使用 Gemma 和 Haystack 进行构建

! pip install haystack-ai "huggingface_hub>=0.22.0"

import getpass, os


os.environ["HF_API_TOKEN"] = getpass.getpass("Your Hugging Face token")

from haystack.components.generators.chat import HuggingFaceAPIChatGenerator
from haystack.dataclasses import ChatMessage

generator = HuggingFaceAPIChatGenerator(
    api_type="serverless_inference_api",
    api_params={"model": "google/gemma-7b-it"},
    generation_kwargs={"max_new_tokens": 350})

messages = []

while True:
  msg = input("Enter your message or Q to exit\n🧑 ")
  if msg=="Q":
    break
  messages.append(ChatMessage.from_user(msg))
  response = generator.run(messages=messages)
  assistant_resp = response['replies'][0]
  print("🤖 "+assistant_resp.text)
  messages.append(assistant_resp)

! pip install wikipedia

favourite_bands="""Audioslave
Blink-182
Dire Straits
Evanescence
Green Day
Muse (band)
Nirvana (band)
Sum 41
The Cure
The Smiths""".split("\n")

from IPython.display import Image
from pprint import pprint
import rich
import random

import wikipedia
from haystack.dataclasses import Document

raw_docs=[]

for title in favourite_bands:
    page = wikipedia.page(title=title, auto_suggest=False)
    doc = Document(content=page.content, meta={"title": page.title, "url":page.url})
    raw_docs.append(doc)

from haystack import Pipeline
from haystack.document_stores.in_memory import InMemoryDocumentStore
from haystack.components.preprocessors import DocumentCleaner, DocumentSplitter
from haystack.components.writers import DocumentWriter
from haystack.document_stores.types import DuplicatePolicy

document_store = InMemoryDocumentStore()

indexing = Pipeline()
indexing.add_component("cleaner", DocumentCleaner())
indexing.add_component("splitter", DocumentSplitter(split_by='sentence', split_length=2))
indexing.add_component("writer", DocumentWriter(document_store=document_store, policy=DuplicatePolicy.OVERWRITE))

indexing.connect("cleaner", "splitter")
indexing.connect("splitter", "writer")

indexing.run({"cleaner":{"documents":raw_docs}})

document_store.filter_documents()[0].meta

from haystack.components.builders import PromptBuilder

prompt_template = """
<start_of_turn>user
Using the information contained in the context, give a comprehensive answer to the question.
If the answer is contained in the context, also report the source URL.
If the answer cannot be deduced from the context, do not give an answer.

Context:
  {% for doc in documents %}
  {{ doc.content }} URL:{{ doc.meta['url'] }}
  {% endfor %};
  Question: {{query}}<end_of_turn>

<start_of_turn>model
"""
prompt_builder = PromptBuilder(template=prompt_template)

from haystack.components.generators import HuggingFaceAPIGenerator

generator = HuggingFaceAPIGenerator(
    api_type="serverless_inference_api",
    api_params={"model": "google/gemma-7b-it"},
    generation_kwargs={"max_new_tokens": 500})

from haystack.components.retrievers.in_memory import InMemoryBM25Retriever

rag = Pipeline()
rag.add_component("retriever", InMemoryBM25Retriever(document_store=document_store, top_k=5))
rag.add_component("prompt_builder", prompt_builder)
rag.add_component("llm", generator)

rag.connect("retriever.documents", "prompt_builder.documents")
rag.connect("prompt_builder.prompt", "llm.prompt")

def get_generative_answer(query):

  results = rag.run({
      "retriever": {"query": query},
      "prompt_builder": {"query": query}
    }
  )

  answer = results["llm"]["replies"][0]
  rich.print(answer)

get_generative_answer("Audioslave was formed by members of two iconic bands. Can you name the bands and discuss the sound of Audioslave in comparison?")

nice_questions_to_try="""What was the original name of Sum 41?
What was the title of Nirvana's breakthrough album released in 1991?
Green Day's "American Idiot" is a rock opera. What's the story it tells?
Audioslave was formed by members of two iconic bands. Can you name the bands and discuss the sound of Audioslave in comparison?
Evanescence's "Bring Me to Life" features a male vocalist. Who is he, and how does his voice complement Amy Lee's in the song?
What is Sum 41's debut studio album called?
Who was the lead singer of Audioslave?
When was Nirvana's first studio album, "Bleach," released?
Were the Smiths an influential band?
What is the name of Evanescence's debut album?
Which band was Morrissey the lead singer of before he formed The Smiths?
Dire Straits' hit song "Money for Nothing" features a guest vocal by a famous artist. Who is this artist?
Who played the song "Like a stone"?""".split('\n')

q=random.choice(nice_questions_to_try)
print(q)
get_generative_answer(q)