github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-01 19:12:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

community: Add support for SAP HANA Vector hnsw index creation (#27884)

Browse Source 
**Issue:** Added support for creating indexes in the SAP HANA Vector
engine.
 
**Changes**: 
1. Introduced a new function `create_hnsw_index` in `hanavector.py` that
enables the creation of indexes for SAP HANA Vector.
2. Added integration tests for the index creation function to ensure
functionality.
3. Updated the documentation to reflect the new index creation feature,
including examples and output from the notebook.
4. Fix the operator issue in ` _process_filter_object` function and
change the array argument to a placeholder in the similarity search SQL
statement.

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
This commit is contained in:
cinqisap
2024-12-06 00:29:08 +01:00
committed by GitHub
parent 28f8d436f6
commit 482e8a7855
3 changed files with 681 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files

458
docs/docs/integrations/vectorstores/sap_hanavector.ipynb
View File

@@ -22,7 +22,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 1,
"metadata": {
"tags": []
},
@@ -41,7 +41,7 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": 1,
"metadata": {
"ExecuteTime": {
"end_time": "2023-09-09T08:02:16.802456Z",
@@ -64,7 +64,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 9,
"metadata": {
"ExecuteTime": {
"end_time": "2023-09-09T08:02:28.174088Z",
@@ -73,8 +73,10 @@
},
"outputs": [],
"source": [
"from dotenv import load_dotenv\n",
"from hdbcli import dbapi\n",
"\n",
"load_dotenv()\n",
"# Use connection settings from the environment\n",
"connection = dbapi.connect(\n",
" address=os.environ.get(\"HANA_DB_ADDRESS\"),\n",
@@ -102,14 +104,22 @@
},
{
"cell_type": "code",
"execution_count": 20,
"execution_count": 10,
"metadata": {
"ExecuteTime": {
"end_time": "2023-09-09T08:02:25.452472Z",
"start_time": "2023-09-09T08:02:25.441563Z"
}
},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of document chunks: 88\n"
]
}
],
"source": [
"from langchain_community.document_loaders import TextLoader\n",
"from langchain_community.vectorstores.hanavector import HanaDB\n",
@@ -134,7 +144,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 11,
"metadata": {
"ExecuteTime": {
"end_time": "2023-09-09T08:04:16.696625Z",
@@ -157,9 +167,20 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 12,
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/plain": [
"[]"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Delete already existing documents from the table\n",
"db.delete(filter={})\n",
@@ -178,9 +199,24 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 13,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--------------------------------------------------------------------------------\n",
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
"\n",
"And 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.\n",
"--------------------------------------------------------------------------------\n",
"As I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential. \n",
"\n",
"While it often appears that we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice.\n"
]
}
],
"source": [
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
"docs = db.similarity_search(query, k=2)\n",
@@ -199,9 +235,24 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 14,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--------------------------------------------------------------------------------\n",
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
"\n",
"And 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.\n",
"--------------------------------------------------------------------------------\n",
"As I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential. \n",
"\n",
"While it often appears that we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice.\n"
]
}
],
"source": [
"from langchain_community.vectorstores.utils import DistanceStrategy\n",
"\n",
@@ -235,7 +286,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 15,
"metadata": {
"ExecuteTime": {
"end_time": "2023-09-09T08:05:23.276819Z",
@@ -246,7 +297,24 @@
"outputs_hidden": false
}
},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--------------------------------------------------------------------------------\n",
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
"\n",
"And 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.\n",
"--------------------------------------------------------------------------------\n",
"Groups of citizens blocking tanks with their bodies. Everyone from students to retirees teachers turned soldiers defending their homeland. \n",
"\n",
"In this struggle as President Zelenskyy said in his speech to the European Parliament “Light will win over darkness.” The Ukrainian Ambassador to the United States is here tonight. \n",
"\n",
"Let each of us here tonight in this Chamber send an unmistakable signal to Ukraine and to the world.\n"
]
}
],
"source": [
"docs = db.max_marginal_relevance_search(query, k=2, fetch_k=20)\n",
"for doc in docs:\n",
@@ -254,6 +322,86 @@
" print(doc.page_content)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Creating an HNSW Vector Index\n",
"\n",
"A vector index can significantly speed up top-k nearest neighbor queries for vectors. Users can create a Hierarchical Navigable Small World (HNSW) vector index using the `create_hnsw_index` function.\n",
"\n",
"For more information about creating an index at the database level, please refer to the [official documentation](https://help.sap.com/docs/hana-cloud-database/sap-hana-cloud-sap-hana-database-vector-engine-guide/create-vector-index-statement-data-definition).\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--------------------------------------------------------------------------------\n",
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
"\n",
"And 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.\n",
"--------------------------------------------------------------------------------\n",
"Groups of citizens blocking tanks with their bodies. Everyone from students to retirees teachers turned soldiers defending their homeland. \n",
"\n",
"In this struggle as President Zelenskyy said in his speech to the European Parliament “Light will win over darkness.” The Ukrainian Ambassador to the United States is here tonight. \n",
"\n",
"Let each of us here tonight in this Chamber send an unmistakable signal to Ukraine and to the world.\n"
]
}
],
"source": [
"# HanaDB instance uses cosine similarity as default:\n",
"db_cosine = HanaDB(\n",
" embedding=embeddings, connection=connection, table_name=\"STATE_OF_THE_UNION\"\n",
")\n",
"\n",
"# Attempting to create the HNSW index with default parameters\n",
"db_cosine.create_hnsw_index() # If no other parameters are specified, the default values will be used\n",
"# Default values: m=64, ef_construction=128, ef_search=200\n",
"# The default index name will be: STATE_OF_THE_UNION_COSINE_SIMILARITY_IDX (verify this naming pattern in HanaDB class)\n",
"\n",
"\n",
"# Creating a HanaDB instance with L2 distance as the similarity function and defined values\n",
"db_l2 = HanaDB(\n",
" embedding=embeddings,\n",
" connection=connection,\n",
" table_name=\"STATE_OF_THE_UNION\",\n",
" distance_strategy=DistanceStrategy.EUCLIDEAN_DISTANCE, # Specify L2 distance\n",
")\n",
"\n",
"# This will create an index based on L2 distance strategy.\n",
"db_l2.create_hnsw_index(\n",
" index_name=\"STATE_OF_THE_UNION_L2_index\",\n",
" m=100, # Max number of neighbors per graph node (valid range: 4 to 1000)\n",
" ef_construction=200, # Max number of candidates during graph construction (valid range: 1 to 100000)\n",
" ef_search=500, # Min number of candidates during the search (valid range: 1 to 100000)\n",
")\n",
"\n",
"# Use L2 index to perform MMR\n",
"docs = db_l2.max_marginal_relevance_search(query, k=2, fetch_k=20)\n",
"for doc in docs:\n",
" print(\"-\" * 80)\n",
" print(doc.page_content)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"**Key Points**:\n",
"- **Similarity Function**: The similarity function for the index is **cosine similarity** by default. If you want to use a different similarity function (e.g., `L2` distance), you need to specify it when initializing the `HanaDB` instance.\n",
"- **Default Parameters**: In the `create_hnsw_index` function, if the user does not provide custom values for parameters like `m`, `ef_construction`, or `ef_search`, the default values (e.g., `m=64`, `ef_construction=128`, `ef_search=200`) will be used automatically. These values ensure the index is created with reasonable performance without requiring user intervention.\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
@@ -263,9 +411,20 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 19,
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"db = HanaDB(\n",
" connection=connection, embedding=embeddings, table_name=\"LANGCHAIN_DEMO_BASIC\"\n",
@@ -284,9 +443,20 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 20,
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/plain": [
"[]"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"docs = [Document(page_content=\"Some text\"), Document(page_content=\"Other docs\")]\n",
"db.add_documents(docs)"
@@ -301,9 +471,20 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 21,
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/plain": [
"[]"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"docs = [\n",
" Document(\n",
@@ -327,9 +508,19 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 22,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--------------------------------------------------------------------------------\n",
"foo\n",
"{'start': 100, 'end': 150, 'doc_name': 'foo.txt', 'quality': 'bad'}\n"
]
}
],
"source": [
"docs = db.similarity_search(\"foobar\", k=2, filter={\"quality\": \"bad\"})\n",
"# With filtering on \"quality\"==\"bad\", only one document should be returned\n",
@@ -348,9 +539,17 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 23,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0\n"
]
}
],
"source": [
"db.delete(filter={\"quality\": \"bad\"})\n",
"\n",
@@ -385,7 +584,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 24,
"metadata": {},
"outputs": [],
"source": [
@@ -433,9 +632,30 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 25,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Filter: {'id': {'$ne': 1}}\n",
"{'name': 'bob', 'is_active': False, 'id': 2, 'height': 5.7}\n",
"{'name': 'jane', 'is_active': True, 'id': 3, 'height': 2.4}\n",
"Filter: {'id': {'$gt': 1}}\n",
"{'name': 'bob', 'is_active': False, 'id': 2, 'height': 5.7}\n",
"{'name': 'jane', 'is_active': True, 'id': 3, 'height': 2.4}\n",
"Filter: {'id': {'$gte': 1}}\n",
"{'name': 'adam', 'is_active': True, 'id': 1, 'height': 10.0}\n",
"{'name': 'bob', 'is_active': False, 'id': 2, 'height': 5.7}\n",
"{'name': 'jane', 'is_active': True, 'id': 3, 'height': 2.4}\n",
"Filter: {'id': {'$lt': 1}}\n",
"<empty result>\n",
"Filter: {'id': {'$lte': 1}}\n",
"{'name': 'adam', 'is_active': True, 'id': 1, 'height': 10.0}\n"
]
}
],
"source": [
"advanced_filter = {\"id\": {\"$ne\": 1}}\n",
"print(f\"Filter: {advanced_filter}\")\n",
@@ -467,9 +687,24 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 26,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Filter: {'id': {'$between': (1, 2)}}\n",
"{'name': 'adam', 'is_active': True, 'id': 1, 'height': 10.0}\n",
"{'name': 'bob', 'is_active': False, 'id': 2, 'height': 5.7}\n",
"Filter: {'name': {'$in': ['adam', 'bob']}}\n",
"{'name': 'adam', 'is_active': True, 'id': 1, 'height': 10.0}\n",
"{'name': 'bob', 'is_active': False, 'id': 2, 'height': 5.7}\n",
"Filter: {'name': {'$nin': ['adam', 'bob']}}\n",
"{'name': 'jane', 'is_active': True, 'id': 3, 'height': 2.4}\n"
]
}
],
"source": [
"advanced_filter = {\"id\": {\"$between\": (1, 2)}}\n",
"print(f\"Filter: {advanced_filter}\")\n",
@@ -493,9 +728,21 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 27,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Filter: {'name': {'$like': 'a%'}}\n",
"{'name': 'adam', 'is_active': True, 'id': 1, 'height': 10.0}\n",
"Filter: {'name': {'$like': '%a%'}}\n",
"{'name': 'adam', 'is_active': True, 'id': 1, 'height': 10.0}\n",
"{'name': 'jane', 'is_active': True, 'id': 3, 'height': 2.4}\n"
]
}
],
"source": [
"advanced_filter = {\"name\": {\"$like\": \"a%\"}}\n",
"print(f\"Filter: {advanced_filter}\")\n",
@@ -515,9 +762,25 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 28,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Filter: {'$or': [{'id': 1}, {'name': 'bob'}]}\n",
"{'name': 'adam', 'is_active': True, 'id': 1, 'height': 10.0}\n",
"{'name': 'bob', 'is_active': False, 'id': 2, 'height': 5.7}\n",
"Filter: {'$and': [{'id': 1}, {'id': 2}]}\n",
"<empty result>\n",
"Filter: {'$or': [{'id': 1}, {'id': 2}, {'id': 3}]}\n",
"{'name': 'adam', 'is_active': True, 'id': 1, 'height': 10.0}\n",
"{'name': 'bob', 'is_active': False, 'id': 2, 'height': 5.7}\n",
"{'name': 'jane', 'is_active': True, 'id': 3, 'height': 2.4}\n"
]
}
],
"source": [
"advanced_filter = {\"$or\": [{\"id\": 1}, {\"name\": \"bob\"}]}\n",
"print(f\"Filter: {advanced_filter}\")\n",
@@ -541,7 +804,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 29,
"metadata": {},
"outputs": [],
"source": [
@@ -574,7 +837,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 30,
"metadata": {},
"outputs": [],
"source": [
@@ -635,9 +898,21 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 32,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Answer from LLM:\n",
"================\n",
"The United States has set up joint patrols with Mexico and Guatemala to catch more human traffickers. This collaboration is part of the efforts to address immigration issues and secure the borders in the region.\n",
"================\n",
"Number of used source document chunks: 5\n"
]
}
],
"source": [
"question = \"What about Mexico and Guatemala?\"\n",
"\n",
@@ -679,9 +954,19 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 34,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Answer from LLM:\n",
"================\n",
"Mexico and Guatemala are involved in joint patrols to catch human traffickers.\n"
]
}
],
"source": [
"question = \"What about other countries?\"\n",
"\n",
@@ -711,9 +996,20 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 35,
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/plain": [
"[]"
]
},
"execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Access the vector DB with a new table\n",
"db = HanaDB(\n",
@@ -742,9 +1038,19 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 36,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"('VEC_META', 'NCLOB')\n",
"('VEC_TEXT', 'NCLOB')\n",
"('VEC_VECTOR', 'REAL_VECTOR')\n"
]
}
],
"source": [
"cur = connection.cursor()\n",
"cur.execute(\n",
@@ -795,12 +1101,23 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 39,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"None\n",
"Some other text\n",
"{\"start\": 400, \"end\": 450, \"doc_name\": \"other.txt\"}\n",
"<memory at 0x7f5edcb18d00>\n"
]
}
],
"source": [
"# Create a new table \"MY_OWN_TABLE\" with three \"standard\" columns and one additional column\n",
"my_own_table_name = \"MY_OWN_TABLE\"\n",
"# Create a new table \"MY_OWN_TABLE_ADD\" with three \"standard\" columns and one additional column\n",
"my_own_table_name = \"MY_OWN_TABLE_ADD\"\n",
"cur = connection.cursor()\n",
"cur.execute(\n",
" (\n",
@@ -851,9 +1168,20 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 40,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--------------------------------------------------------------------------------\n",
"Some other text\n",
"--------------------------------------------------------------------------------\n",
"Some more text\n"
]
}
],
"source": [
"docs = [\n",
" Document(\n",
@@ -886,9 +1214,20 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 41,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Filters on this value are very performant\n",
"Some other text\n",
"{\"start\": 400, \"end\": 450, \"doc_name\": \"other.txt\", \"CUSTOMTEXT\": \"Filters on this value are very performant\"}\n",
"<memory at 0x7f5edcb193c0>\n"
]
}
],
"source": [
"# Create a new table \"PERFORMANT_CUSTOMTEXT_FILTER\" with three \"standard\" columns and one additional column\n",
"my_own_table_name = \"PERFORMANT_CUSTOMTEXT_FILTER\"\n",
@@ -952,9 +1291,20 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 42,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--------------------------------------------------------------------------------\n",
"Some other text\n",
"--------------------------------------------------------------------------------\n",
"Some more text\n"
]
}
],
"source": [
"docs = [\n",
" Document(\n",
@@ -994,7 +1344,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.9"
"version": "3.10.14"
}
},
"nbformat": 4,