mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-07-14 04:20:38 +00:00
7cc6080dfa
* replace metadata w meta in tests/examples * do not touch already broken e2e tests * Revert "do not touch already broken e2e tests" This reverts commit 1f911920d98954b57daacfe8d8ed02fd77d136db.
52 lines
2.3 KiB
Python
52 lines
2.3 KiB
Python
import os
|
|
from haystack import Pipeline, Document
|
|
from haystack.document_stores import InMemoryDocumentStore
|
|
from haystack.components.retrievers import InMemoryBM25Retriever
|
|
from haystack.components.generators import GPTGenerator
|
|
from haystack.components.builders.answer_builder import AnswerBuilder
|
|
from haystack.components.builders.prompt_builder import PromptBuilder
|
|
|
|
# We are model agnostic :) Here, we use OpenAI models and load an api key from environment variables.
|
|
OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY")
|
|
|
|
# We support many different databases. Here we load a simple and lightweight in-memory document store.
|
|
document_store = InMemoryDocumentStore()
|
|
|
|
# Create some example documents and add them to the document store.
|
|
documents = [
|
|
Document(content="My name is Jean and I live in Paris."),
|
|
Document(content="My name is Mark and I live in Berlin."),
|
|
Document(content="My name is Giorgio and I live in Rome."),
|
|
]
|
|
document_store.write_documents(documents)
|
|
|
|
# Build a RAG pipeline with a Retriever to get relevant documents to the query and a GPTGenerator interacting with LLMs using a custom prompt.
|
|
prompt_template = """
|
|
Given these documents, answer the question.\nDocuments:
|
|
{% for doc in documents %}
|
|
{{ doc.content }}
|
|
{% endfor %}
|
|
|
|
\nQuestion: {{question}}
|
|
\nAnswer:
|
|
"""
|
|
rag_pipeline = Pipeline()
|
|
rag_pipeline.add_component(instance=InMemoryBM25Retriever(document_store=document_store), name="retriever")
|
|
rag_pipeline.add_component(instance=PromptBuilder(template=prompt_template), name="prompt_builder")
|
|
rag_pipeline.add_component(instance=GPTGenerator(api_key=OPENAI_API_KEY), name="llm")
|
|
rag_pipeline.add_component(instance=AnswerBuilder(), name="answer_builder")
|
|
rag_pipeline.connect("retriever", "prompt_builder.documents")
|
|
rag_pipeline.connect("prompt_builder", "llm")
|
|
rag_pipeline.connect("llm.replies", "answer_builder.replies")
|
|
rag_pipeline.connect("llm.meta", "answer_builder.meta")
|
|
rag_pipeline.connect("retriever", "answer_builder.documents")
|
|
|
|
# Ask a question on the data you just added.
|
|
question = "Where does Mark live?"
|
|
result = rag_pipeline.run(
|
|
{"retriever": {"query": question}, "prompt_builder": {"question": question}, "answer_builder": {"query": question}}
|
|
)
|
|
|
|
# For details, like which documents were used to generate the answer, look into the GeneratedAnswer object
|
|
print(result["answer_builder"]["answers"])
|