ChatGPT¶

如果您正在 Colab 中打开此 Notebook，您可能需要安装 LlamaIndex 🦙。

In [ ]

%pip install llama-index-llms-openai

%pip install llama-index-llms-openai

In [ ]

!pip install llama-index

!pip install llama-index

In [ ]

import logging
import sys

logging.basicConfig(stream=sys.stdout, level=logging.INFO)
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.core import Settings
from llama_index.llms.openai import OpenAI
from IPython.display import Markdown, display

import logging import sys logging.basicConfig(stream=sys.stdout, level=logging.INFO) logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout)) from llama_index.core import VectorStoreIndex, SimpleDirectoryReader from llama_index.core import Settings from llama_index.llms.openai import OpenAI from IPython.display import Markdown, display

下载数据¶

In [ ]

!mkdir -p 'data/paul_graham/'
!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'

!mkdir -p 'data/paul_graham/' !wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'

加载文档，构建 VectorStoreIndex¶

In [ ]

# load documents
documents = SimpleDirectoryReader("./data/paul_graham").load_data()

# load documents documents = SimpleDirectoryReader("./data/paul_graham").load_data()

In [ ]

# set global settings config
llm = OpenAI(temperature=0, model="gpt-3.5-turbo")
Settings.llm = llm
Settings.chunk_size = 512

# set global settings config llm = OpenAI(temperature=0, model="gpt-3.5-turbo") Settings.llm = llm Settings.chunk_size = 512

In [ ]

index = VectorStoreIndex.from_documents(documents)

index = VectorStoreIndex.from_documents(documents)

查询索引¶

默认情况下，借助 langchain 的 PromptSelector 抽象，如果使用 ChatGPT 模型，我们会使用专为 ChatGPT 使用量身定制的修改后的 refine prompt。

In [ ]

query_engine = index.as_query_engine(
    similarity_top_k=3,
    streaming=True,
)
response = query_engine.query(
    "What did the author do growing up?",
)

query_engine = index.as_query_engine( similarity_top_k=3, streaming=True, ) response = query_engine.query( "What did the author do growing up?", )

INFO:llama_index.token_counter.token_counter:> [retrieve] Total LLM token usage: 0 tokens
> [retrieve] Total LLM token usage: 0 tokens
INFO:llama_index.token_counter.token_counter:> [retrieve] Total embedding token usage: 8 tokens
> [retrieve] Total embedding token usage: 8 tokens
INFO:llama_index.token_counter.token_counter:> [get_response] Total LLM token usage: 0 tokens
> [get_response] Total LLM token usage: 0 tokens
INFO:llama_index.token_counter.token_counter:> [get_response] Total embedding token usage: 0 tokens
> [get_response] Total embedding token usage: 0 tokens

In [ ]

response.print_response_stream()

response.print_response_stream()

Before college, the author worked on writing short stories and programming on an IBM 1401 using an early version of Fortran. They also worked on programming with microcomputers and eventually created a new dialect of Lisp called Arc. They later realized the potential of publishing essays on the web and began writing and publishing them. The author also worked on spam filters, painting, and cooking for groups.

In [ ]

query_engine = index.as_query_engine(
    similarity_top_k=5,
    streaming=True,
)
response = query_engine.query(
    "What did the author do during his time at RISD?",
)

query_engine = index.as_query_engine( similarity_top_k=5, streaming=True, ) response = query_engine.query( "What did the author do during his time at RISD?", )

INFO:llama_index.token_counter.token_counter:> [retrieve] Total LLM token usage: 0 tokens
> [retrieve] Total LLM token usage: 0 tokens
INFO:llama_index.token_counter.token_counter:> [retrieve] Total embedding token usage: 12 tokens
> [retrieve] Total embedding token usage: 12 tokens
INFO:llama_index.token_counter.token_counter:> [get_response] Total LLM token usage: 0 tokens
> [get_response] Total LLM token usage: 0 tokens
INFO:llama_index.token_counter.token_counter:> [get_response] Total embedding token usage: 0 tokens
> [get_response] Total embedding token usage: 0 tokens

In [ ]

response.print_response_stream()

response.print_response_stream()

The author attended RISD and took classes in fundamental subjects like drawing, color, and design. They also learned a lot in the color class they took, but otherwise, they were basically teaching themselves to paint. The author dropped out of RISD in 1993.

Refine Prompt: 以下是聊天 refine prompt

In [ ]

from llama_index.core.prompts.chat_prompts import CHAT_REFINE_PROMPT

from llama_index.core.prompts.chat_prompts import CHAT_REFINE_PROMPT

In [ ]

dict(CHAT_REFINE_PROMPT.prompt)

dict(CHAT_REFINE_PROMPT.prompt)

查询索引 (使用标准 Refine Prompt)¶

如果我们使用“标准”refine prompt（其中 prompt 是单个文本模板而不是多条消息），我们会发现 ChatGPT 上的结果会更差。

In [ ]

from llama_index.core.prompts.default_prompts import DEFAULT_REFINE_PROMPT

from llama_index.core.prompts.default_prompts import DEFAULT_REFINE_PROMPT

In [ ]

query_engine = index.as_query_engine(
    refine_template=DEFAULT_REFINE_PROMPT,
    similarity_top_k=5,
    streaming=True,
)
response = query_engine.query(
    "What did the author do during his time at RISD?",
)

query_engine = index.as_query_engine( refine_template=DEFAULT_REFINE_PROMPT, similarity_top_k=5, streaming=True, ) response = query_engine.query( "What did the author do during his time at RISD?", )

In [ ]

response.print_response_stream()

response.print_response_stream()