简单向量存储库¶
如果您在colab上打开此笔记本,您可能需要安装LlamaIndex 🦙。
!pip install llama-index
import os
import openai
os.environ["OPENAI_API_KEY"] = "sk-..."
openai.api_key = os.environ["OPENAI_API_KEY"]
加载文档,构建VectorStoreIndex¶
import nltk
nltk.download("stopwords")
[nltk_data] Downloading package stopwords to [nltk_data] /Users/jerryliu/nltk_data... [nltk_data] Package stopwords is already up-to-date!
True
import llama_index.core
[nltk_data] Downloading package stopwords to /Users/jerryliu/Programmi [nltk_data] ng/gpt_index/.venv/lib/python3.10/site- [nltk_data] packages/llama_index/core/_static/nltk_cache... [nltk_data] Unzipping corpora/stopwords.zip. [nltk_data] Downloading package punkt to /Users/jerryliu/Programming/g [nltk_data] pt_index/.venv/lib/python3.10/site- [nltk_data] packages/llama_index/core/_static/nltk_cache... [nltk_data] Unzipping tokenizers/punkt.zip.
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,
load_index_from_storage,
StorageContext,
)
from IPython.display import Markdown, display
下载数据
!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'
--2024-02-12 13:21:13-- https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.110.133, 185.199.111.133, 185.199.108.133, ... Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.110.133|:443... connected. HTTP request sent, awaiting response... 200 OK Length: 75042 (73K) [text/plain] Saving to: ‘data/paul_graham/paul_graham_essay.txt’ data/paul_graham/pa 100%[===================>] 73.28K --.-KB/s in 0.02s 2024-02-12 13:21:13 (4.76 MB/s) - ‘data/paul_graham/paul_graham_essay.txt’ saved [75042/75042]
# 加载文档
documents = SimpleDirectoryReader("./data/paul_graham/").load_data()
index = VectorStoreIndex.from_documents(documents)
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
# 将索引保存到磁盘
index.set_index_id("vector_index")
index.storage_context.persist("./storage")
# 重新构建存储上下文
storage_context = StorageContext.from_defaults(persist_dir="storage")
# 加载索引
index = load_index_from_storage(storage_context, index_id="vector_index")
INFO:llama_index.core.indices.loading:Loading indices with ids: ['vector_index'] Loading indices with ids: ['vector_index']
查询索引¶
# 将日志级别设置为DEBUG,以获得更详细的输出
query_engine = index.as_query_engine(response_mode="tree_summarize")
response = query_engine.query("作者在成长过程中做了什么?")
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
display(Markdown(f"<b>{response}</b>"))
The author wrote short stories and also worked on programming, specifically on an IBM 1401 computer in 9th grade. They later transitioned to working with microcomputers, starting with a kit-built microcomputer and eventually acquiring a TRS-80. They wrote simple games, a program to predict rocket heights, and even a word processor. Although the author initially planned to study philosophy in college, they eventually switched to studying AI.
使用SVM/线性回归查询索引
使用Karpathy的SVM-based方法。将查询设置为正例,将所有其他数据点设置为负例,然后拟合一个超平面。
查询模式 = [
"svm",
"linear_regression",
"logistic_regression",
]
for 查询模式 in 查询模式:
# 将日志设置为DEBUG以获得更详细的输出
查询引擎 = 索引.as_query_engine(vector_store_query_mode=查询模式)
响应 = 查询引擎.query("作者在成长过程中做了什么?")
print(f"查询模式:{查询模式}")
display(Markdown(f"<b>{响应}</b>"))
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
/Users/jerryliu/Programming/gpt_index/.venv/lib/python3.10/site-packages/sklearn/svm/_classes.py:31: FutureWarning: The default value of `dual` will change from `True` to `'auto'` in 1.5. Set the value of `dual` explicitly to suppress the warning. warnings.warn(
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" Query mode: svm
The author wrote short stories and also worked on programming, specifically on an IBM 1401 computer in 9th grade. They later got a microcomputer and started programming on it, writing simple games and a word processor. They initially planned to study philosophy in college but ended up switching to AI.
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
/Users/jerryliu/Programming/gpt_index/.venv/lib/python3.10/site-packages/sklearn/svm/_classes.py:31: FutureWarning: The default value of `dual` will change from `True` to `'auto'` in 1.5. Set the value of `dual` explicitly to suppress the warning. warnings.warn(
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" Query mode: linear_regression
The author wrote short stories and also worked on programming, specifically on an IBM 1401 computer in 9th grade. They later got a microcomputer and started programming on it, writing simple games and a word processor. They initially planned to study philosophy in college but ended up switching to AI.
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
/Users/jerryliu/Programming/gpt_index/.venv/lib/python3.10/site-packages/sklearn/svm/_classes.py:31: FutureWarning: The default value of `dual` will change from `True` to `'auto'` in 1.5. Set the value of `dual` explicitly to suppress the warning. warnings.warn(
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" Query mode: logistic_regression
The author wrote short stories and also worked on programming, specifically on an IBM 1401 computer in 9th grade. They later got a microcomputer and started programming on it, writing simple games and a word processor. They initially planned to study philosophy in college but eventually switched to AI.
display(Markdown(f"<b>{response}</b>"))
The author wrote short stories and also worked on programming, specifically on an IBM 1401 computer in 9th grade. They later got a microcomputer and started programming on it, writing simple games and a word processor. They initially planned to study philosophy in college but eventually switched to AI.
print(response.source_nodes[0].text)
What I Worked On February 2021 Before college the two main things I worked on, outside of school, were writing and programming. I didn't write essays. I wrote what beginning writers were supposed to write then, and probably still are: short stories. My stories were awful. They had hardly any plot, just characters with strong feelings, which I imagined made them deep. The first programs I tried writing were on the IBM 1401 that our school district used for what was then called "data processing." This was in 9th grade, so I was 13 or 14. The school district's 1401 happened to be in the basement of our junior high school, and my friend Rich Draves and I got permission to use it. It was like a mini Bond villain's lair down there, with all these alien-looking machines — CPU, disk drives, printer, card reader — sitting up on a raised floor under bright fluorescent lights. The language we used was an early version of Fortran. You had to type programs on punch cards, then stack them in the card reader and press a button to load the program into memory and run it. The result would ordinarily be to print something on the spectacularly loud printer. I was puzzled by the 1401. I couldn't figure out what to do with it. And in retrospect there's not much I could have done with it. The only form of input to programs was data stored on punched cards, and I didn't have any data stored on punched cards. The only other option was to do things that didn't rely on any input, like calculate approximations of pi, but I didn't know enough math to do anything interesting of that type. So I'm not surprised I can't remember any programs I wrote, because they can't have done much. My clearest memory is of the moment I learned it was possible for programs not to terminate, when one of mine didn't. On a machine without time-sharing, this was a social as well as a technical error, as the data center manager's expression made clear. With microcomputers, everything changed. Now you could have a computer sitting right in front of you, on a desk, that could respond to your keystrokes as it was running instead of just churning through a stack of punch cards and then stopping. [1] The first of my friends to get a microcomputer built it himself. It was sold as a kit by Heathkit. I remember vividly how impressed and envious I felt watching him sitting in front of it, typing programs right into the computer. Computers were expensive in those days and it took me years of nagging before I convinced my father to buy one, a TRS-80, in about 1980. The gold standard then was the Apple II, but a TRS-80 was good enough. This was when I really started programming. I wrote simple games, a program to predict how high my model rockets would fly, and a word processor that my father used to write at least one book. There was only room in memory for about 2 pages of text, so he'd write 2 pages at a time and then print them out, but it was a lot better than a typewriter. Though I liked programming, I didn't plan to study it in college. In college I was going to study philosophy, which sounded much more powerful. It seemed, to my naive high school self, to be the study of the ultimate truths, compared to which the things studied in other fields would be mere domain knowledge. What I discovered when I got to college was that the other fields took up so much of the space of ideas that there wasn't much left for these supposed ultimate truths. All that seemed left for philosophy were edge cases that people in other fields felt could safely be ignored. I couldn't have put this into words when I was 18. All I knew at the time was that I kept taking philosophy courses and they kept being boring. So I decided to switch to AI. AI was in the air in the mid 1980s, but there were two things especially that made me want to work on it: a novel by Heinlein called The Moon is a Harsh Mistress, which featured an intelligent computer called Mike, and a PBS documentary that showed Terry Winograd using SHRDLU. I haven't tried rereading The Moon is a Harsh Mistress, so I don't know how well it has aged, but when I read it I was drawn entirely into its world. It seemed only a matter of time before we'd have Mike, and when I saw Winograd using SHRDLU, it seemed like that time would be a few years at most.
使用自定义嵌入字符串查询索引
from llama_index.core import QueryBundle
query_bundle = QueryBundle(
query_str="What did the author do growing up?",
custom_embedding_strs=["The author grew up painting."],
)
query_engine = index.as_query_engine()
response = query_engine.query(query_bundle)
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
display(Markdown(f"<b>{response}</b>"))
The context does not provide information about what the author did growing up.
使用最大边际相关性
与仅通过相似性对向量进行排名不同,最大边际相关性(MMR)根据 MMR 对已经发现的类似文档进行惩罚,从而为文档增加多样性。较低的mmr_treshold会增加多样性。
query_engine = index.as_query_engine(
vector_store_query_mode="mmr", vector_store_kwargs={"mmr_threshold": 0.2}
)
response = query_engine.query("What did the author do growing up?")
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK" HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
获取数据源¶
print(response.get_formatted_sources())
> Source (Doc id: c4118521-8f55-4a4d-819a-2db546b6491e): What I Worked On February 2021 Before college the two main things I worked on, outside of schoo... > Source (Doc id: 74f77233-e4fe-4389-9820-76dd9f765af6): Which meant being easy to use and inexpensive. It was lucky for us that we were poor, because tha...
使用过滤器查询索引¶
我们也可以使用元数据来过滤我们的查询。
from llama_index.core import Document
doc = Document(text="target", metadata={"tag": "target"})
index.insert(doc)
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
from llama_index.core.vector_stores import ExactMatchFilter, MetadataFilters
filters = MetadataFilters(
filters=[ExactMatchFilter(key="tag", value="target")]
)
retriever = index.as_retriever(
similarity_top_k=20,
filters=filters,
)
source_nodes = retriever.retrieve("What did the author do growing up?")
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK" HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
# 仅检索我们的目标节点,即使我们将top k设置为20
print(len(source_nodes))
1
print(source_nodes[0].text)
print(source_nodes[0].metadata)
target {'tag': 'target'}