LlamaIndex

import weave
from llama_index.core.chat_engine import SimpleChatEngine

# 프로젝트 이름으로 Weave 초기화
weave.init("llamaindex_demo")

chat_engine = SimpleChatEngine.from_defaults()
response = chat_engine.chat(
    "Say something profound and romantic about fourth of July"
)
print(response)

import weave
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader

# 프로젝트 이름으로 Weave 초기화
weave.init("llamaindex_demo")

# `data` 디렉토리에 `.txt` 파일이 있다고 가정
documents = SimpleDirectoryReader("data").load_data()
index = VectorStoreIndex.from_documents(documents)

query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")
print(response)

import weave

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.core.node_parser import SentenceSplitter
from llama_index.llms.openai import OpenAI
from llama_index.core import PromptTemplate


PROMPT_TEMPLATE = """
Paul Graham에 관한 관련 정보가 제공됩니다. 제공된 정보만을 바탕으로 사용자 쿼리에 답변하세요. 내용을 지어내지 마세요.

User Query: {query_str}
Context: {context_str}
Answer:
"""

class SimpleRAGPipeline(weave.Model):
    chat_llm: str = "gpt-4"
    temperature: float = 0.1
    similarity_top_k: int = 2
    chunk_size: int = 256
    chunk_overlap: int = 20
    prompt_template: str = PROMPT_TEMPLATE

    def get_llm(self):
        return OpenAI(temperature=self.temperature, model=self.chat_llm)

    def get_template(self):
        return PromptTemplate(self.prompt_template)

    def load_documents_and_chunk(self, data):
        documents = SimpleDirectoryReader(data).load_data()
        splitter = SentenceSplitter(
            chunk_size=self.chunk_size,
            chunk_overlap=self.chunk_overlap,
        )
        nodes = splitter.get_nodes_from_documents(documents)
        return nodes

    def get_query_engine(self, data):
        nodes = self.load_documents_and_chunk(data)
        index = VectorStoreIndex(nodes)

        llm = self.get_llm()
        prompt_template = self.get_template()

        return index.as_query_engine(
            similarity_top_k=self.similarity_top_k,
            llm=llm,
            text_qa_template=prompt_template,
        )

    @weave.op()
    def predict(self, query: str):
        query_engine = self.get_query_engine(
            # 이 데이터는 weave 저장소의 data/paul_graham 경로에서 찾을 수 있습니다
            "data/paul_graham",
        )
        response = query_engine.query(query)
        return {"response": response.response}

weave.init("test-llamaindex-weave")

rag_pipeline = SimpleRAGPipeline()
response = rag_pipeline.predict("What did the author do growing up?")
print(response)

import asyncio
from llama_index.core.evaluation import CorrectnessEvaluator

eval_examples = [
    {
        "id": "0",
        "query": "What programming language did Paul Graham learn to teach himself AI when he was in college?",
        "ground_truth": "Paul Graham learned Lisp to teach himself AI when he was in college.",
    },
    {
        "id": "1",
        "query": "What was the name of the startup Paul Graham co-founded that was eventually acquired by Yahoo?",
        "ground_truth": "The startup Paul Graham co-founded that was eventually acquired by Yahoo was called Viaweb.",
    },
    {
        "id": "2",
        "query": "What is the capital city of France?",
        "ground_truth": "I cannot answer this question because no information was provided in the text.",
    },
]

llm_judge = OpenAI(model="gpt-4", temperature=0.0)
evaluator = CorrectnessEvaluator(llm=llm_judge)

@weave.op()
def correctness_evaluator(query: str, ground_truth: str, output: dict):
    result = evaluator.evaluate(
        query=query, reference=ground_truth, response=output["response"]
    )
    return {"correctness": float(result.score)}

evaluation = weave.Evaluation(dataset=eval_examples, scorers=[correctness_evaluator])

rag_pipeline = SimpleRAGPipeline()

asyncio.run(evaluation.evaluate(rag_pipeline))