Retrieval-Augmented Generation (RAG) con Milvus y Haystack

Esta guía muestra cómo construir un sistema de Generación Aumentada por Recuperación (RAG) utilizando Haystack y Milvus.

El sistema RAG combina un sistema de recuperación con un modelo generativo para generar texto nuevo basado en una petición dada. En primer lugar, el sistema recupera documentos relevantes de un corpus utilizando Milvus y, a continuación, utiliza un modelo generativo para generar un nuevo texto basado en los documentos recuperados.

Haystack es el framework de código abierto en Python de deepset para crear aplicaciones personalizadas con grandes modelos lingüísticos (LLM). Milvus es la base de datos vectorial de código abierto más avanzada del mundo, creada para potenciar la búsqueda de similitudes incrustadas y las aplicaciones de IA.

Requisitos previos

Antes de ejecutar este cuaderno, asegúrate de tener instaladas las siguientes dependencias:

! pip install --upgrade --quiet pymilvus milvus-haystack markdown-it-py mdit_plain

Utilizaremos los modelos de OpenAI. Debes preparar la clave api OPENAI_API_KEY como variable de entorno.

import os

os.environ["OPENAI_API_KEY"] = "sk-***********"

Preparar los datos

Utilizamos un contenido online sobre Leonardo Da Vinci como almacén de conocimiento privado para nuestro pipeline RAG, que es una buena fuente de datos para un pipeline RAG sencillo.

Descárgalo y guárdalo como archivo de texto local.

import os
import urllib.request

url = "https://www.gutenberg.org/cache/epub/7785/pg7785.txt"
file_path = "./davinci.txt"

if not os.path.exists(file_path):
    urllib.request.urlretrieve(url, file_path)

Crear el proceso de indexación

Cree un proceso de indexación que convierta el texto en documentos, los divida en frases y los incorpore. A continuación, los documentos se escriben en el almacén de documentos de Milvus.

from haystack import Pipeline
from haystack.components.converters import MarkdownToDocument
from haystack.components.embedders import OpenAIDocumentEmbedder, OpenAITextEmbedder
from haystack.components.preprocessors import DocumentSplitter
from haystack.components.writers import DocumentWriter
from haystack.utils import Secret

from milvus_haystack import MilvusDocumentStore
from milvus_haystack.milvus_embedding_retriever import MilvusEmbeddingRetriever


document_store = MilvusDocumentStore(
    connection_args={"uri": "./milvus.db"},
    # connection_args={"uri": "http://localhost:19530"},
    # connection_args={"uri": YOUR_ZILLIZ_CLOUD_URI, "token": Secret.from_env_var("ZILLIZ_CLOUD_API_KEY")},
    drop_old=True,
)

indexing_pipeline = Pipeline()
indexing_pipeline.add_component("converter", MarkdownToDocument())
indexing_pipeline.add_component(
    "splitter", DocumentSplitter(split_by="sentence", split_length=2)
)
indexing_pipeline.add_component("embedder", OpenAIDocumentEmbedder())
indexing_pipeline.add_component("writer", DocumentWriter(document_store))
indexing_pipeline.connect("converter", "splitter")
indexing_pipeline.connect("splitter", "embedder")
indexing_pipeline.connect("embedder", "writer")
indexing_pipeline.run({"converter": {"sources": [file_path]}})

print("Number of documents:", document_store.count_documents())

Converting markdown files to Documents: 100%|█| 1/
Calculating embeddings: 100%|█| 9/9 [00:05<00:00, 
E20240516 10:40:32.945937 5309095 milvus_local.cpp:189] [SERVER][GetCollection][] Collecton HaystackCollection not existed
E20240516 10:40:32.946677 5309095 milvus_local.cpp:189] [SERVER][GetCollection][] Collecton HaystackCollection not existed
E20240516 10:40:32.946704 5309095 milvus_local.cpp:189] [SERVER][GetCollection][] Collecton HaystackCollection not existed
E20240516 10:40:32.946725 5309095 milvus_local.cpp:189] [SERVER][GetCollection][] Collecton HaystackCollection not existed


Number of documents: 277

Crear la canalización de recuperación

Cree una canalización de recuperación que recupere documentos del almacén de documentos de Milvus utilizando un motor de búsqueda de similitud vectorial.

question = 'Where is the painting "Warrior" currently stored?'

retrieval_pipeline = Pipeline()
retrieval_pipeline.add_component("embedder", OpenAITextEmbedder())
retrieval_pipeline.add_component(
    "retriever", MilvusEmbeddingRetriever(document_store=document_store, top_k=3)
)
retrieval_pipeline.connect("embedder", "retriever")

retrieval_results = retrieval_pipeline.run({"embedder": {"text": question}})

for doc in retrieval_results["retriever"]["documents"]:
    print(doc.content)
    print("-" * 10)

). The
composition of this oil-painting seems to have been built up on the
second cartoon, which he had made some eight years earlier, and which
was apparently taken to France in 1516 and ultimately lost.
----------

This "Baptism of Christ," which is now in the Accademia in Florence
and is in a bad state of preservation, appears to have been a
comparatively early work by Verrocchio, and to have been painted
in 1480-1482, when Leonardo would be about thirty years of age.

To about this period belongs the superb drawing of the "Warrior," now
in the Malcolm Collection in the British Museum.
----------
" Although he
completed the cartoon, the only part of the composition which he
eventually executed in colour was an incident in the foreground
which dealt with the "Battle of the Standard." One of the many
supposed copies of a study of this mural painting now hangs on the
south-east staircase in the Victoria and Albert Museum.
----------

Crear la canalización RAG

Cree una canalización RAG que combine el MilvusEmbeddingRetriever y el OpenAIGenerator para responder a la pregunta utilizando los documentos recuperados.

from haystack.utils import Secret
from haystack.components.builders import PromptBuilder
from haystack.components.generators import OpenAIGenerator

prompt_template = """Answer the following query based on the provided context. If the context does
                     not include an answer, reply with 'I don't know'.\n
                     Query: {{query}}
                     Documents:
                     {% for doc in documents %}
                        {{ doc.content }}
                     {% endfor %}
                     Answer:
                  """

rag_pipeline = Pipeline()
rag_pipeline.add_component("text_embedder", OpenAITextEmbedder())
rag_pipeline.add_component(
    "retriever", MilvusEmbeddingRetriever(document_store=document_store, top_k=3)
)
rag_pipeline.add_component("prompt_builder", PromptBuilder(template=prompt_template))
rag_pipeline.add_component(
    "generator",
    OpenAIGenerator(
        api_key=Secret.from_token(os.getenv("OPENAI_API_KEY")),
        generation_kwargs={"temperature": 0},
    ),
)
rag_pipeline.connect("text_embedder.embedding", "retriever.query_embedding")
rag_pipeline.connect("retriever.documents", "prompt_builder.documents")
rag_pipeline.connect("prompt_builder", "generator")

results = rag_pipeline.run(
    {
        "text_embedder": {"text": question},
        "prompt_builder": {"query": question},
    }
)
print("RAG answer:", results["generator"]["replies"][0])

RAG answer: The painting "Warrior" is currently stored in the Malcolm Collection in the British Museum.

Para más información sobre cómo utilizar milvus-haystack, consulte el Léame de milvus-haystack.