created vector store in Supabase

README.md

@@ -14,3 +14,31 @@ hf_oauth_expiration_minutes: 480
 ---
 
 
+Script to setting up tables and vector search
+ "CREATE EXTENSION IF NOT EXISTS vector;"
+ """
+CREATE TABLE IF NOT EXISTS documents2 (
+    id BIGINT PRIMARY KEY,
+    content TEXT,
+    metadata JSONB,
+    embedding VECTOR(1536)
+);
+"""
+
+create or replace function match_documents_2(
+  query_embedding vector(1536),
+  match_count int default 5
+)
+returns table (
+  id bigint,
+  content text,
+  metadata jsonb,
+  embedding vector
+)
+language sql
+as $$
+  select id, content, metadata, embedding
+  from documents2
+  order by embedding <#> query_embedding
+  limit match_count;
+$$;

pdm.lock

@@ -5,7 +5,7 @@
 groups = ["default"]
 strategy = ["inherit_metadata"]
 lock_version = "4.5.0"
-content_hash = "sha256:d1b978f5c5889ca1859fe0ed1e488dcb2e81f11d054248bf21c48daccbdc55af"
+content_hash = "sha256:0c6e1c83ed4ec2b1751cc0917ce598d614bf977d7f7b4568110a8a1b16d40739"
 
 [[metadata.targets]]
 requires_python = "==3.12.*"
@@ -220,7 +220,7 @@ version = "0.4.6"
 requires_python = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
 summary = "Cross-platform colored terminal text."
 groups = ["default"]
-marker = "platform_system == \"Windows\""
+marker = "platform_system == \"Windows\" or sys_platform == \"win32\""
 files = [
     {file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"},
     {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
@@ -267,6 +267,19 @@ files = [
     {file = "datasets-3.6.0.tar.gz", hash = "sha256:1b2bf43b19776e2787e181cfd329cb0ca1a358ea014780c3581e0f276375e041"},
 ]
 
+[[package]]
+name = "deprecation"
+version = "2.1.0"
+summary = "A library to handle automated deprecations"
+groups = ["default"]
+dependencies = [
+    "packaging",
+]
+files = [
+    {file = "deprecation-2.1.0-py2.py3-none-any.whl", hash = "sha256:a10811591210e1fb0e768a8c25517cabeabcba6f0bf96564f8ff45189f90b14a"},
+    {file = "deprecation-2.1.0.tar.gz", hash = "sha256:72b3bde64e5d778694b0cf68178aed03d15e15477116add3fb773e581f9518ff"},
+]
+
 [[package]]
 name = "dill"
 version = "0.3.8"
@@ -424,6 +437,23 @@ files = [
     {file = "fsspec-2025.3.0.tar.gz", hash = "sha256:a935fd1ea872591f2b5148907d103488fc523295e6c64b835cfad8c3eca44972"},
 ]
 
+[[package]]
+name = "gotrue"
+version = "2.12.0"
+requires_python = "<4.0,>=3.9"
+summary = "Python Client Library for Supabase Auth"
+groups = ["default"]
+dependencies = [
+    "httpx[http2]<0.29,>=0.26",
+    "pydantic<3,>=1.10",
+    "pyjwt<3.0.0,>=2.10.1",
+    "pytest-mock<4.0.0,>=3.14.0",
+]
+files = [
+    {file = "gotrue-2.12.0-py3-none-any.whl", hash = "sha256:de94928eebb42d7d9672dbe4fbd0b51140a45051a31626a06dad2ad44a9a976a"},
+    {file = "gotrue-2.12.0.tar.gz", hash = "sha256:b9ea164ee52964d8364c550cde16dd0e9576241a4cffeaa52eca339f61d1d14b"},
+]
+
 [[package]]
 name = "gradio"
 version = "5.29.1"
@@ -516,6 +546,25 @@ files = [
     {file = "groovy-0.1.2.tar.gz", hash = "sha256:25c1dc09b3f9d7e292458aa762c6beb96ea037071bf5e917fc81fb78d2231083"},
 ]
 
+[[package]]
+name = "grpcio"
+version = "1.67.1"
+requires_python = ">=3.8"
+summary = "HTTP/2-based RPC framework"
+groups = ["default"]
+files = [
+    {file = "grpcio-1.67.1-cp312-cp312-linux_armv7l.whl", hash = "sha256:267d1745894200e4c604958da5f856da6293f063327cb049a51fe67348e4f953"},
+    {file = "grpcio-1.67.1-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:85f69fdc1d28ce7cff8de3f9c67db2b0ca9ba4449644488c1e0303c146135ddb"},
+    {file = "grpcio-1.67.1-cp312-cp312-manylinux_2_17_aarch64.whl", hash = "sha256:f26b0b547eb8d00e195274cdfc63ce64c8fc2d3e2d00b12bf468ece41a0423a0"},
+    {file = "grpcio-1.67.1-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4422581cdc628f77302270ff839a44f4c24fdc57887dc2a45b7e53d8fc2376af"},
+    {file = "grpcio-1.67.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1d7616d2ded471231c701489190379e0c311ee0a6c756f3c03e6a62b95a7146e"},
+    {file = "grpcio-1.67.1-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:8a00efecde9d6fcc3ab00c13f816313c040a28450e5e25739c24f432fc6d3c75"},
+    {file = "grpcio-1.67.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:699e964923b70f3101393710793289e42845791ea07565654ada0969522d0a38"},
+    {file = "grpcio-1.67.1-cp312-cp312-win32.whl", hash = "sha256:4e7b904484a634a0fff132958dabdb10d63e0927398273917da3ee103e8d1f78"},
+    {file = "grpcio-1.67.1-cp312-cp312-win_amd64.whl", hash = "sha256:5721e66a594a6c4204458004852719b38f3d5522082be9061d6510b455c90afc"},
+    {file = "grpcio-1.67.1.tar.gz", hash = "sha256:3dc2ed4cabea4dc14d5e708c2b426205956077cc5de419b4d4079315017e9732"},
+]
+
 [[package]]
 name = "h11"
 version = "0.16.0"
@@ -527,6 +576,32 @@ files = [
     {file = "h11-0.16.0.tar.gz", hash = "sha256:4e35b956cf45792e4caa5885e69fba00bdbc6ffafbfa020300e549b208ee5ff1"},
 ]
 
+[[package]]
+name = "h2"
+version = "4.2.0"
+requires_python = ">=3.9"
+summary = "Pure-Python HTTP/2 protocol implementation"
+groups = ["default"]
+dependencies = [
+    "hpack<5,>=4.1",
+    "hyperframe<7,>=6.1",
+]
+files = [
+    {file = "h2-4.2.0-py3-none-any.whl", hash = "sha256:479a53ad425bb29af087f3458a61d30780bc818e4ebcf01f0b536ba916462ed0"},
+    {file = "h2-4.2.0.tar.gz", hash = "sha256:c8a52129695e88b1a0578d8d2cc6842bbd79128ac685463b887ee278126ad01f"},
+]
+
+[[package]]
+name = "hpack"
+version = "4.1.0"
+requires_python = ">=3.9"
+summary = "Pure-Python HPACK header encoding"
+groups = ["default"]
+files = [
+    {file = "hpack-4.1.0-py3-none-any.whl", hash = "sha256:157ac792668d995c657d93111f46b4535ed114f0c9c8d672271bbec7eae1b496"},
+    {file = "hpack-4.1.0.tar.gz", hash = "sha256:ec5eca154f7056aa06f196a557655c5b009b382873ac8d1e66e79e87535f1dca"},
+]
+
 [[package]]
 name = "httpcore"
 version = "1.0.9"
@@ -570,6 +645,22 @@ files = [
     {file = "httpx_sse-0.4.0-py3-none-any.whl", hash = "sha256:f329af6eae57eaa2bdfd962b42524764af68075ea87370a2de920af5341e318f"},
 ]
 
+[[package]]
+name = "httpx"
+version = "0.28.1"
+extras = ["http2"]
+requires_python = ">=3.8"
+summary = "The next generation HTTP client."
+groups = ["default"]
+dependencies = [
+    "h2<5,>=3",
+    "httpx==0.28.1",
+]
+files = [
+    {file = "httpx-0.28.1-py3-none-any.whl", hash = "sha256:d909fcccc110f8c7faf814ca82a9a4d816bc5a6dbfea25d6591d6985b8ba59ad"},
+    {file = "httpx-0.28.1.tar.gz", hash = "sha256:75e98c5f16b0f35b567856f597f06ff2270a374470a5c2392242528e3e3e42fc"},
+]
+
 [[package]]
 name = "huggingface-hub"
 version = "0.31.2"
@@ -590,6 +681,17 @@ files = [
     {file = "huggingface_hub-0.31.2.tar.gz", hash = "sha256:7053561376ed7f6ffdaecf09cc54d70dc784ac6315fa4bb9b93e19662b029675"},
 ]
 
+[[package]]
+name = "hyperframe"
+version = "6.1.0"
+requires_python = ">=3.9"
+summary = "Pure-Python HTTP/2 framing"
+groups = ["default"]
+files = [
+    {file = "hyperframe-6.1.0-py3-none-any.whl", hash = "sha256:b03380493a519fce58ea5af42e4a42317bf9bd425596f7a0835ffce80f1a42e5"},
+    {file = "hyperframe-6.1.0.tar.gz", hash = "sha256:f630908a00854a7adeabd6382b43923a4c4cd4b821fcb527e6ab9e15382a3b08"},
+]
+
 [[package]]
 name = "idna"
 version = "3.10"
@@ -601,6 +703,17 @@ files = [
     {file = "idna-3.10.tar.gz", hash = "sha256:12f65c9b470abda6dc35cf8e63cc574b1c52b11df2c86030af0ac09b01b13ea9"},
 ]
 
+[[package]]
+name = "iniconfig"
+version = "2.1.0"
+requires_python = ">=3.8"
+summary = "brain-dead simple config-ini parsing"
+groups = ["default"]
+files = [
+    {file = "iniconfig-2.1.0-py3-none-any.whl", hash = "sha256:9deba5723312380e77435581c6bf4935c94cbfab9b1ed33ef8d238ea168eb760"},
+    {file = "iniconfig-2.1.0.tar.gz", hash = "sha256:3abbd2e30b36733fee78f9c7f7308f2d0050e88f0087fd25c2645f63c773e1c7"},
+]
+
 [[package]]
 name = "jinja2"
 version = "3.1.6"
@@ -963,6 +1076,23 @@ files = [
     {file = "mdurl-0.1.2.tar.gz", hash = "sha256:bb413d29f5eea38f31dd4754dd7377d4465116fb207585f97bf925588687c1ba"},
 ]
 
+[[package]]
+name = "milvus-lite"
+version = "2.4.12"
+requires_python = ">=3.7"
+summary = "A lightweight version of Milvus wrapped with Python."
+groups = ["default"]
+marker = "sys_platform != \"win32\""
+dependencies = [
+    "tqdm",
+]
+files = [
+    {file = "milvus_lite-2.4.12-py3-none-macosx_10_9_x86_64.whl", hash = "sha256:e8d4f7cdd5f731efd6faeee3715d280fd91a5f9b4d89312664d56401f65b1473"},
+    {file = "milvus_lite-2.4.12-py3-none-macosx_11_0_arm64.whl", hash = "sha256:20087663e7b4385050b7ad08f1f03404426d4c87b1ff91d5a8723eee7fd49e88"},
+    {file = "milvus_lite-2.4.12-py3-none-manylinux2014_aarch64.whl", hash = "sha256:a0f3a5ddbfd19f4a6b842b2fd3445693c796cde272b701a1646a94c1ac45d3d7"},
+    {file = "milvus_lite-2.4.12-py3-none-manylinux2014_x86_64.whl", hash = "sha256:334037ebbab60243b5d8b43d54ca2f835d81d48c3cda0c6a462605e588deb05d"},
+]
+
 [[package]]
 name = "mpmath"
 version = "1.3.0"
@@ -1388,6 +1518,34 @@ files = [
     {file = "pillow-11.2.1.tar.gz", hash = "sha256:a64dd61998416367b7ef979b73d3a85853ba9bec4c2925f74e588879a58716b6"},
 ]
 
+[[package]]
+name = "pluggy"
+version = "1.6.0"
+requires_python = ">=3.9"
+summary = "plugin and hook calling mechanisms for python"
+groups = ["default"]
+files = [
+    {file = "pluggy-1.6.0-py3-none-any.whl", hash = "sha256:e920276dd6813095e9377c0bc5566d94c932c33b27a3e3945d8389c374dd4746"},
+    {file = "pluggy-1.6.0.tar.gz", hash = "sha256:7dcc130b76258d33b90f61b658791dede3486c3e6bfb003ee5c9bfb396dd22f3"},
+]
+
+[[package]]
+name = "postgrest"
+version = "1.0.1"
+requires_python = "<4.0,>=3.9"
+summary = "PostgREST client for Python. This library provides an ORM interface to PostgREST."
+groups = ["default"]
+dependencies = [
+    "deprecation<3.0.0,>=2.1.0",
+    "httpx[http2]<0.29,>=0.26",
+    "pydantic<3.0,>=1.9",
+    "strenum<0.5.0,>=0.4.9; python_version < \"3.11\"",
+]
+files = [
+    {file = "postgrest-1.0.1-py3-none-any.whl", hash = "sha256:fcc0518d68d924198c41c8cbaa70c342c641cb49311be33ba4fc74b4e742f22e"},
+    {file = "postgrest-1.0.1.tar.gz", hash = "sha256:0d6556dadfd8392147d98aad097fe7bf0196602e28a58eee5e9bde4390bb573f"},
+]
+
 [[package]]
 name = "primp"
 version = "0.15.0"
@@ -1433,6 +1591,44 @@ files = [
     {file = "propcache-0.3.1.tar.gz", hash = "sha256:40d980c33765359098837527e18eddefc9a24cea5b45e078a7f3bb5b032c6ecf"},
 ]
 
+[[package]]
+name = "protobuf"
+version = "6.31.0"
+requires_python = ">=3.9"
+summary = ""
+groups = ["default"]
+files = [
+    {file = "protobuf-6.31.0-cp310-abi3-win32.whl", hash = "sha256:10bd62802dfa0588649740a59354090eaf54b8322f772fbdcca19bc78d27f0d6"},
+    {file = "protobuf-6.31.0-cp310-abi3-win_amd64.whl", hash = "sha256:3e987c99fd634be8347246a02123250f394ba20573c953de133dc8b2c107dd71"},
+    {file = "protobuf-6.31.0-cp39-abi3-macosx_10_9_universal2.whl", hash = "sha256:2c812f0f96ceb6b514448cefeb1df54ec06dde456783f5099c0e2f8a0f2caa89"},
+    {file = "protobuf-6.31.0-cp39-abi3-manylinux2014_aarch64.whl", hash = "sha256:67ce50195e4e584275623b8e6bc6d3d3dfd93924bf6116b86b3b8975ab9e4571"},
+    {file = "protobuf-6.31.0-cp39-abi3-manylinux2014_x86_64.whl", hash = "sha256:5353e38844168a327acd2b2aa440044411cd8d1b6774d5701008bd1dba067c79"},
+    {file = "protobuf-6.31.0-py3-none-any.whl", hash = "sha256:6ac2e82556e822c17a8d23aa1190bbc1d06efb9c261981da95c71c9da09e9e23"},
+    {file = "protobuf-6.31.0.tar.gz", hash = "sha256:314fab1a6a316469dc2dd46f993cbbe95c861ea6807da910becfe7475bc26ffe"},
+]
+
+[[package]]
+name = "psycopg2-binary"
+version = "2.9.10"
+requires_python = ">=3.8"
+summary = "psycopg2 - Python-PostgreSQL Database Adapter"
+groups = ["default"]
+files = [
+    {file = "psycopg2-binary-2.9.10.tar.gz", hash = "sha256:4b3df0e6990aa98acda57d983942eff13d824135fe2250e6522edaa782a06de2"},
+    {file = "psycopg2_binary-2.9.10-cp312-cp312-macosx_12_0_x86_64.whl", hash = "sha256:880845dfe1f85d9d5f7c412efea7a08946a46894537e4e5d091732eb1d34d9a0"},
+    {file = "psycopg2_binary-2.9.10-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:9440fa522a79356aaa482aa4ba500b65f28e5d0e63b801abf6aa152a29bd842a"},
+    {file = "psycopg2_binary-2.9.10-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e3923c1d9870c49a2d44f795df0c889a22380d36ef92440ff618ec315757e539"},
+    {file = "psycopg2_binary-2.9.10-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7b2c956c028ea5de47ff3a8d6b3cc3330ab45cf0b7c3da35a2d6ff8420896526"},
+    {file = "psycopg2_binary-2.9.10-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f758ed67cab30b9a8d2833609513ce4d3bd027641673d4ebc9c067e4d208eec1"},
+    {file = "psycopg2_binary-2.9.10-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8cd9b4f2cfab88ed4a9106192de509464b75a906462fb846b936eabe45c2063e"},
+    {file = "psycopg2_binary-2.9.10-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:6dc08420625b5a20b53551c50deae6e231e6371194fa0651dbe0fb206452ae1f"},
+    {file = "psycopg2_binary-2.9.10-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:d7cd730dfa7c36dbe8724426bf5612798734bff2d3c3857f36f2733f5bfc7c00"},
+    {file = "psycopg2_binary-2.9.10-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:155e69561d54d02b3c3209545fb08938e27889ff5a10c19de8d23eb5a41be8a5"},
+    {file = "psycopg2_binary-2.9.10-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:c3cc28a6fd5a4a26224007712e79b81dbaee2ffb90ff406256158ec4d7b52b47"},
+    {file = "psycopg2_binary-2.9.10-cp312-cp312-win32.whl", hash = "sha256:ec8a77f521a17506a24a5f626cb2aee7850f9b69a0afe704586f63a464f3cd64"},
+    {file = "psycopg2_binary-2.9.10-cp312-cp312-win_amd64.whl", hash = "sha256:18c5ee682b9c6dd3696dad6e54cc7ff3a1a9020df6a5c0f861ef8bfd338c3ca0"},
+]
+
 [[package]]
 name = "pyarrow"
 version = "20.0.0"
@@ -1546,6 +1742,39 @@ files = [
     {file = "pygments-2.19.1.tar.gz", hash = "sha256:61c16d2a8576dc0649d9f39e089b5f02bcd27fba10d8fb4dcc28173f7a45151f"},
 ]
 
+[[package]]
+name = "pyjwt"
+version = "2.10.1"
+requires_python = ">=3.9"
+summary = "JSON Web Token implementation in Python"
+groups = ["default"]
+files = [
+    {file = "PyJWT-2.10.1-py3-none-any.whl", hash = "sha256:dcdd193e30abefd5debf142f9adfcdd2b58004e644f25406ffaebd50bd98dacb"},
+    {file = "pyjwt-2.10.1.tar.gz", hash = "sha256:3cc5772eb20009233caf06e9d8a0577824723b44e6648ee0a2aedb6cf9381953"},
+]
+
+[[package]]
+name = "pymilvus"
+version = "2.5.9"
+requires_python = ">=3.8"
+summary = "Python Sdk for Milvus"
+groups = ["default"]
+dependencies = [
+    "grpcio<=1.67.1,>=1.49.1",
+    "milvus-lite>=2.4.0; sys_platform != \"win32\"",
+    "numpy<1.25.0; python_version <= \"3.8\"",
+    "pandas>=1.2.4",
+    "protobuf>=3.20.0",
+    "python-dotenv<2.0.0,>=1.0.1",
+    "setuptools<70.1; python_version <= \"3.8\"",
+    "setuptools>69",
+    "ujson>=2.0.0",
+]
+files = [
+    {file = "pymilvus-2.5.9-py3-none-any.whl", hash = "sha256:e905a38429c3d8682a314e133a2dcc6e97f7b3cd28f07ef41c679e0cf92b0e0a"},
+    {file = "pymilvus-2.5.9.tar.gz", hash = "sha256:5f524233450494f64d4db6549d0f56e7eb147e96da6183486c737c71a3f7dc61"},
+]
+
 [[package]]
 name = "pymupdf"
 version = "1.25.5"
@@ -1563,6 +1792,39 @@ files = [
     {file = "pymupdf-1.25.5.tar.gz", hash = "sha256:5f96311cacd13254c905f6654a004a0a2025b71cabc04fda667f5472f72c15a0"},
 ]
 
+[[package]]
+name = "pytest"
+version = "8.3.5"
+requires_python = ">=3.8"
+summary = "pytest: simple powerful testing with Python"
+groups = ["default"]
+dependencies = [
+    "colorama; sys_platform == \"win32\"",
+    "exceptiongroup>=1.0.0rc8; python_version < \"3.11\"",
+    "iniconfig",
+    "packaging",
+    "pluggy<2,>=1.5",
+    "tomli>=1; python_version < \"3.11\"",
+]
+files = [
+    {file = "pytest-8.3.5-py3-none-any.whl", hash = "sha256:c69214aa47deac29fad6c2a4f590b9c4a9fdb16a403176fe154b79c0b4d4d820"},
+    {file = "pytest-8.3.5.tar.gz", hash = "sha256:f4efe70cc14e511565ac476b57c279e12a855b11f48f212af1080ef2263d3845"},
+]
+
+[[package]]
+name = "pytest-mock"
+version = "3.14.0"
+requires_python = ">=3.8"
+summary = "Thin-wrapper around the mock package for easier use with pytest"
+groups = ["default"]
+dependencies = [
+    "pytest>=6.2.5",
+]
+files = [
+    {file = "pytest-mock-3.14.0.tar.gz", hash = "sha256:2719255a1efeceadbc056d6bf3df3d1c5015530fb40cf347c0f9afac88410bd0"},
+    {file = "pytest_mock-3.14.0-py3-none-any.whl", hash = "sha256:0b72c38033392a5f4621342fe11e9219ac11ec9d375f8e2a0c164539e0d70f6f"},
+]
+
 [[package]]
 name = "python-dateutil"
 version = "2.9.0.post0"
@@ -1641,6 +1903,23 @@ files = [
     {file = "rank_bm25-0.2.2.tar.gz", hash = "sha256:096ccef76f8188563419aaf384a02f0ea459503fdf77901378d4fd9d87e5e51d"},
 ]
 
+[[package]]
+name = "realtime"
+version = "2.4.3"
+requires_python = "<4.0,>=3.9"
+summary = ""
+groups = ["default"]
+dependencies = [
+    "aiohttp<4.0.0,>=3.11.18",
+    "python-dateutil<3.0.0,>=2.8.1",
+    "typing-extensions<5.0.0,>=4.13.2",
+    "websockets<15,>=11",
+]
+files = [
+    {file = "realtime-2.4.3-py3-none-any.whl", hash = "sha256:09ff3b61ac928413a27765640b67362380eaddba84a7037a17972a64b1ac52f7"},
+    {file = "realtime-2.4.3.tar.gz", hash = "sha256:152febabc822ce60e11f202842c5aa6858ae4bd04920bfd6a00c1dd492f426b0"},
+]
+
 [[package]]
 name = "regex"
 version = "2024.11.6"
@@ -1861,7 +2140,6 @@ version = "80.7.1"
 requires_python = ">=3.9"
 summary = "Easily download, build, install, upgrade, and uninstall Python packages"
 groups = ["default"]
-marker = "platform_system == \"Linux\" and platform_machine == \"x86_64\" or python_version >= \"3.12\""
 files = [
     {file = "setuptools-80.7.1-py3-none-any.whl", hash = "sha256:ca5cc1069b85dc23070a6628e6bcecb3292acac802399c7f8edc0100619f9009"},
     {file = "setuptools-80.7.1.tar.gz", hash = "sha256:f6ffc5f0142b1bd8d0ca94ee91b30c0ca862ffd50826da1ea85258a06fd94552"},
@@ -1949,6 +2227,65 @@ files = [
     {file = "starlette-0.46.2.tar.gz", hash = "sha256:7f7361f34eed179294600af672f565727419830b54b7b084efe44bb82d2fccd5"},
 ]
 
+[[package]]
+name = "storage3"
+version = "0.11.3"
+requires_python = "<4.0,>=3.9"
+summary = "Supabase Storage client for Python."
+groups = ["default"]
+dependencies = [
+    "httpx[http2]<0.29,>=0.26",
+    "python-dateutil<3.0.0,>=2.8.2",
+]
+files = [
+    {file = "storage3-0.11.3-py3-none-any.whl", hash = "sha256:090c42152217d5d39bd94af3ddeb60c8982f3a283dcd90b53d058f2db33e6007"},
+    {file = "storage3-0.11.3.tar.gz", hash = "sha256:883637132aad36d9d92b7c497a8a56dff7c51f15faf2ff7acbccefbbd5e97347"},
+]
+
+[[package]]
+name = "strenum"
+version = "0.4.15"
+summary = "An Enum that inherits from str."
+groups = ["default"]
+files = [
+    {file = "StrEnum-0.4.15-py3-none-any.whl", hash = "sha256:a30cda4af7cc6b5bf52c8055bc4bf4b2b6b14a93b574626da33df53cf7740659"},
+    {file = "StrEnum-0.4.15.tar.gz", hash = "sha256:878fb5ab705442070e4dd1929bb5e2249511c0bcf2b0eeacf3bcd80875c82eff"},
+]
+
+[[package]]
+name = "supabase"
+version = "2.15.1"
+requires_python = "<4.0,>=3.9"
+summary = "Supabase client for Python."
+groups = ["default"]
+dependencies = [
+    "gotrue<3.0.0,>=2.11.0",
+    "httpx<0.29,>=0.26",
+    "postgrest<1.1,>0.19",
+    "realtime<2.5.0,>=2.4.0",
+    "storage3<0.12,>=0.10",
+    "supafunc<0.10,>=0.9",
+]
+files = [
+    {file = "supabase-2.15.1-py3-none-any.whl", hash = "sha256:749299cdd74ecf528f52045c1e60d9dba81cc2054656f754c0ca7fba0dd34827"},
+    {file = "supabase-2.15.1.tar.gz", hash = "sha256:66e847dab9346062aa6a25b4e81ac786b972c5d4299827c57d1d5bd6a0346070"},
+]
+
+[[package]]
+name = "supafunc"
+version = "0.9.4"
+requires_python = "<4.0,>=3.9"
+summary = "Library for Supabase Functions"
+groups = ["default"]
+dependencies = [
+    "httpx[http2]<0.29,>=0.26",
+    "strenum<0.5.0,>=0.4.15",
+]
+files = [
+    {file = "supafunc-0.9.4-py3-none-any.whl", hash = "sha256:2b34a794fb7930953150a434cdb93c24a04cf526b2f51a9e60b2be0b86d44fb2"},
+    {file = "supafunc-0.9.4.tar.gz", hash = "sha256:68824a9a7bcccf5ab1e038cda632ba47cba27f2a7dc606014206b56f5a071de2"},
+]
+
 [[package]]
 name = "sympy"
 version = "1.14.0"
@@ -2199,6 +2536,26 @@ files = [
     {file = "tzdata-2025.2.tar.gz", hash = "sha256:b60a638fcc0daffadf82fe0f57e53d06bdec2f36c4df66280ae79bce6bd6f2b9"},
 ]
 
+[[package]]
+name = "ujson"
+version = "5.10.0"
+requires_python = ">=3.8"
+summary = "Ultra fast JSON encoder and decoder for Python"
+groups = ["default"]
+files = [
+    {file = "ujson-5.10.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:98ba15d8cbc481ce55695beee9f063189dce91a4b08bc1d03e7f0152cd4bbdd5"},
+    {file = "ujson-5.10.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a9d2edbf1556e4f56e50fab7d8ff993dbad7f54bac68eacdd27a8f55f433578e"},
+    {file = "ujson-5.10.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6627029ae4f52d0e1a2451768c2c37c0c814ffc04f796eb36244cf16b8e57043"},
+    {file = "ujson-5.10.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f8ccb77b3e40b151e20519c6ae6d89bfe3f4c14e8e210d910287f778368bb3d1"},
+    {file = "ujson-5.10.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f3caf9cd64abfeb11a3b661329085c5e167abbe15256b3b68cb5d914ba7396f3"},
+    {file = "ujson-5.10.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:6e32abdce572e3a8c3d02c886c704a38a1b015a1fb858004e03d20ca7cecbb21"},
+    {file = "ujson-5.10.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:a65b6af4d903103ee7b6f4f5b85f1bfd0c90ba4eeac6421aae436c9988aa64a2"},
+    {file = "ujson-5.10.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:604a046d966457b6cdcacc5aa2ec5314f0e8c42bae52842c1e6fa02ea4bda42e"},
+    {file = "ujson-5.10.0-cp312-cp312-win32.whl", hash = "sha256:6dea1c8b4fc921bf78a8ff00bbd2bfe166345f5536c510671bccececb187c80e"},
+    {file = "ujson-5.10.0-cp312-cp312-win_amd64.whl", hash = "sha256:38665e7d8290188b1e0d57d584eb8110951a9591363316dd41cf8686ab1d0abc"},
+    {file = "ujson-5.10.0.tar.gz", hash = "sha256:b3cd8f3c5d8c7738257f1018880444f7b7d9b66232c64649f562d7ba86ad4bc1"},
+]
+
 [[package]]
 name = "urllib3"
 version = "2.4.0"
@@ -2229,24 +2586,24 @@ files = [
 
 [[package]]
 name = "websockets"
-version = "15.0.1"
+version = "14.2"
 requires_python = ">=3.9"
 summary = "An implementation of the WebSocket Protocol (RFC 6455 & 7692)"
 groups = ["default"]
 files = [
-    {file = "websockets-15.0.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:3e90baa811a5d73f3ca0bcbf32064d663ed81318ab225ee4f427ad4e26e5aff3"},
-    {file = "websockets-15.0.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:592f1a9fe869c778694f0aa806ba0374e97648ab57936f092fd9d87f8bc03665"},
-    {file = "websockets-15.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:0701bc3cfcb9164d04a14b149fd74be7347a530ad3bbf15ab2c678a2cd3dd9a2"},
-    {file = "websockets-15.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e8b56bdcdb4505c8078cb6c7157d9811a85790f2f2b3632c7d1462ab5783d215"},
-    {file = "websockets-15.0.1-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0af68c55afbd5f07986df82831c7bff04846928ea8d1fd7f30052638788bc9b5"},
-    {file = "websockets-15.0.1-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:64dee438fed052b52e4f98f76c5790513235efaa1ef7f3f2192c392cd7c91b65"},
-    {file = "websockets-15.0.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:d5f6b181bb38171a8ad1d6aa58a67a6aa9d4b38d0f8c5f496b9e42561dfc62fe"},
-    {file = "websockets-15.0.1-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:5d54b09eba2bada6011aea5375542a157637b91029687eb4fdb2dab11059c1b4"},
-    {file = "websockets-15.0.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:3be571a8b5afed347da347bfcf27ba12b069d9d7f42cb8c7028b5e98bbb12597"},
-    {file = "websockets-15.0.1-cp312-cp312-win32.whl", hash = "sha256:c338ffa0520bdb12fbc527265235639fb76e7bc7faafbb93f6ba80d9c06578a9"},
-    {file = "websockets-15.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:fcd5cf9e305d7b8338754470cf69cf81f420459dbae8a3b40cee57417f4614a7"},
-    {file = "websockets-15.0.1-py3-none-any.whl", hash = "sha256:f7a866fbc1e97b5c617ee4116daaa09b722101d4a3c170c787450ba409f9736f"},
-    {file = "websockets-15.0.1.tar.gz", hash = "sha256:82544de02076bafba038ce055ee6412d68da13ab47f0c60cab827346de828dee"},
+    {file = "websockets-14.2-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:1f20522e624d7ffbdbe259c6b6a65d73c895045f76a93719aa10cd93b3de100c"},
+    {file = "websockets-14.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:647b573f7d3ada919fd60e64d533409a79dcf1ea21daeb4542d1d996519ca967"},
+    {file = "websockets-14.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:6af99a38e49f66be5a64b1e890208ad026cda49355661549c507152113049990"},
+    {file = "websockets-14.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:091ab63dfc8cea748cc22c1db2814eadb77ccbf82829bac6b2fbe3401d548eda"},
+    {file = "websockets-14.2-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b374e8953ad477d17e4851cdc66d83fdc2db88d9e73abf755c94510ebddceb95"},
+    {file = "websockets-14.2-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a39d7eceeea35db85b85e1169011bb4321c32e673920ae9c1b6e0978590012a3"},
+    {file = "websockets-14.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:0a6f3efd47ffd0d12080594f434faf1cd2549b31e54870b8470b28cc1d3817d9"},
+    {file = "websockets-14.2-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:065ce275e7c4ffb42cb738dd6b20726ac26ac9ad0a2a48e33ca632351a737267"},
+    {file = "websockets-14.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:e9d0e53530ba7b8b5e389c02282f9d2aa47581514bd6049d3a7cffe1385cf5fe"},
+    {file = "websockets-14.2-cp312-cp312-win32.whl", hash = "sha256:20e6dd0984d7ca3037afcb4494e48c74ffb51e8013cac71cf607fffe11df7205"},
+    {file = "websockets-14.2-cp312-cp312-win_amd64.whl", hash = "sha256:44bba1a956c2c9d268bdcdf234d5e5ff4c9b6dc3e300545cbe99af59dda9dcce"},
+    {file = "websockets-14.2-py3-none-any.whl", hash = "sha256:7a6ceec4ea84469f15cf15807a747e9efe57e369c384fa86e022b3bea679b79b"},
+    {file = "websockets-14.2.tar.gz", hash = "sha256:5059ed9c54945efb321f097084b4c7e52c246f2c869815876a69d1efc4ad6eb5"},
 ]
 
 [[package]]

pyproject.toml

@@ -5,7 +5,7 @@ description = "Default template for PDM package"
 authors = [
     {name = "Supphawit_Golf", email = "supphawit.n@gmail.com"},
 ]
-dependencies = ["langchain>=0.3.25", "huggingface-hub>=0.31.2", "pandas>=2.2.3", "langgraph>=0.4.5", "langchain-openai>=0.3.17", "dotenv>=0.9.9", "datasets>=3.6.0", "langchain-community>=0.3.24", "rank-bm25>=0.2.2", "langchain-huggingface>=0.2.0", "duckduckgo-search>=8.0.2", "requests>=2.32.3", "gradio>=5.29.1", "arxiv>=2.2.0", "pymupdf>=1.25.5"]
+dependencies = ["langchain>=0.3.25", "huggingface-hub>=0.31.2", "pandas>=2.2.3", "langgraph>=0.4.5", "langchain-openai>=0.3.17", "dotenv>=0.9.9", "datasets>=3.6.0", "langchain-community>=0.3.24", "rank-bm25>=0.2.2", "langchain-huggingface>=0.2.0", "duckduckgo-search>=8.0.2", "requests>=2.32.3", "gradio>=5.29.1", "arxiv>=2.2.0", "pymupdf>=1.25.5", "pymilvus>=2.5.9", "supabase>=2.15.1", "psycopg2-binary>=2.9.10"]
 requires-python = "==3.12.*"
 readme = "README.md"
 license = {text = "MIT"}

upload_metadata.py

@@ -0,0 +1,96 @@
+import json
+import os
+from dotenv import load_dotenv
+load_dotenv()
+with open('metadata.jsonl', 'r') as f: 
+    json_list = list(f)
+
+json_QA = []
+for json_str in json_list: 
+    json_data = json.loads(json_str)
+    json_QA.append(json_data)
+
+#test access to the metadata
+# import random
+# random_samples = random.sample(json_QA, 1)
+# for sample in random_samples:
+#     print("=" * 50)
+#     print(f"Task ID: {sample['task_id']}")
+#     print(f"Question: {sample['Question']}")
+#     print(f"Level: {sample['Level']}")
+#     print(f"Final Answer: {sample['Final answer']}")
+#     print(f"Annotator Metadata: ")
+#     print(f"  ├── Steps: ")
+#     for step in sample['Annotator Metadata']['Steps'].split('\n'):
+#         print(f"  │      ├── {step}")
+#     print(f"  ├── Number of steps: {sample['Annotator Metadata']['Number of steps']}")
+#     print(f"  ├── How long did this take?: {sample['Annotator Metadata']['How long did this take?']}")
+#     print(f"  ├── Tools:")
+#     for tool in sample['Annotator Metadata']['Tools'].split('\n'):
+#         print(f"  │      ├── {tool}")
+#     print(f"  └── Number of tools: {sample['Annotator Metadata']['Number of tools']}")
+# print("=" * 50)
+#initialize the supabase client
+import os
+from dotenv import load_dotenv
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_community.vectorstores import SupabaseVectorStore
+from supabase.client import Client, create_client
+from langchain.embeddings import OpenAIEmbeddings
+
+load_dotenv()
+
+supabase_url = os.environ.get("SUPABASE_URL")
+supabase_key = os.environ.get("SUPABASE_KEY")
+supabase: Client = create_client(supabase_url, supabase_key)
+
+#setup embedding model
+embeddings = OpenAIEmbeddings(
+    model="text-embedding-3-small",api_key=os.environ.get("OPENAI_KEY"))
+
+def get_embedding(text: str) -> list[float]:
+    """Get the embedding for a given text using OpenAI's API."""
+    response = embeddings.embed_query(text)
+    return response
+
+# #insert data into database
+# from langchain.schema import Document
+# docs = []
+# cnt = 0 
+# for sample in json_QA:
+#     content = f"Question : {sample['Question']}\n\nFinal answer : {sample['Final answer']}"
+#     doc = {
+#         "id" : cnt,
+#         "content" : content,
+#         "metadata" : {
+#             "source" : sample['task_id']
+#         },
+#         "embedding" : get_embedding(content),
+#     }
+#     docs.append(doc)
+#     cnt += 1
+# print(f'total number of documents: {cnt+1}')
+# # upload the documents to the vector database
+# try:
+#     response = (
+#         supabase.table("documents_agent")
+#         .insert(docs)
+#         .execute()
+#     )
+# except Exception as exception:
+#     print("Error inserting data into Supabase:", exception)
+
+#Check data in table and setup vectorstore
+# add items to vector database
+vector_store = SupabaseVectorStore(
+    client=supabase,
+    embedding= embeddings,
+    table_name="documents_agent",
+    query_name="match_documents",
+)
+retriever = vector_store.as_retriever()
+
+query = "On June 6, 2023, an article by Carolyn Collins Petersen was published in Universe Today. This article mentions a team that produced a paper about their observations, linked at the bottom of the article. Find this paper. Under what NASA award number was the work performed by R. G. Arendt supported by?"
+# matched_docs = vector_store.similarity_search(query, k=2)
+retrived_docs = retriever.invoke(query)
+print(retrived_docs[0])