Skip to content

Update hybrid search notebook #70

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Mar 27, 2025
Merged

Update hybrid search notebook #70

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ad9df2f
update to bm25std and add escaper for safety
rbs333 Mar 27, 2025
c34b8d9
weird test output
rbs333 Mar 27, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 16 additions & 12 deletions python-recipes/vector-search/02_hybrid_search.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -367,7 +367,7 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": null,
"metadata": {},
"outputs": [
{
Expand All @@ -382,6 +382,10 @@
}
],
"source": [
"from redisvl.utils.token_escaper import TokenEscaper\n",
"\n",
"escaper = TokenEscaper()\n",
"\n",
"# list of stopwords to filter out noise from query string\n",
"stopwords = set([\n",
" \"a\", \"is\", \"the\", \"an\", \"and\", \"are\", \"as\", \"at\", \"be\", \"but\", \"by\", \"for\",\n",
Expand All @@ -391,8 +395,8 @@
"\n",
"def tokenize_query(user_query: str) -> str:\n",
" \"\"\"Convert a raw user query to a redis full text query joined by ORs\"\"\"\n",
" tokens = [token.strip().strip(\",\").lower() for token in user_query.split()]\n",
" return \" | \".join([token for token in tokens if token not in stopwords])\n",
" tokens = [escaper.escape(token.strip().strip(\",\").lower()) for token in user_query.split()]\n",
" return \" | \".join([token for token in tokens if token and token not in stopwords])\n",
"\n",
"# Example\n",
"tokenize_query(user_query)"
Expand All @@ -407,7 +411,7 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
Expand Down Expand Up @@ -438,8 +442,8 @@
" filter_expression=f\"~({Text(text_field) % tokenize_query(user_query)})\",\n",
" num_results=num_results,\n",
" return_fields=[\"title\", \"description\"],\n",
" dialect=4,\n",
" ).scorer(\"BM25\").with_scores()"
" dialect=2,\n",
" ).scorer(\"BM25STD\").with_scores()"
]
},
{
Expand Down Expand Up @@ -540,7 +544,7 @@
},
{
"cell_type": "code",
"execution_count": 14,
"execution_count": null,
"metadata": {},
"outputs": [
{
Expand Down Expand Up @@ -581,13 +585,13 @@
"# Build the aggregation request\n",
"req = (\n",
" AggregateRequest(query.query_string())\n",
" .scorer(\"BM25\")\n",
" .scorer(\"BM25STD\")\n",
" .add_scores()\n",
" .apply(cosine_similarity=\"(2 - @vector_distance)/2\", bm25_score=\"@__score\")\n",
" .apply(hybrid_score=f\"0.3*@bm25_score + 0.7*@cosine_similarity\")\n",
" .load(\"title\", \"description\", \"cosine_similarity\", \"bm25_score\", \"hybrid_score\")\n",
" .sort_by(Desc(\"@hybrid_score\"), max=3)\n",
" .dialect(4)\n",
" .dialect(2)\n",
")\n",
"\n",
"# Run the query\n",
Expand Down Expand Up @@ -620,7 +624,7 @@
},
{
"cell_type": "code",
"execution_count": 15,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -634,13 +638,13 @@
" # Build aggregation\n",
" req = (\n",
" AggregateRequest(query.query_string())\n",
" .scorer(\"BM25\")\n",
" .scorer(\"BM25STD\")\n",
" .add_scores()\n",
" .apply(cosine_similarity=\"(2 - @vector_distance)/2\", bm25_score=\"@__score\")\n",
" .apply(hybrid_score=f\"{1-alpha}*@bm25_score + {alpha}*@cosine_similarity\")\n",
" .sort_by(Desc(\"@hybrid_score\"), max=num_results)\n",
" .load(\"title\", \"description\", \"cosine_similarity\", \"bm25_score\", \"hybrid_score\")\n",
" .dialect(4)\n",
" .dialect(2)\n",
" )\n",
"\n",
" # Run the query\n",
Expand Down
Loading