py

    class R2RQuickstart:
        def __init__(
            self,
            client_server_mode=False,
            base_url="http://localhost:8000",
        ):
            # Optional - pass a `config_path` to `from_json` to override default `config.json`
            config = R2RConfig.from_json()

            self.client_server_mode = client_server_mode
            if client_server_mode:
                self.client = R2RClient(base_url)
            else:
                self.app = R2R(config=config)

        def serve(self) -> None:
            if self.client_server_mode:
                raise ValueError("Cannot start server in client-server mode")
            self.app.serve()

Ingesting file(s)

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

r2r ingest

{'results': {'processed_documents': ["File '.../aristotle.txt' processed successfully."], 'skipped_documents': []}}

To run on your own selected files, execute the following:

r2r ingest /path/to/your_file_1 /path/to/your_file_2 ...

r2r/examples/quickstart.py

    class R2RQuickstart:
        ...
        def ingest(self, files: list[str] = None) -> None:
            files = files.split(",") if files else [DEFAULT_INGESTION_FILE]
            if not self.client_server_mode:
                # Parse each input file into an R2R document
                # each document is given a deterministic id
                documents = [
                    Document(
                        type=DocumentType(file.split(".")[-1]),
                        data=open(file, "rb").read(),
                        metadata={},
                    )
                    for file in files
                ]
                result = self.app.ingest_documents(documents)
            else:
                result = self.client.ingest_files(files)
            print(result)

Executing a search

The following command returns the search results from the input query 'who was aristotle?':

# execute with hybrid search
r2r search --query="who was aristotle?" --do-hybrid-search

{'results': {'vector_search_results': [
    {
        'id': '7ed3a01c-88dc-5a58-a68b-6e5d9f292df2', 
        'score': 0.780314067545999, 
        'metadata': {
            'text': 'Aristotle[A] (Greek: Ἀριστοτέλης Aristotélēs, pronounced [aristotélɛːs]; 384–322 BC) was an Ancient Greek philosopher and polymath. His writings cover a broad range of subjects spanning the natural sciences, philosophy, linguistics, economics, politics, psychology, and the arts. As the founder of the Peripatetic school of philosophy in the Lyceum in Athens, he began the wider Aristotelian tradition that followed, which set the groundwork for the development of modern science.', 
            'title': 'aristotle.txt', 
            'version': 'v0', 
            'chunk_order': 0, 
            'document_id': 'c9bdbac7-0ea3-5c9e-b590-018bd09b127b', 
            'extraction_id': '472d6921-b4cd-5514-bf62-90b05c9102cb',
            ...

r2r/examples/quickstart.py > search

def search(self, query: str) -> None:
    if not self.client_server_mode:
        # use the R2R instance directly
        result = self.app.search(query)
    else:
        result = self.client.search(query)
    print(result)

RAG Response

The following command generates a RAG response to the input query 'who was aristotle?':

r2r rag --query="who was aristotle?" --do-hybrid-search

Search Results:
{'vector_search_results': [
    {'id': '7ed3a01c-88dc-5a58-a68b-6e5d9f292df2', 
    'score': 0.7802911996841491, 
    'metadata': {'text': 'Aristotle[A] (Greek: Ἀριστοτέλης Aristotélēs, pronounced [aristotélɛːs]; 384–322 BC) was an Ancient Greek philosopher and polymath. His writings cover a broad range of subjects spanning the natural sciences, philosophy, linguistics, economics, politics, psychology, and the arts. As the founder of the Peripatetic schoo
    ...
Completion:
{'results': [
    {
        'id': 'chatcmpl-9eXL6sKWlUkP3f6QBnXvEiKkWKBK4', 
        'choices': [
            {
                'finish_reason': 'stop', 
                'index': 0, 
                'logprobs': None, 
                'message': {
                    'content': "Aristotle (384–322 BC) was an Ancient Greek philosopher and polymath whose writings covered a broad range of subjects including the natural sciences, 
                    ...

r2r/examples/quickstart.py > rag

def rag(self, query: str, model: Optional[str] = "gpt-4o") -> None:
    if not self.client_server_mode:
        result = self.app.rag(query, GenerationConfig(model=model))
    else:
        result = self.client.rag(
            query, rag_generation_config=GenerationConfig(model=model)
        )
    print(result)

Stream a RAG Response

The following command streams a RAG response to the input query 'who was aristotle?':

r2r rag --query="who was aristotle?" --stream --do-hybrid-search

Hello R2R

R2R supports configurable vector search and RAG right out of the box, as the example below shows:


from r2r import Document, GenerationConfig, R2R

app = R2R() # You may pass a custom configuration to `R2R`

app.ingest_documents(
    [
        Document(
            type="txt",
            data="John is a person that works at Google.",
            metadata={},
        )
    ]
)

rag_results = app.rag(
    "Who is john", GenerationConfig(model="gpt-3.5-turbo", temperature=0.0)
)
print(f"Search Results:\n{rag_results.search_results}")
print(f"Completion:\n{rag_results.completion}")

# RAG Results:
# Search Results:
# AggregateSearchResult(vector_search_results=[VectorSearchResult(id=2d71e689-0a0e-5491-a50b-4ecb9494c832, score=0.6848798582029441, metadata={'text': 'John is a person that works at Google.', 'version': 'v0', 'chunk_order': 0, 'document_id': 'ed76b6ee-dd80-5172-9263-919d493b439a', 'extraction_id': '1ba494d7-cb2f-5f0e-9f64-76c31da11381', 'associatedQuery': 'Who is john'})], kg_search_results=None)
# Completion:
# ChatCompletion(id='chatcmpl-9g0HnjGjyWDLADe7E2EvLWa35cMkB', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content='John is a person that works at Google [1].', role='assistant', function_call=None, tool_calls=None))], created=1719797903, model='gpt-3.5-turbo-0125', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=11, prompt_tokens=145, total_tokens=156))

Get Started

RAG Cookbooks

App Features

Deep Dive

Starting the server

Ingesting file(s)

Executing a search

RAG Response

Stream a RAG Response

Hello R2R

Get Started

RAG Cookbooks

App Features

Deep Dive

​Starting the server

​Ingesting file(s)

​Executing a search

​RAG Response

​Stream a RAG Response

​Hello R2R

Starting the server

Ingesting file(s)

Executing a search

RAG Response

Stream a RAG Response

Hello R2R