Advance Prompt Customization for Anthropic

!pip install anthropic-haystack "datasets>=2.6.1" "sentence-transformers>=3.0.0"

import os
from getpass import getpass

os.environ["ANTHROPIC_API_KEY"] = getpass("Enter the ANTHROPIC_API_KEY: ")

from datasets import load_dataset
from haystack import Document

dataset = load_dataset("bilgeyucel/seven-wonders", split="train")
docs = [Document(content=doc["content"], meta=doc["meta"]) for doc in dataset]

from haystack.document_stores.in_memory import InMemoryDocumentStore
from haystack.components.embedders import SentenceTransformersDocumentEmbedder

document_store = InMemoryDocumentStore()

doc_embedder = SentenceTransformersDocumentEmbedder(model="sentence-transformers/all-MiniLM-L6-v2")
doc_embedder.warm_up()

docs_with_embeddings = doc_embedder.run(docs)
document_store.write_documents(docs_with_embeddings["documents"])

prompt = """
Here is a document, in <document></document> XML tags:

<documents>
{% for document in documents %}
 <document index="{{loop.index}}">
  {{document.content}}
  </document>
{% endfor %}
</documents>

First, extract, word-for-word, any quotes relevant to the question, enclose the full list of quotes in <quotes></quotes> XML tags with the corresponding document index and use these quotes to an answer to the question.

If there are no quotes in this document that seem relevant to this question, please say "I can't find any relevant quotes".

Then, answer the question in <answer></answer> tags. Do not include or reference quoted content verbatim in the answer. Ensure that your answer is accurate and doesn't contain any information not directly supported by the quotes. Make references to quotes relevant to each section of the answer solely by adding their bracketed numbers at the end of relevant sentences

Here is the question: {{question}}
"""

Here is a document, in <document></document> XML tags:

<documents>
<document index="1">
  (the text content of the first document)
</document>
<document index="2">
  (the text content of the second document)
</document>
<document index="3">
  (the text content of the third document)
</document>
...
</documents>

First, extract, word-for-word, any quotes relevant to the question, enclose the full list of quotes in <quotes></quotes> XML tags with the corresponding document index and use these quotes to an answer to the question.

If there are no quotes in this document that seem relevant to this question, please say "I can't find any relevant quotes".

Then, answer the question in <answer></answer> tags. Do not include or reference quoted content verbatim in the answer. Ensure that your answer is accurate and doesn't contain any information not directly supported by the quotes. Make references to quotes relevant to each section of the answer solely by adding their bracketed numbers at the end of relevant sentences

Here is the question: (user question)

<quotes>
<quote index="1">Large numbers of people came to Ephesus in March and in the beginning of May to attend the main Artemis Procession.</quote>
<quote index="2">The Temple of Artemis or Artemision (Greek: Ἀρτεμίσιον; Turkish: Artemis Tapınağı), also known as the Temple of Diana, was a Greek temple dedicated to an ancient, local form of the goddess Artemis (identified with Diana, a Roman goddess).</quote>
</quotes>

<answer>
According to the documents, people visited the Temple of Artemis in Ephesus primarily for religious reasons to attend festivals and processions dedicated to the goddess Artemis (also known as Diana). The temple was dedicated to an ancient local form of the goddess and held a main Artemis Procession in March and early May that drew large crowds. [1] The temple was considered an important religious site for the worship of Artemis in the Greek world. [2] People likely traveled there to make offerings, participate in rituals, and celebrate the goddess during major festivals and ceremonies held at the sacred site.
</answer>

from haystack.components.builders import DynamicChatPromptBuilder
from haystack_integrations.components.generators.anthropic import AnthropicChatGenerator
from haystack.dataclasses import ChatMessage
from haystack.components.embedders import SentenceTransformersTextEmbedder
from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever

text_embedder = SentenceTransformersTextEmbedder(model="sentence-transformers/all-MiniLM-L6-v2")
retriever = InMemoryEmbeddingRetriever(document_store)

messages = [
    ChatMessage.from_system("You are an expert who answers questions based on the given documents."),
    ChatMessage.from_user(prompt),
]

prompt_builder = DynamicChatPromptBuilder(runtime_variables=["documents"])
llm = AnthropicChatGenerator(model="claude-3-sonnet-20240229")

from haystack import Pipeline

rag_with_quotes = Pipeline()
# Add components to your pipeline
rag_with_quotes.add_component("text_embedder", text_embedder)
rag_with_quotes.add_component("retriever", retriever)
rag_with_quotes.add_component("prompt_builder", prompt_builder)
rag_with_quotes.add_component("llm", llm)

# Now, connect the components to each other
rag_with_quotes.connect("text_embedder.embedding", "retriever.query_embedding")
rag_with_quotes.connect("retriever", "prompt_builder.documents")
rag_with_quotes.connect("prompt_builder", "llm")

question = "Why were people visiting the Temple of Artemis?" # @param ["Why were people visiting the Temple of Artemis?", "How did Colossus of Rhodes collapse?", "What is the importance of Colossus of Rhodes?", "Why did people build Great Pyramid of Giza?", "What does Rhodes Statue look like?"]

result = rag_with_quotes.run(
    data={
        "text_embedder" : {"text": question},
        "retriever" : {"top_k": 5},
        "prompt_builder": {"template_variables": {"question": question}, "prompt_source": messages},
    }
)

print(result["llm"]["replies"][0].content)

import re

re.findall(r'<quote .*?>([\s\S]*?)<\/quote>', result["llm"]["replies"][0].content)

import re

re.findall(r'<answer>([\s\S]*?)<\/answer>', result["llm"]["replies"][0].content)