github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-30 02:13:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

zep: VectorStore: Use Native MMR (#12690)

Browse Source 
- refactor to use Zep's native MMR; update example
- 
@baskaryan @eyurtsev
This commit is contained in:
Daniel Chalef 2023-11-02 16:45:42 -07:00 committed by GitHub
parent cc3d3920e3
commit 0cbdba6a9b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 185 additions and 149 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

249
docs/docs/integrations/vectorstores/zep.ipynb
View File

@ -8,6 +8,13 @@
},
"source": [
"# Zep\n",
"## VectorStore Example for [Zep](https://docs.getzep.com/) - Fast, scalable building blocks for LLM Apps\n",
"\n",
"### More on Zep:\n",
"\n",
"Zep is an open source platform for productionizing LLM apps. Go from a prototype\n",
"built in LangChain or LlamaIndex, or a custom app, to production in minutes without\n",
"rewriting code.\n",
"\n",
"## Fast, Scalable Building Blocks for LLM Apps\n",
"Zep is an open source platform for productionizing LLM apps. Go from a prototype\n",
@ -104,6 +111,7 @@
" config=config,\n",
" api_url=ZEP_API_URL,\n",
" api_key=ZEP_API_KEY,\n",
" embedding=None, # we'll have Zep embed our documents using its low-latency embedder\n",
")"
]
},
@ -123,9 +131,13 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Embedding status: 0/402 documents embedded\n",
"Embedding status: 0/402 documents embedded\n",
"Embedding status: 402/402 documents embedded\n"
"Embedding status: 0/401 documents embedded\n",
"Embedding status: 0/401 documents embedded\n",
"Embedding status: 0/401 documents embedded\n",
"Embedding status: 0/401 documents embedded\n",
"Embedding status: 0/401 documents embedded\n",
"Embedding status: 0/401 documents embedded\n",
"Embedding status: 401/401 documents embedded\n"
]
}
],
@ -179,33 +191,34 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Tables necessary to determine the places of the planets are not less\r\n",
"necessary than those for the sun, moon, and stars. Some notion of the\r\n",
"number and complexity of these tables may be formed, when we state that\r\n",
"the positions of the two principal planets, (and these are the most\r\n",
"necessary for the navigator,) Jupiter and Saturn, require each not less\r\n",
"than one hundred and sixteen tables. Yet it is not only necessary to\r\n",
"predict the position of these bodies, but it is likewise expedient to -> 0.8998482592744614 \n",
"the positions of the two principal planets, (and these the most\n",
"necessary for the navigator,) Jupiter and Saturn, require each not less\n",
"than one hundred and sixteen tables. Yet it is not only necessary to\n",
"predict the position of these bodies, but it is likewise expedient to\n",
"tabulate the motions of the four satellites of Jupiter, to predict the\n",
"exact times at which they enter his shadow, and at which their shadows\n",
"cross his disc, as well as the times at which they are interposed -> 0.9003241539387915 \n",
"====\n",
"\n",
"tabulate the motions of the four satellites of Jupiter, to predict the\r\n",
"exact times at which they enter his shadow, and at which their shadows\r\n",
"cross his disc, as well as the times at which they are interposed\r\n",
"between him and the Earth, and he between them and the Earth.\r\n",
"\r\n",
"Among the extensive classes of tables here enumerated, there are several\r\n",
"which are in their nature permanent and unalterable, and would never\r\n",
"require to be recomputed, if they could once be computed with perfect -> 0.8976143854195493 \n",
"furnish more than a small fraction of that aid to navigation (in the\n",
"large sense of that term), which, with greater facility, expedition, and\n",
"economy in the calculation and printing of tables, it might be made to\n",
"supply.\n",
"\n",
"Tables necessary to determine the places of the planets are not less\n",
"necessary than those for the sun, moon, and stars. Some notion of the\n",
"number and complexity of these tables may be formed, when we state that -> 0.8911165633479508 \n",
"====\n",
"\n",
"the scheme of notation thus applied, immediately suggested the\r\n",
"advantages which must attend it as an instrument for expressing the\r\n",
"structure, operation, and circulation of the animal system; and we\r\n",
"entertain no doubt of its adequacy for that purpose. Not only the\r\n",
"mechanical connexion of the solid members of the bodies of men and\r\n",
"animals, but likewise the structure and operation of the softer parts,\r\n",
"including the muscles, integuments, membranes, &c. the nature, motion, -> 0.889982614061763 \n",
"====\n"
"the scheme of notation thus applied, immediately suggested the\n",
"advantages which must attend it as an instrument for expressing the\n",
"structure, operation, and circulation of the animal system; and we\n",
"entertain no doubt of its adequacy for that purpose. Not only the\n",
"mechanical connexion of the solid members of the bodies of men and\n",
"animals, but likewise the structure and operation of the softer parts,\n",
"including the muscles, integuments, membranes, &c. the nature, motion, -> 0.8899750214770481 \n",
"====\n",
"\n"
]
}
],
@ -226,7 +239,9 @@
"collapsed": false
},
"source": [
"## Search over Collection Re-ranked by MMR"
"## Search over Collection Re-ranked by MMR\n",
"\n",
"Zep offers native, hardware-accelerated MMR re-ranking of search results."
]
},
{
@ -245,33 +260,34 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Tables necessary to determine the places of the planets are not less\r\n",
"necessary than those for the sun, moon, and stars. Some notion of the\r\n",
"number and complexity of these tables may be formed, when we state that\r\n",
"the positions of the two principal planets, (and these the most\r\n",
"necessary for the navigator,) Jupiter and Saturn, require each not less\r\n",
"than one hundred and sixteen tables. Yet it is not only necessary to\r\n",
"predict the position of these bodies, but it is likewise expedient to \n",
"the positions of the two principal planets, (and these the most\n",
"necessary for the navigator,) Jupiter and Saturn, require each not less\n",
"than one hundred and sixteen tables. Yet it is not only necessary to\n",
"predict the position of these bodies, but it is likewise expedient to\n",
"tabulate the motions of the four satellites of Jupiter, to predict the\n",
"exact times at which they enter his shadow, and at which their shadows\n",
"cross his disc, as well as the times at which they are interposed \n",
"====\n",
"\n",
"the scheme of notation thus applied, immediately suggested the\r\n",
"advantages which must attend it as an instrument for expressing the\r\n",
"structure, operation, and circulation of the animal system; and we\r\n",
"entertain no doubt of its adequacy for that purpose. Not only the\r\n",
"mechanical connexion of the solid members of the bodies of men and\r\n",
"animals, but likewise the structure and operation of the softer parts,\r\n",
"the scheme of notation thus applied, immediately suggested the\n",
"advantages which must attend it as an instrument for expressing the\n",
"structure, operation, and circulation of the animal system; and we\n",
"entertain no doubt of its adequacy for that purpose. Not only the\n",
"mechanical connexion of the solid members of the bodies of men and\n",
"animals, but likewise the structure and operation of the softer parts,\n",
"including the muscles, integuments, membranes, &c. the nature, motion, \n",
"====\n",
"\n",
"tabulate the motions of the four satellites of Jupiter, to predict the\r\n",
"exact times at which they enter his shadow, and at which their shadows\r\n",
"cross his disc, as well as the times at which they are interposed\r\n",
"between him and the Earth, and he between them and the Earth.\r\n",
"\r\n",
"Among the extensive classes of tables here enumerated, there are several\r\n",
"which are in their nature permanent and unalterable, and would never\r\n",
"require to be recomputed, if they could once be computed with perfect \n",
"====\n"
"resistance, economizing time, harmonizing the mechanism, and giving to\n",
"the whole mechanical action the utmost practical perfection.\n",
"\n",
"The system of mechanical contrivances by which the results, here\n",
"attempted to be described, are attained, form only one order of\n",
"expedients adopted in this machinery;--although such is the perfection\n",
"of their action, that in any ordinary case they would be regarded as\n",
"having attained the ends in view with an almost superfluous degree of \n",
"====\n",
"\n"
]
}
],
@ -311,17 +327,23 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Embedding status: 402/1692 documents embedded\n",
"Embedding status: 402/1692 documents embedded\n",
"Embedding status: 552/1692 documents embedded\n",
"Embedding status: 702/1692 documents embedded\n",
"Embedding status: 1002/1692 documents embedded\n",
"Embedding status: 1002/1692 documents embedded\n",
"Embedding status: 1152/1692 documents embedded\n",
"Embedding status: 1302/1692 documents embedded\n",
"Embedding status: 1452/1692 documents embedded\n",
"Embedding status: 1602/1692 documents embedded\n",
"Embedding status: 1692/1692 documents embedded\n"
"Embedding status: 401/1691 documents embedded\n",
"Embedding status: 401/1691 documents embedded\n",
"Embedding status: 401/1691 documents embedded\n",
"Embedding status: 401/1691 documents embedded\n",
"Embedding status: 401/1691 documents embedded\n",
"Embedding status: 401/1691 documents embedded\n",
"Embedding status: 901/1691 documents embedded\n",
"Embedding status: 901/1691 documents embedded\n",
"Embedding status: 901/1691 documents embedded\n",
"Embedding status: 901/1691 documents embedded\n",
"Embedding status: 901/1691 documents embedded\n",
"Embedding status: 901/1691 documents embedded\n",
"Embedding status: 1401/1691 documents embedded\n",
"Embedding status: 1401/1691 documents embedded\n",
"Embedding status: 1401/1691 documents embedded\n",
"Embedding status: 1401/1691 documents embedded\n",
"Embedding status: 1691/1691 documents embedded\n"
]
}
],
@ -366,33 +388,33 @@
"name": "stdout",
"output_type": "stream",
"text": [
"by that body to Mr Babbage:--'In no department of science, or of the\r\n",
"arts, does this discovery promise to be so eminently useful as in that\r\n",
"of astronomy, and its kindred sciences, with the various arts dependent\r\n",
"on them. In none are computations more operose than those which\r\n",
"astronomy in particular requires;--in none are preparatory facilities\r\n",
"more needful;--in none is error more detrimental. The practical\r\n",
"astronomer is interrupted in his pursuit, and diverted from his task of -> {'source': 'https://www.gutenberg.org/cache/epub/71292/pg71292.txt'} \n",
"or remotely, for this purpose. But in addition to these, a great number\n",
"of tables, exclusively astronomical, are likewise indispensable. The\n",
"predictions of the astronomer, with respect to the positions and motions\n",
"of the bodies of the firmament, are the means, and the only means, which\n",
"enable the mariner to prosecute his art. By these he is enabled to\n",
"discover the distance of his ship from the Line, and the extent of his -> {'source': 'https://www.gutenberg.org/cache/epub/71292/pg71292.txt'} \n",
"====\n",
"\n",
"possess all knowledge which is likely to be useful to him in his work,\r\n",
"and this I have endeavored in my case to do. If I remember rightly, you\r\n",
"on one occasion, in the early days of our friendship, defined my limits\r\n",
"in a very precise fashion.”\r\n",
"\r\n",
"“Yes,” I answered, laughing. “It was a singular document. Philosophy,\r\n",
"astronomy, and politics were marked at zero, I remember. Botany\r\n",
"possess all knowledge which is likely to be useful to him in his work,\n",
"and this I have endeavored in my case to do. If I remember rightly, you\n",
"on one occasion, in the early days of our friendship, defined my limits\n",
"in a very precise fashion.”\n",
"\n",
"“Yes,” I answered, laughing. “It was a singular document. Philosophy,\n",
"astronomy, and politics were marked at zero, I remember. Botany\n",
"variable, geology profound as regards the mud-stains from any region -> {'source': 'https://www.gutenberg.org/files/48320/48320-0.txt'} \n",
"====\n",
"\n",
"in all its relations; but above all, with Astronomy and Navigation. So\r\n",
"important have they been considered, that in many instances large sums\r\n",
"have been appropriated by the most enlightened nations in the production\r\n",
"of them; and yet so numerous and insurmountable have been the\r\n",
"difficulties attending the attainment of this end, that after all, even\r\n",
"navigators, putting aside every other department of art and science,\r\n",
"have, until very recently, been scantily and imperfectly supplied with -> {'source': 'https://www.gutenberg.org/cache/epub/71292/pg71292.txt'} \n",
"====\n"
"of astronomy, and its kindred sciences, with the various arts dependent\n",
"on them. In none are computations more operose than those which\n",
"astronomy in particular requires;--in none are preparatory facilities\n",
"more needful;--in none is error more detrimental. The practical\n",
"astronomer is interrupted in his pursuit, and diverted from his task of\n",
"observation by the irksome labours of computation, or his diligence in\n",
"observing becomes ineffectual for want of yet greater industry of -> {'source': 'https://www.gutenberg.org/cache/epub/71292/pg71292.txt'} \n",
"====\n",
"\n"
]
}
],
@ -430,38 +452,39 @@
"name": "stdout",
"output_type": "stream",
"text": [
"possess all knowledge which is likely to be useful to him in his work,\r\n",
"and this I have endeavored in my case to do. If I remember rightly, you\r\n",
"on one occasion, in the early days of our friendship, defined my limits\r\n",
"in a very precise fashion.”\r\n",
"\r\n",
"“Yes,” I answered, laughing. “It was a singular document. Philosophy,\r\n",
"astronomy, and politics were marked at zero, I remember. Botany\r\n",
"possess all knowledge which is likely to be useful to him in his work,\n",
"and this I have endeavored in my case to do. If I remember rightly, you\n",
"on one occasion, in the early days of our friendship, defined my limits\n",
"in a very precise fashion.”\n",
"\n",
"“Yes,” I answered, laughing. “It was a singular document. Philosophy,\n",
"astronomy, and politics were marked at zero, I remember. Botany\n",
"variable, geology profound as regards the mud-stains from any region -> {'source': 'https://www.gutenberg.org/files/48320/48320-0.txt'} \n",
"====\n",
"\n",
"the light shining upon his strong-set aquiline features. So he sat as I\r\n",
"dropped off to sleep, and so he sat when a sudden ejaculation caused me\r\n",
"to wake up, and I found the summer sun shining into the apartment. The\r\n",
"pipe was still between his lips, the smoke still curled upward, and the\r\n",
"room was full of a dense tobacco haze, but nothing remained of the heap\r\n",
"of shag which I had seen upon the previous night.\r\n",
"\r\n",
"“Awake, Watson?” he asked.\r\n",
"\r\n",
"“Yes.”\r\n",
"\r\n",
"the light shining upon his strong-set aquiline features. So he sat as I\n",
"dropped off to sleep, and so he sat when a sudden ejaculation caused me\n",
"to wake up, and I found the summer sun shining into the apartment. The\n",
"pipe was still between his lips, the smoke still curled upward, and the\n",
"room was full of a dense tobacco haze, but nothing remained of the heap\n",
"of shag which I had seen upon the previous night.\n",
"\n",
"“Awake, Watson?” he asked.\n",
"\n",
"“Yes.”\n",
"\n",
"“Game for a morning drive?” -> {'source': 'https://www.gutenberg.org/files/48320/48320-0.txt'} \n",
"====\n",
"\n",
"“I glanced at the books upon the table, and in spite of my ignorance\r\n",
"of German I could see that two of them were treatises on science, the\r\n",
"others being volumes of poetry. Then I walked across to the window,\r\n",
"hoping that I might catch some glimpse of the country-side, but an oak\r\n",
"shutter, heavily barred, was folded across it. It was a wonderfully\r\n",
"silent house. There was an old clock ticking loudly somewhere in the\r\n",
"“I glanced at the books upon the table, and in spite of my ignorance\n",
"of German I could see that two of them were treatises on science, the\n",
"others being volumes of poetry. Then I walked across to the window,\n",
"hoping that I might catch some glimpse of the country-side, but an oak\n",
"shutter, heavily barred, was folded across it. It was a wonderfully\n",
"silent house. There was an old clock ticking loudly somewhere in the\n",
"passage, but otherwise everything was deadly still. A vague feeling of -> {'source': 'https://www.gutenberg.org/files/48320/48320-0.txt'} \n",
"====\n"
"====\n",
"\n"
]
}
],
@ -479,6 +502,14 @@
"for d in docs:\n",
" print(d.page_content, \" -> \", d.metadata, \"\\n====\\n\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "96132aa6",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
@ -490,13 +521,13 @@
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"pygments_lexer": "ipython3",
"version": "3.11.6"
}
},

85
libs/langchain/langchain/vectorstores/zep.py
View File

@ -5,12 +5,9 @@ import warnings
from dataclasses import asdict, dataclass
from typing import TYPE_CHECKING, Any, Dict, Iterable, List, Optional, Tuple
import numpy as np
from langchain.docstore.document import Document
from langchain.schema.embeddings import Embeddings
from langchain.schema.vectorstore import VectorStore
from langchain.vectorstores.utils import maximal_marginal_relevance
if TYPE_CHECKING:
from zep_python.document import Document as ZepDocument
@ -112,8 +109,7 @@ class ZepVectorStore(VectorStore):
collection = self._client.document.get_collection(self.collection_name)
except NotFoundError:
logger.info(
f"Collection {self.collection_name} not found. "
"Creating new collection."
f"Collection {self.collection_name} not found. Creating new collection."
)
collection = self._create_collection()
@ -452,23 +448,6 @@ class ZepVectorStore(VectorStore):
for doc in results
]
def _max_marginal_relevance_selection(
self,
query_vector: List[float],
results: List["ZepDocument"],
*,
lambda_mult: float = 0.5,
k: int = 4,
) -> List[Document]:
mmr_selected = maximal_marginal_relevance(
np.array([query_vector], dtype=np.float32),
[d.embedding for d in results],
lambda_mult=lambda_mult,
k=k,
)
selected = [results[i] for i in mmr_selected]
return [Document(page_content=d.content, metadata=d.metadata) for d in selected]
def max_marginal_relevance_search(
self,
query: str,
@ -487,6 +466,8 @@ class ZepVectorStore(VectorStore):
query: Text to look up documents similar to.
k: Number of Documents to return. Defaults to 4.
fetch_k: Number of Documents to fetch to pass to MMR algorithm.
Zep determines this automatically and this parameter is
ignored.
lambda_mult: Number between 0 and 1 that determines the degree
of diversity among the results with 0 corresponding
to maximum diversity and 1 to minimum diversity.
@ -504,16 +485,24 @@ class ZepVectorStore(VectorStore):
if not self._collection.is_auto_embedded and self._embedding:
query_vector = self._embedding.embed_query(query)
results = self._collection.search(
embedding=query_vector, limit=k, metadata=metadata, **kwargs
embedding=query_vector,
limit=k,
metadata=metadata,
search_type="mmr",
mmr_lambda=lambda_mult,
**kwargs,
)
else:
results, query_vector = self._collection.search_return_query_vector(
query, limit=k, metadata=metadata, **kwargs
query,
limit=k,
metadata=metadata,
search_type="mmr",
mmr_lambda=lambda_mult,
**kwargs,
)
return self._max_marginal_relevance_selection(
query_vector, results, k=k, lambda_mult=lambda_mult
)
return [Document(page_content=d.content, metadata=d.metadata) for d in results]
async def amax_marginal_relevance_search(
self,
@ -534,16 +523,24 @@ class ZepVectorStore(VectorStore):
if not self._collection.is_auto_embedded and self._embedding:
query_vector = self._embedding.embed_query(query)
results = await self._collection.asearch(
embedding=query_vector, limit=k, metadata=metadata, **kwargs
embedding=query_vector,
limit=k,
metadata=metadata,
search_type="mmr",
mmr_lambda=lambda_mult,
**kwargs,
)
else:
results, query_vector = await self._collection.asearch_return_query_vector(
query, limit=k, metadata=metadata, **kwargs
query,
limit=k,
metadata=metadata,
search_type="mmr",
mmr_lambda=lambda_mult,
**kwargs,
)
return self._max_marginal_relevance_selection(
query_vector, results, k=k, lambda_mult=lambda_mult
)
return [Document(page_content=d.content, metadata=d.metadata) for d in results]
def max_marginal_relevance_search_by_vector(
self,
@ -563,6 +560,8 @@ class ZepVectorStore(VectorStore):
embedding: Embedding to look up documents similar to.
k: Number of Documents to return. Defaults to 4.
fetch_k: Number of Documents to fetch to pass to MMR algorithm.
Zep determines this automatically and this parameter is
ignored.
lambda_mult: Number between 0 and 1 that determines the degree
of diversity among the results with 0 corresponding
to maximum diversity and 1 to minimum diversity.
@ -577,12 +576,15 @@ class ZepVectorStore(VectorStore):
)
results = self._collection.search(
embedding=embedding, limit=k, metadata=metadata, **kwargs
embedding=embedding,
limit=k,
metadata=metadata,
search_type="mmr",
mmr_lambda=lambda_mult,
**kwargs,
)
return self._max_marginal_relevance_selection(
embedding, results, k=k, lambda_mult=lambda_mult
)
return [Document(page_content=d.content, metadata=d.metadata) for d in results]
async def amax_marginal_relevance_search_by_vector(
self,
@ -600,12 +602,15 @@ class ZepVectorStore(VectorStore):
)
results = await self._collection.asearch(
embedding=embedding, limit=k, metadata=metadata, **kwargs
embedding=embedding,
limit=k,
metadata=metadata,
search_type="mmr",
mmr_lambda=lambda_mult,
**kwargs,
)
return self._max_marginal_relevance_selection(
embedding, results, k=k, lambda_mult=lambda_mult
)
return [Document(page_content=d.content, metadata=d.metadata) for d in results]
@classmethod
def from_texts(