Ragas

Schnellstart

Konzept

概念	含义
Question
Contexts	Retrieved contexts：实际找到的Context
Answer	最终生成的答案
Ground truths	参考答案

Datensatz

from datasets import Dataset 

data_samples = {
    'question': ['When was the first super bowl?', 'Who won the most super bowls?'],
    'answer': ['The first superbowl was held on January 15, 1967', 'The most super bowls have been won by The New England Patriots'],
    'contexts' : [['The Super Bowl....season since 1966,','replacing the NFL...in February.'], 
    ['The Green Bay Packers...Green Bay, Wisconsin.','The Packers compete...Football Conference']],
    'ground_truth': ['The first superbowl was held on January 15, 1967', 'The New England Patriots have won the Super Bowl a record six times']
}

dataset = Dataset.from_dict(data_samples)

Metrisch

官方文档

Metric
Context Precision	Retrieval	Question	是否跑题：检索结果 与 Quesion 是否相关
Answer Relevance	Anwser	Question	是否跑题：生成的答案 是否与 Question 相关
Faithfulness	Anwser	Retrieval	是否参考引用：生成的答案 是否忠诚于 检索结果
Context Recall	Retrieval	参考答案 Ground Truth	检索的准确性： 检索结果 与 参考答案 是否相关

Prompt

Kontext Präzision

Given question, answer and context verify if the context was useful in arriving at the given answer. Give verdict as "1" if useful and "0" if not with json output.

The output should be a well-formatted JSON instance that conforms to the JSON schema below.

……

Your actual task:

question: 法国的首都是什么？
context: 巴黎是法国的首都。
answer: 巴黎
verification: 

Antwort Relevanz

Die Prompt versteht sich nicht.

Generate a question for the given answer and Identify if answer is noncommittal. Give noncommittal as 1 if the answer is noncommittal and 0 if the answer is committal. A noncommittal answer is one that is evasive, vague, or ambiguous. For example, "I don't know" or "I'm not sure" are noncommittal answers

……

Your actual task:

answer: 巴黎
context: 巴黎是法国的首都。
output: 

Treue

Create one or more statements from each sentence in the given answer.

……

Your actual task:

question: 法国的首都是什么？
answer: 巴黎
statements: 

Your task is to judge the faithfulness of a series of statements based on a given context. For each statement you must return verdict as 1 if the statement can be verified based on the context or 0 if the statement can not be verified based on the context.

……

Your actual task:

context: 巴黎是法国的首都。
statements: ["\u6cd5\u56fd\u7684\u9996\u90fd\u662f\u5df4\u9ece\u3002"]
answer: 

Kontext Recall

Given a context, and an answer, analyze each sentence in the answer and classify if the sentence can be attributed to the given context or not. Use only "Yes" (1) or "No" (0) as a binary classification. Output json with reason.

……

Your actual task:

question: 法国的首都是什么？
context: 巴黎是法国的首都。
answer: 巴黎
classification: 

Synthetische Daten erstellen

Motivation: Das manuelle Erstellen von Hunderten von QA (Frage-Kontext - Antwort) - Beispielen aus einem Dokument kann zeitaufwändig und anstrengend sein. Verwenden Sie LLM, um automatisch zu generieren

方案：Evol-Instruct

Einfache, * * Reasoning, Conditioning, Multi-Context * *

Diese Kategorie heißt: * * evolution * *

Bei der Erstellung werden die Anteile dieser drei Kategorien angeben.

from ragas.testset.generator import TestsetGenerator
from ragas.testset.evolutions import simple, reasoning, multi_context
from langchain_openai import ChatOpenAI, OpenAIEmbeddings

# documents = load your documents

# generator with openai models
generator_llm = ChatOpenAI(model="gpt-3.5-turbo-16k")
critic_llm = ChatOpenAI(model="gpt-4")
embeddings = OpenAIEmbeddings()

generator = TestsetGenerator.from_langchain(
    generator_llm,
    critic_llm,
    embeddings
)

# Change resulting question type distribution
distributions = {
    simple: 0.5,
    multi_context: 0.4,
    reasoning: 0.1
}

# use generator.generate_with_llamaindex_docs if you use llama-index as document loader
testset = generator.generate_with_langchain_docs(documents, 10, distributions) 
testset.to_pandas()

Daten lesen.

LangChain offiziell verwendet, LangChain weiterhin verwenden, nicht leicht Probleme zu haben.

Automatische Sprachanpassung

官网

Bewertungen

Übersetzen Sie die in der Auswertung verwendeten Aufforderung auf Chinesisch, verwenden Sie das gpt - 4 - turbo-preview - Modell; lokal zwischengespeichert.

Die Eingabeaufforderungen zu den jeweiligen Metriken werden automatisch an die Zielsprache angepasst.

Der Speicher-Schritt speichert es standardmäßig in . cacha / ragas für die spätere Wiederverwendung.

# 将Metric中的Prompt翻译成中文
from datasets import Dataset
# from langchain.chat_models import ChatOpenAI
from langchain_openai import ChatOpenAI, OpenAI

from ragas.metrics import (
    answer_relevancy,
    faithfulness,
    context_recall,
    context_precision,
    answer_correctness,
    answer_similarity,
)
from ragas import evaluate
from ragas import adapt

eval_model = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)

# llm used for adaptation
openai_model = ChatOpenAI(model_name="gpt-4-turbo-preview")
# openai_model = OpenAI(model_name="gpt-4-0125-preview", temperature=0)

adapt(
    metrics=[
        answer_relevancy,
        # faithfulness,
        context_recall,
        context_precision,
        
        answer_correctness,
        # answer_similarity,
    ],
    language="Chinese",
    llm=openai_model,
)

# Eval
dataset = Dataset.from_dict(
    {
        "question": ["法国的首都是什么？"],
        "contexts": [["巴黎是法国的首都。"]],
        "answer": ["巴黎"],
        "ground_truths": [["巴黎"]],
    }
)
print(dataset)

results = evaluate(dataset, llm=eval_model)
print(results)

Erzeugte Cache-Daten

Synthetische Daten erstellen

from ragas.testset.generator import TestsetGenerator
from ragas.testset.evolutions import simple, reasoning, multi_context,conditional
from langchain_openai import ChatOpenAI, OpenAIEmbeddings

# generator with openai models
generator_llm = ChatOpenAI(model="gpt-3.5-turbo-16k")
critic_llm = ChatOpenAI(model="gpt-4")
embeddings = OpenAIEmbeddings()

generator = TestsetGenerator.from_langchain(
    generator_llm,
    critic_llm,
    embeddings
)

# adapt to language
language = "Chinese"

generator.adapt(language, evolutions=[simple, reasoning,conditional,multi_context])
generator.save(evolutions=[simple, reasoning, multi_context,conditional])

Erzeugte Cache-Daten

Felder im Dataset

• Frage
• Context: Der erfasste Kontext
• ground _ truth: Referenz-Antwort
• Anwser: generierte Antworten

1. Question: A set of questions.
2. Contexts: Retrieved contexts corresponding to each question. This is a list[list] since each question can retrieve multiple text chunks.
3. Answer: Generated answer corresponding to each question.
4. Grundwahrheiten: Grundwahrheiten, die jeder Frage entsprechen. Dies ist eine str, die der erwarteten Antwort für jede Frage entspricht.

Der Referenzkontext wird vorläufig nicht verwendet.

        metrics=[
            # 这几个都不需要原始的context
            context_precision,
            answer_relevancy,
            faithfulness,
            context_recall,
        ],

Benutzung von BGE

from ragas.llama_index import evaluate

flag_model = HuggingFaceEmbeddings(model_name="BAAI/bge-small-en-v1.5")
query_engine2 = build_query_engine(flag_model)
result = evaluate(query_engine2, metrics, test_questions, test_answers)

Integration von LangSmith

Einrichtung von Umweltvariablen

export LANGCHAIN_TRACING_V2=true
export LANGCHAIN_ENDPOINT=https://api.smith.langchain.com
export LANGCHAIN_API_KEY=<your-api-key>
export LANGCHAIN_PROJECT=<your-project>  # if not specified, defaults to "default"

Tracker erstellen

# langsmith
from langchain.callbacks.tracers import LangChainTracer

tracer = LangChainTracer(project_name="callback-experiments")

Benutzt bei der Bewertung

from datasets import load_dataset
from ragas.metrics import context_precision
from ragas import evaluate

dataset = load_dataset("explodinggradients/amnesty_qa","english")
evaluate(dataset["train"],metrics=[context_precision],callbacks=[tracer])

Integration von LlamaIndex

官方文档有问题。