Zep
回顧、理解和提取聊天記錄中的數據。為個人化 AI 體驗提供動力。
Zep 是一個適用於 AI 助理應用程式的長期記憶服務。 透過 Zep，您可以讓 AI 助理能夠回憶起過去的對話，無論多麼久遠，同時減少幻覺、延遲和成本。
對 Zep Cloud 感興趣？請參閱 Zep Cloud 安裝指南 和 Zep Cloud Vector Store 範例
開源安裝與設定
Zep 開源專案：https://github.com/getzep/zep
Zep 開源文檔：https://docs.getzep.com/
您需要安裝 langchain-community，使用 pip install -qU langchain-community 才能使用此整合
用法
在以下範例中，我們使用 Zep 的自動嵌入功能，該功能使用低延遲嵌入模型自動在 Zep 伺服器上嵌入文檔。
注意
- 這些範例使用 Zep 的非同步介面。 透過從方法名稱中移除
a字首來呼叫同步介面。 - 如果您傳入
Embeddings實例，Zep 將使用它來嵌入文檔，而不是自動嵌入它們。 您還必須將您的文檔集合設定為isAutoEmbedded === false。 - 如果您將集合設定為
isAutoEmbedded === false，則必須傳入Embeddings實例。
從文檔載入或建立集合
from uuid import uuid4
from langchain_community.document_loaders import WebBaseLoader
from langchain_community.vectorstores import ZepVectorStore
from langchain_community.vectorstores.zep import CollectionConfig
from langchain_text_splitters import RecursiveCharacterTextSplitter
ZEP_API_URL = "https://127.0.0.1:8000" # this is the API url of your Zep instance
ZEP_API_KEY = "<optional_key>" # optional API Key for your Zep instance
collection_name = f"babbage{uuid4().hex}" # a unique collection name. alphanum only
# Collection config is needed if we're creating a new Zep Collection
config = CollectionConfig(
name=collection_name,
description="<optional description>",
metadata={"optional_metadata": "associated with the collection"},
is_auto_embedded=True, # we'll have Zep embed our documents using its low-latency embedder
embedding_dimensions=1536, # this should match the model you've configured Zep to use.
)
# load the document
article_url = "https://www.gutenberg.org/cache/epub/71292/pg71292.txt"
loader = WebBaseLoader(article_url)
documents = loader.load()
# split it into chunks
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
docs = text_splitter.split_documents(documents)
# Instantiate the VectorStore. Since the collection does not already exist in Zep,
# it will be created and populated with the documents we pass in.
vs = ZepVectorStore.from_documents(
docs,
collection_name=collection_name,
config=config,
api_url=ZEP_API_URL,
api_key=ZEP_API_KEY,
embedding=None, # we'll have Zep embed our documents using its low-latency embedder
)
# wait for the collection embedding to complete
async def wait_for_ready(collection_name: str) -> None:
import time
from zep_python import ZepClient
client = ZepClient(ZEP_API_URL, ZEP_API_KEY)
while True:
c = await client.document.aget_collection(collection_name)
print(
"Embedding status: "
f"{c.document_embedded_count}/{c.document_count} documents embedded"
)
time.sleep(1)
if c.status == "ready":
break
await wait_for_ready(collection_name)
Embedding status: 0/401 documents embedded
Embedding status: 0/401 documents embedded
Embedding status: 0/401 documents embedded
Embedding status: 0/401 documents embedded
Embedding status: 0/401 documents embedded
Embedding status: 0/401 documents embedded
Embedding status: 401/401 documents embedded
對集合進行相似性搜尋查詢
# query it
query = "what is the structure of our solar system?"
docs_scores = await vs.asimilarity_search_with_relevance_scores(query, k=3)
# print results
for d, s in docs_scores:
print(d.page_content, " -> ", s, "\n====\n")
the positions of the two principal planets, (and these the most
necessary for the navigator,) Jupiter and Saturn, require each not less
than one hundred and sixteen tables. Yet it is not only necessary to
predict the position of these bodies, but it is likewise expedient to
tabulate the motions of the four satellites of Jupiter, to predict the
exact times at which they enter his shadow, and at which their shadows
cross his disc, as well as the times at which they are interposed -> 0.9003241539387915
====
furnish more than a small fraction of that aid to navigation (in the
large sense of that term), which, with greater facility, expedition, and
economy in the calculation and printing of tables, it might be made to
supply.
Tables necessary to determine the places of the planets are not less
necessary than those for the sun, moon, and stars. Some notion of the
number and complexity of these tables may be formed, when we state that -> 0.8911165633479508
====
the scheme of notation thus applied, immediately suggested the
advantages which must attend it as an instrument for expressing the
structure, operation, and circulation of the animal system; and we
entertain no doubt of its adequacy for that purpose. Not only the
mechanical connexion of the solid members of the bodies of men and
animals, but likewise the structure and operation of the softer parts,
including the muscles, integuments, membranes, &c. the nature, motion, -> 0.8899750214770481
====
對集合進行 MMR 重新排序的搜尋
Zep 提供原生、硬體加速的 MMR 搜尋結果重新排序。
query = "what is the structure of our solar system?"
docs = await vs.asearch(query, search_type="mmr", k=3)
for d in docs:
print(d.page_content, "\n====\n")
the positions of the two principal planets, (and these the most
necessary for the navigator,) Jupiter and Saturn, require each not less
than one hundred and sixteen tables. Yet it is not only necessary to
predict the position of these bodies, but it is likewise expedient to
tabulate the motions of the four satellites of Jupiter, to predict the
exact times at which they enter his shadow, and at which their shadows
cross his disc, as well as the times at which they are interposed
====
the scheme of notation thus applied, immediately suggested the
advantages which must attend it as an instrument for expressing the
structure, operation, and circulation of the animal system; and we
entertain no doubt of its adequacy for that purpose. Not only the
mechanical connexion of the solid members of the bodies of men and
animals, but likewise the structure and operation of the softer parts,
including the muscles, integuments, membranes, &c. the nature, motion,
====
resistance, economizing time, harmonizing the mechanism, and giving to
the whole mechanical action the utmost practical perfection.
The system of mechanical contrivances by which the results, here
attempted to be described, are attained, form only one order of
expedients adopted in this machinery;--although such is the perfection
of their action, that in any ordinary case they would be regarded as
having attained the ends in view with an almost superfluous degree of
====
依中繼資料篩選
使用中繼資料篩選器來縮小結果範圍。 首先，載入另一本書：「福爾摩斯冒險記」
# Let's add more content to the existing Collection
article_url = "https://www.gutenberg.org/files/48320/48320-0.txt"
loader = WebBaseLoader(article_url)
documents = loader.load()
# split it into chunks
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
docs = text_splitter.split_documents(documents)
await vs.aadd_documents(docs)
await wait_for_ready(collection_name)
Embedding status: 401/1691 documents embedded
Embedding status: 401/1691 documents embedded
Embedding status: 401/1691 documents embedded
Embedding status: 401/1691 documents embedded
Embedding status: 401/1691 documents embedded
Embedding status: 401/1691 documents embedded
Embedding status: 901/1691 documents embedded
Embedding status: 901/1691 documents embedded
Embedding status: 901/1691 documents embedded
Embedding status: 901/1691 documents embedded
Embedding status: 901/1691 documents embedded
Embedding status: 901/1691 documents embedded
Embedding status: 1401/1691 documents embedded
Embedding status: 1401/1691 documents embedded
Embedding status: 1401/1691 documents embedded
Embedding status: 1401/1691 documents embedded
Embedding status: 1691/1691 documents embedded
我們看到來自兩本書的結果。 請注意 source 中繼資料
query = "Was he interested in astronomy?"
docs = await vs.asearch(query, search_type="similarity", k=3)
for d in docs:
print(d.page_content, " -> ", d.metadata, "\n====\n")
or remotely, for this purpose. But in addition to these, a great number
of tables, exclusively astronomical, are likewise indispensable. The
predictions of the astronomer, with respect to the positions and motions
of the bodies of the firmament, are the means, and the only means, which
enable the mariner to prosecute his art. By these he is enabled to
discover the distance of his ship from the Line, and the extent of his -> {'source': 'https://www.gutenberg.org/cache/epub/71292/pg71292.txt'}
====
possess all knowledge which is likely to be useful to him in his work,
and this I have endeavored in my case to do. If I remember rightly, you
on one occasion, in the early days of our friendship, defined my limits
in a very precise fashion.”
“Yes,” I answered, laughing. “It was a singular document. Philosophy,
astronomy, and politics were marked at zero, I remember. Botany
variable, geology profound as regards the mud-stains from any region -> {'source': 'https://www.gutenberg.org/files/48320/48320-0.txt'}
====
of astronomy, and its kindred sciences, with the various arts dependent
on them. In none are computations more operose than those which
astronomy in particular requires;--in none are preparatory facilities
more needful;--in none is error more detrimental. The practical
astronomer is interrupted in his pursuit, and diverted from his task of
observation by the irksome labours of computation, or his diligence in
observing becomes ineffectual for want of yet greater industry of -> {'source': 'https://www.gutenberg.org/cache/epub/71292/pg71292.txt'}
====
現在，我們設定篩選器
filter = {
"where": {
"jsonpath": (
"$[*] ? (@.source == 'https://www.gutenberg.org/files/48320/48320-0.txt')"
)
},
}
docs = await vs.asearch(query, search_type="similarity", metadata=filter, k=3)
for d in docs:
print(d.page_content, " -> ", d.metadata, "\n====\n")
possess all knowledge which is likely to be useful to him in his work,
and this I have endeavored in my case to do. If I remember rightly, you
on one occasion, in the early days of our friendship, defined my limits
in a very precise fashion.”
“Yes,” I answered, laughing. “It was a singular document. Philosophy,
astronomy, and politics were marked at zero, I remember. Botany
variable, geology profound as regards the mud-stains from any region -> {'source': 'https://www.gutenberg.org/files/48320/48320-0.txt'}
====
the light shining upon his strong-set aquiline features. So he sat as I
dropped off to sleep, and so he sat when a sudden ejaculation caused me
to wake up, and I found the summer sun shining into the apartment. The
pipe was still between his lips, the smoke still curled upward, and the
room was full of a dense tobacco haze, but nothing remained of the heap
of shag which I had seen upon the previous night.
“Awake, Watson?” he asked.
“Yes.”
“Game for a morning drive?” -> {'source': 'https://www.gutenberg.org/files/48320/48320-0.txt'}
====
“I glanced at the books upon the table, and in spite of my ignorance
of German I could see that two of them were treatises on science, the
others being volumes of poetry. Then I walked across to the window,
hoping that I might catch some glimpse of the country-side, but an oak
shutter, heavily barred, was folded across it. It was a wonderfully
silent house. There was an old clock ticking loudly somewhere in the
passage, but otherwise everything was deadly still. A vague feeling of -> {'source': 'https://www.gutenberg.org/files/48320/48320-0.txt'}
====