Haystack框架部署与初步使用记录

pip install haystack-ai

from openai import OpenAI

# deepseek-API
client = OpenAI(
    api_key="sk-xxx",
    base_url="https://api.siliconflow.cn/v1"
)

response = client.chat.completions.create(
    # model="gpt-3.5-turbo",
    model="deepseek-ai/DeepSeek-V3",
    messages=[{"role": "user", "content": "HI"}]
)
print(response.choices[0].message.content)

from haystack import Pipeline, Document
from haystack.utils import Secret
from haystack.document_stores.in_memory import InMemoryDocumentStore
from haystack.components.retrievers.in_memory import InMemoryBM25Retriever
from haystack.components.generators.chat import OpenAIChatGenerator
from haystack.components.builders.chat_prompt_builder import ChatPromptBuilder
from haystack.dataclasses import ChatMessage

# Write documents to InMemoryDocumentStore
document_store = InMemoryDocumentStore()
document_store.write_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.")
])

# Build a RAG pipeline
prompt_template = [
    ChatMessage.from_system("You are a helpful assistant."),
    ChatMessage.from_user(
        "Given these documents, answer the question.\n"
        "Documents:\n{% for doc in documents %}{{ doc.content }}{% endfor %}\n"
        "Question: {{question}}\n"
        "Answer:"
    )
]

# Define required variables explicitly
prompt_builder = ChatPromptBuilder(template=prompt_template, required_variables={"question", "documents"})

retriever = InMemoryBM25Retriever(document_store=document_store)

llm = OpenAIChatGenerator(api_key=Secret.from_token("sk-xxx"),
                          model="deepseek-ai/DeepSeek-V3",
                          api_base_url="https://api.siliconflow.cn/v1")

rag_pipeline = Pipeline()
rag_pipeline.add_component("retriever", retriever)
rag_pipeline.add_component("prompt_builder", prompt_builder)
rag_pipeline.add_component("llm", llm)
rag_pipeline.connect("retriever", "prompt_builder.documents")
rag_pipeline.connect("prompt_builder", "llm.messages")

# Ask a question
question = "Who lives in Rome?"
results = rag_pipeline.run(
    {
        "retriever": {"query": question},
        "prompt_builder": {"question": question},
    }
)

print(results["llm"]["replies"])