Skip to main content
Open In ColabOpen on GitHub
Open In Colab

UpTrain

UpTrain [github || website || docs] 是一个开源平台，用于评估和改进LLM应用程序。它提供了20多个预配置检查的评分（涵盖语言、代码、嵌入用例），对失败案例的实例进行根本原因分析，并提供解决这些问题的指导。

UpTrain 回调处理程序​

本笔记本展示了UpTrain回调处理程序无缝集成到您的管道中，促进多样化的评估。我们选择了一些我们认为适合评估链的评估。这些评估会自动运行，结果在输出中显示。有关UpTrain评估的更多详细信息，请参见此处。

从Langchain中选择的接收器被突出显示以进行演示：

1. Vanilla RAG:​

RAG 在检索上下文和生成响应中起着至关重要的作用。为了确保其性能和响应质量，我们进行以下评估：

2. 多查询生成:​

MultiQueryRetriever 创建了多个与原问题意义相似的问题变体。鉴于复杂性，我们包含了之前的评估并添加了：

3. 上下文压缩和重新排序:​

重新排序涉及根据与查询的相关性重新排序节点并选择前n个节点。由于重新排序完成后节点数量可能会减少，我们执行以下评估：

  • Context Reranking: 检查重新排序的节点顺序是否比原始顺序更符合查询。
  • Context Conciseness: 检查减少的节点数量是否仍能提供所有所需信息。

这些评估共同确保了链中RAG、MultiQueryRetriever和重排序过程的鲁棒性和有效性。

安装依赖​

%pip install -qU langchain langchain_openai langchain-community uptrain faiss-cpu flashrank
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
``````output
WARNING: There was an error checking the latest version of pip.
Note: you may need to restart the kernel to use updated packages.

注意：如果你想使用支持GPU的库版本，你也可以安装faiss-gpu而不是faiss-cpu。

导入库​

from getpass import getpass

from langchain.chains import RetrievalQA
from langchain.retrievers import ContextualCompressionRetriever
from langchain.retrievers.document_compressors import FlashrankRerank
from langchain.retrievers.multi_query import MultiQueryRetriever
from langchain_community.callbacks.uptrain_callback import UpTrainCallbackHandler
from langchain_community.document_loaders import TextLoader
from langchain_community.vectorstores import FAISS
from langchain_core.output_parsers.string import StrOutputParser
from langchain_core.prompts.chat import ChatPromptTemplate
from langchain_core.runnables.passthrough import RunnablePassthrough
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_text_splitters import (
    RecursiveCharacterTextSplitter,
)

加载文档​

loader = TextLoader("../../how_to/state_of_the_union.txt")
documents = loader.load()

将文档分割成块​

text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
chunks = text_splitter.split_documents(documents)

创建检索器​

embeddings = OpenAIEmbeddings()
db = FAISS.from_documents(chunks, embeddings)
retriever = db.as_retriever()

定义LLM​

llm = ChatOpenAI(temperature=0, model="gpt-4")

设置​

UpTrain 为您提供：

  1. 具有高级钻取和筛选选项的仪表板
  2. 失败案例中的洞察和常见主题
  3. 生产数据的可观测性和实时监控
  4. 通过与您的CI/CD管道无缝集成进行回归测试

您可以选择以下选项来使用UpTrain进行评估：

1. UpTrain的开源软件（OSS）:​

您可以使用开源评估服务来评估您的模型。在这种情况下，您需要提供一个OpenAI API密钥。UpTrain使用GPT模型来评估由LLM生成的响应。您可以在这里获取您的密钥。

为了在UpTrain仪表板中查看您的评估，您需要通过运行以下命令来设置它：

git clone https://github.com/uptrain-ai/uptrain
cd uptrain
bash run_uptrain.sh

这将在您的本地机器上启动UpTrain仪表板。您可以在http://localhost:3000/dashboard访问它。

参数:

  • key_type="openai"
  • api_key="OPENAI_API_KEY"
  • 项目名称="PROJECT_NAME"

2. UpTrain 托管服务和仪表板:​

或者，您可以使用UpTrain的托管服务来评估您的模型。您可以在这里创建一个免费的UpTrain账户并获得免费试用积分。如果您想要更多的试用积分，请在这里与UpTrain的维护者预约通话。

使用托管服务的好处是：

  1. 无需在本地机器上设置UpTrain仪表板。
  2. 无需API密钥即可访问许多LLMs。

一旦你执行了评估，你可以在UpTrain仪表板中查看它们，地址为https://dashboard.uptrain.ai/dashboard

参数:

  • key_type="uptrain"
  • api_key="UPTRAIN_API_KEY"
  • 项目名称="PROJECT_NAME"

注意： project_name 将是在 UpTrain 仪表板中显示评估结果的项目名称。

设置API密钥​

笔记本将提示您输入API密钥。您可以通过更改下面单元格中的key_type参数来选择使用OpenAI API密钥或UpTrain API密钥。

KEY_TYPE = "openai"  # or "uptrain"
API_KEY = getpass()

1. 基础RAG

UpTrain回调处理程序将自动捕获生成的查询、上下文和响应，并将在响应上运行以下三个评估（评分从0到1）：

# Create the RAG prompt
template = """Answer the question based only on the following context, which can include text and tables:
{context}
Question: {question}
"""
rag_prompt_text = ChatPromptTemplate.from_template(template)

# Create the chain
chain = (
    {"context": retriever, "question": RunnablePassthrough()}
    | rag_prompt_text
    | llm
    | StrOutputParser()
)

# Create the uptrain callback handler
uptrain_callback = UpTrainCallbackHandler(key_type=KEY_TYPE, api_key=API_KEY)
config = {"callbacks": [uptrain_callback]}

# Invoke the chain with a query
query = "What did the president say about Ketanji Brown Jackson"
docs = chain.invoke(query, config=config)
2024-04-17 17:03:44.969 | INFO     | uptrain.framework.evalllm:evaluate_on_server:378 - Sending evaluation request for rows 0 to <50 to the Uptrain
2024-04-17 17:04:05.809 | INFO     | uptrain.framework.evalllm:evaluate:367 - Local server not running, start the server to log data and visualize in the dashboard!
``````output

Question: What did the president say about Ketanji Brown Jackson
Response: The president mentioned that he had nominated Ketanji Brown Jackson to serve on the United States Supreme Court 4 days ago. He described her as one of the nation's top legal minds who will continue Justice Breyer’s legacy of excellence. He also mentioned that she is a former top litigator in private practice, a former federal public defender, and comes from a family of public school educators and police officers. He described her as a consensus builder and noted that since her nomination, she has received a broad range of support from various groups, including the Fraternal Order of Police and former judges appointed by both Democrats and Republicans.

Context Relevance Score: 1.0
Factual Accuracy Score: 1.0
Response Completeness Score: 1.0

2. 多查询生成

MultiQueryRetriever 用于解决 RAG 管道可能无法根据查询返回最佳文档集的问题。它生成多个与原始查询意思相同的查询，然后为每个查询获取文档。

为了评估这个检索器，UpTrain 将运行以下评估：

# Create the retriever
multi_query_retriever = MultiQueryRetriever.from_llm(retriever=retriever, llm=llm)

# Create the uptrain callback
uptrain_callback = UpTrainCallbackHandler(key_type=KEY_TYPE, api_key=API_KEY)
config = {"callbacks": [uptrain_callback]}

# Create the RAG prompt
template = """Answer the question based only on the following context, which can include text and tables:
{context}
Question: {question}
"""
rag_prompt_text = ChatPromptTemplate.from_template(template)

chain = (
    {"context": multi_query_retriever, "question": RunnablePassthrough()}
    | rag_prompt_text
    | llm
    | StrOutputParser()
)

# Invoke the chain with a query
question = "What did the president say about Ketanji Brown Jackson"
docs = chain.invoke(question, config=config)
2024-04-17 17:04:10.675 | INFO     | uptrain.framework.evalllm:evaluate_on_server:378 - Sending evaluation request for rows 0 to <50 to the Uptrain
2024-04-17 17:04:16.804 | INFO     | uptrain.framework.evalllm:evaluate:367 - Local server not running, start the server to log data and visualize in the dashboard!
``````output

Question: What did the president say about Ketanji Brown Jackson
Multi Queries:
  - How did the president comment on Ketanji Brown Jackson?
  - What were the president's remarks regarding Ketanji Brown Jackson?
  - What statements has the president made about Ketanji Brown Jackson?

Multi Query Accuracy Score: 0.5
``````output
2024-04-17 17:04:22.027 | INFO     | uptrain.framework.evalllm:evaluate_on_server:378 - Sending evaluation request for rows 0 to <50 to the Uptrain
2024-04-17 17:04:44.033 | INFO     | uptrain.framework.evalllm:evaluate:367 - Local server not running, start the server to log data and visualize in the dashboard!
``````output

Question: What did the president say about Ketanji Brown Jackson
Response: The president mentioned that he had nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to serve on the United States Supreme Court 4 days ago. He described her as one of the nation's top legal minds who will continue Justice Breyer’s legacy of excellence. He also mentioned that since her nomination, she has received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.

Context Relevance Score: 1.0
Factual Accuracy Score: 1.0
Response Completeness Score: 1.0

3. 上下文压缩与重新排序

重新排序过程涉及根据与查询的相关性重新排序节点并选择前n个节点。由于重新排序完成后节点数量可能会减少，我们执行以下评估：

  • Context Reranking: 检查重新排序的节点顺序是否比原始顺序更符合查询。
  • Context Conciseness: 检查减少的节点数量是否仍能提供所有必要的信息。
# Create the retriever
compressor = FlashrankRerank()
compression_retriever = ContextualCompressionRetriever(
    base_compressor=compressor, base_retriever=retriever
)

# Create the chain
chain = RetrievalQA.from_chain_type(llm=llm, retriever=compression_retriever)

# Create the uptrain callback
uptrain_callback = UpTrainCallbackHandler(key_type=KEY_TYPE, api_key=API_KEY)
config = {"callbacks": [uptrain_callback]}

# Invoke the chain with a query
query = "What did the president say about Ketanji Brown Jackson"
result = chain.invoke(query, config=config)
2024-04-17 17:04:46.462 | INFO     | uptrain.framework.evalllm:evaluate_on_server:378 - Sending evaluation request for rows 0 to <50 to the Uptrain
2024-04-17 17:04:53.561 | INFO     | uptrain.framework.evalllm:evaluate:367 - Local server not running, start the server to log data and visualize in the dashboard!
``````output

Question: What did the president say about Ketanji Brown Jackson

Context Conciseness Score: 0.0
Context Reranking Score: 1.0
``````output
2024-04-17 17:04:56.947 | INFO     | uptrain.framework.evalllm:evaluate_on_server:378 - Sending evaluation request for rows 0 to <50 to the Uptrain
2024-04-17 17:05:16.551 | INFO     | uptrain.framework.evalllm:evaluate:367 - Local server not running, start the server to log data and visualize in the dashboard!
``````output

Question: What did the president say about Ketanji Brown Jackson
Response: The President mentioned that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to serve on the United States Supreme Court 4 days ago. He described her as one of the nation's top legal minds who will continue Justice Breyer’s legacy of excellence.

Context Relevance Score: 1.0
Factual Accuracy Score: 1.0
Response Completeness Score: 0.5

UpTrain的仪表板和洞察

这里有一个简短的视频展示仪表板和见解：

langchain_uptrain.gif

这个页面有帮助吗？