mirror of https://github.com/hwchase17/langchain
Harrison/tfidf retriever (#2440)
parent
a63cfad558
commit
00bc8df640
@ -0,0 +1,127 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ab66dd43",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# TF-IDF Retriever\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use a retriever that under the hood uses TF-IDF using scikit-learn.\n",
|
||||
"\n",
|
||||
"For more information on the details of TF-IDF see [this blog post](https://medium.com/data-science-bootcamp/tf-idf-basics-of-information-retrieval-48de122b2a4c)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "393ac030",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.retrievers import TFIDFRetriever"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "a801b57c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# !pip install scikit-learn"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "aaf80e7f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Create New Retriever with Texts"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "98b1c017",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"retriever = TFIDFRetriever.from_texts([\"foo\", \"bar\", \"world\", \"hello\", \"foo bar\"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "08437fa2",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Use Retriever\n",
|
||||
"\n",
|
||||
"We can now use the retriever!"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "c0455218",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"result = retriever.get_relevant_documents(\"foo\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "7dfa5c29",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='foo', metadata={}),\n",
|
||||
" Document(page_content='foo bar', metadata={}),\n",
|
||||
" Document(page_content='hello', metadata={}),\n",
|
||||
" Document(page_content='world', metadata={})]"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"result"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "74bd9256",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
@ -0,0 +1,47 @@
|
||||
"""TF-IDF Retriever.
|
||||
|
||||
Largely based on
|
||||
https://github.com/asvskartheek/Text-Retrieval/blob/master/TF-IDF%20Search%20Engine%20(SKLEARN).ipynb"""
|
||||
from typing import Any, List
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from langchain.schema import BaseRetriever, Document
|
||||
|
||||
|
||||
class TFIDFRetriever(BaseRetriever, BaseModel):
|
||||
vectorizer: Any
|
||||
docs: List[Document]
|
||||
tfidf_array: Any
|
||||
k: int = 4
|
||||
|
||||
class Config:
|
||||
"""Configuration for this pydantic object."""
|
||||
|
||||
arbitrary_types_allowed = True
|
||||
|
||||
@classmethod
|
||||
def from_texts(cls, texts: List[str], **kwargs: Any) -> "TFIDFRetriever":
|
||||
from sklearn.feature_extraction.text import TfidfVectorizer
|
||||
|
||||
vectorizer = TfidfVectorizer()
|
||||
tfidf_array = vectorizer.fit_transform(texts)
|
||||
docs = [Document(page_content=t) for t in texts]
|
||||
return cls(vectorizer=vectorizer, docs=docs, tfidf_array=tfidf_array, **kwargs)
|
||||
|
||||
def get_relevant_documents(self, query: str) -> List[Document]:
|
||||
from sklearn.metrics.pairwise import cosine_similarity
|
||||
|
||||
query_vec = self.vectorizer.transform(
|
||||
[query]
|
||||
) # Ip -- (n_docs,x), Op -- (n_docs,n_Feats)
|
||||
results = cosine_similarity(self.tfidf_array, query_vec).reshape(
|
||||
(-1,)
|
||||
) # Op -- (n_docs,1) -- Cosine Sim with each doc
|
||||
return_docs = []
|
||||
for i in results.argsort()[-self.k :][::-1]:
|
||||
return_docs.append(self.docs[i])
|
||||
return return_docs
|
||||
|
||||
async def aget_relevant_documents(self, query: str) -> List[Document]:
|
||||
raise NotImplementedError
|
Loading…
Reference in New Issue