Skip to content

Commit

Permalink
commnity[patch]: refactor code for faiss vectorstore, update faiss ve…
Browse files Browse the repository at this point in the history 
…ctorstore documentation (#18092)

**Description:** Refactor code of FAISS vectorcstore and update the
related documentation.
Details: 
 - replace `.format()` with f-strings for strings formatting;
- refactor definition of a filtering function to make code more readable
and more flexible;
- slightly improve efficiency of
`max_marginal_relevance_search_with_score_by_vector` method by removing
unnecessary looping over the same elements;
- slightly improve efficiency of `delete` method by using set data
structure for checking if the element was already deleted;

**Issue:** fix small inconsistency in the documentation (the old example
was incorrect and unappliable to faiss vectorstore)

**Dependencies:** basic langchain-community dependencies and `faiss`
(for CPU or for GPU)

**Twitter handle:** antonenkodev
  • Loading branch information
@timofeyantonenko
timofeyantonenko authored Mar 12, 2024
1 parent acf1ecc commit 0bec1f6
Show file tree
Hide file tree
Showing 2 changed files with 91 additions and 121 deletions.
108 changes: 42 additions & 66 deletions docs/docs/integrations/vectorstores/faiss.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -83,7 +83,18 @@
"metadata": {
"tags": []
},
"outputs": [],
"outputs": [
{
"data": {
"text/plain": [
"42"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Uncomment the following line if you need to initialize FAISS with no AVX2 optimization\n",
"# os.environ['FAISS_NO_AVX2'] = '1'\n",
Expand All @@ -98,7 +109,8 @@
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
"docs = text_splitter.split_documents(documents)\n",
"embeddings = OpenAIEmbeddings()\n",
"db = FAISS.from_documents(docs, embeddings)"
"db = FAISS.from_documents(docs, embeddings)\n",
"print(db.index.ntotal)"
]
},
{
Expand All @@ -113,7 +125,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 2,
"id": "5eabdb75",
"metadata": {
"tags": []
Expand All @@ -126,7 +138,7 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 3,
"id": "4b172de8",
"metadata": {
"tags": []
Expand Down Expand Up @@ -162,27 +174,18 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 4,
"id": "6e91b475-3878-44e0-8720-98d903754b46",
"metadata": {},
"outputs": [],
"source": [
"retriever = db.as_retriever()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "a869c874-84b5-4d2c-9993-2513f10aee83",
"metadata": {},
"outputs": [],
"source": [
"retriever = db.as_retriever()\n",
"docs = retriever.invoke(query)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 5,
"id": "046739d2-91fe-4101-8b72-c0bcdd9e02b9",
"metadata": {},
"outputs": [
Expand Down Expand Up @@ -215,7 +218,7 @@
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": 6,
"id": "186ee1d8",
"metadata": {},
"outputs": [],
Expand All @@ -225,7 +228,7 @@
},
{
"cell_type": "code",
"execution_count": 14,
"execution_count": 7,
"id": "284e04b5",
"metadata": {},
"outputs": [
Expand All @@ -236,7 +239,7 @@
" 0.36913747)"
]
},
"execution_count": 14,
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -255,7 +258,7 @@
},
{
"cell_type": "code",
"execution_count": 15,
"execution_count": 9,
"id": "b558ebb7",
"metadata": {},
"outputs": [],
Expand Down Expand Up @@ -289,7 +292,7 @@
},
{
"cell_type": "code",
"execution_count": 19,
"execution_count": 10,
"id": "98378c4e",
"metadata": {},
"outputs": [
Expand All @@ -299,7 +302,7 @@
"Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', metadata={'source': '../../../state_of_the_union.txt'})"
]
},
"execution_count": 19,
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
Expand Down Expand Up @@ -359,7 +362,7 @@
},
{
"cell_type": "code",
"execution_count": 22,
"execution_count": 11,
"id": "83392605",
"metadata": {},
"outputs": [
Expand All @@ -369,7 +372,7 @@
"{'807e0c63-13f6-4070-9774-5c6f0fbb9866': Document(page_content='bar', metadata={})}"
]
},
"execution_count": 22,
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -380,7 +383,7 @@
},
{
"cell_type": "code",
"execution_count": 23,
"execution_count": 12,
"id": "a3fcc1c7",
"metadata": {},
"outputs": [],
Expand All @@ -390,7 +393,7 @@
},
{
"cell_type": "code",
"execution_count": 24,
"execution_count": 13,
"id": "41c51f89",
"metadata": {},
"outputs": [
Expand All @@ -401,7 +404,7 @@
" '807e0c63-13f6-4070-9774-5c6f0fbb9866': Document(page_content='bar', metadata={})}"
]
},
"execution_count": 24,
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -421,7 +424,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 14,
"id": "d5bf812c",
"metadata": {},
"outputs": [
Expand Down Expand Up @@ -465,7 +468,7 @@
},
{
"cell_type": "code",
"execution_count": 26,
"execution_count": 15,
"id": "83159330",
"metadata": {},
"outputs": [
Expand Down Expand Up @@ -496,7 +499,7 @@
},
{
"cell_type": "code",
"execution_count": 27,
"execution_count": 16,
"id": "432c6980",
"metadata": {},
"outputs": [
Expand Down Expand Up @@ -525,7 +528,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 17,
"id": "1fd60fd1",
"metadata": {},
"outputs": [
Expand All @@ -550,59 +553,32 @@
"source": [
"## Delete\n",
"\n",
"You can also delete ids. Note that the ids to delete should be the ids in the docstore."
"You can also delete records from vectorstore. In the example below `db.index_to_docstore_id` represents a dictionary with elements of the FAISS index."
]
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 18,
"id": "1408b870",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"True"
"count before: 8\n",
"count after: 7"
]
},
"execution_count": 4,
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"db.delete([db.index_to_docstore_id[0]])"
"print(\"count before:\", db.index.ntotal)\n",
"db.delete([db.index_to_docstore_id[0]])\n",
"print(\"count after:\", db.index.ntotal)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "d13daf33",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"False"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Is now missing\n",
"0 in db.index_to_docstore_id"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "30ace43e",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
Expand Down
Loading

0 comments on commit 0bec1f6

Please sign in to comment.