From 6ed26f06b30fcc1f3956dc2d773f1c0bf4ee321f Mon Sep 17 00:00:00 2001 From: Erik Mackdanz Date: Tue, 26 Nov 2024 10:04:29 -0600 Subject: [PATCH] basic postgresql connect --- .gitignore | 1 + Cargo.lock | 314 ++++++++++++++++++++++++++++++++++++++++++++++++++++ Cargo.toml | 3 +- src/main.rs | 27 ++++- 4 files changed, 343 insertions(+), 2 deletions(-) diff --git a/.gitignore b/.gitignore index ea8c4bf..a364025 100644 --- a/.gitignore +++ b/.gitignore @@ -1 +1,2 @@ /target +*.gpg diff --git a/Cargo.lock b/Cargo.lock index ce35083..e03fcbf 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -93,6 +93,17 @@ dependencies = [ "derive_arbitrary", ] +[[package]] +name = "async-trait" +version = "0.1.83" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "721cae7de5c34fbb2acd27e21e6d2cf7b886dce0c27388d46c4e6c47ea4318dd" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + [[package]] name = "atomic-waker" version = "1.1.2" @@ -159,6 +170,15 @@ version = "2.6.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "b048fb63fd8b5923fc5aa7b340d8e156aec7ec02f0c78fa8a6ddc2613f6f71de" +[[package]] +name = "block-buffer" +version = "0.10.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3078c7629b62d3f0439517fa394996acacc5cbc91c5a20d8c658e77abd503a71" +dependencies = [ + "generic-array", +] + [[package]] name = "bumpalo" version = "3.16.0" @@ -312,6 +332,7 @@ dependencies = [ "candle-transformers", "clap", "hf-hub", + "postgres", "serde_json", "tokenizers 0.20.3", "tracing-chrome", @@ -408,6 +429,15 @@ version = "0.8.7" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b" +[[package]] +name = "cpufeatures" +version = "0.2.16" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "16b80225097f2e5ae4e7179dd2266824648f3e2f49d9134d584b76389d31c4c3" +dependencies = [ + "libc", +] + [[package]] name = "crc32fast" version = "1.4.2" @@ -448,6 +478,16 @@ version = "0.2.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "7a81dae078cea95a014a339291cec439d2f232ebe854a9d672b796c6afafa9b7" +[[package]] +name = "crypto-common" +version = "0.1.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1bfb12502f3fc46cca1bb51ac28df9d618d813cdc3d2f25b9fe775a34af26bb3" +dependencies = [ + "generic-array", + "typenum", +] + [[package]] name = "csv" version = "1.3.1" @@ -546,6 +586,17 @@ dependencies = [ "syn", ] +[[package]] +name = "digest" +version = "0.10.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292" +dependencies = [ + "block-buffer", + "crypto-common", + "subtle", +] + [[package]] name = "dirs" version = "5.0.1" @@ -646,6 +697,12 @@ dependencies = [ "cc", ] +[[package]] +name = "fallible-iterator" +version = "0.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4443176a9f2c162692bd3d352d745ef9413eec5782a80d8fd6f8a1ac692a07f7" + [[package]] name = "fancy-regex" version = "0.13.0" @@ -919,6 +976,16 @@ dependencies = [ "seq-macro", ] +[[package]] +name = "generic-array" +version = "0.14.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "85649ca51fd72272d7821adaf274ad91c288277713d9c18820d8499a7ff69e9a" +dependencies = [ + "typenum", + "version_check", +] + [[package]] name = "getrandom" version = "0.2.15" @@ -1004,6 +1071,15 @@ dependencies = [ "ureq", ] +[[package]] +name = "hmac" +version = "0.12.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6c49c37c09c17a53d937dfbb742eb3a961d65a994e6bcdcf37e7399d0cc8ab5e" +dependencies = [ + "digest", +] + [[package]] name = "http" version = "1.1.0" @@ -1383,6 +1459,16 @@ version = "0.7.4" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "4ee93343901ab17bd981295f2cf0026d4ad018c7c31ba84549a4ddbb47a45104" +[[package]] +name = "lock_api" +version = "0.4.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "07af8b9cdd281b7915f413fa73f29ebd5d55d0d3f0155584dade1ff18cea1b17" +dependencies = [ + "autocfg", + "scopeguard", +] + [[package]] name = "log" version = "0.4.22" @@ -1405,6 +1491,16 @@ version = "0.2.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "b8dd856d451cc0da70e2ef2ce95a18e39a93b7558bedf10201ad28503f918568" +[[package]] +name = "md-5" +version = "0.10.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d89e7ee0cfbedfc4da3340218492196241d89eefb6dab27de5df917a6d2e78cf" +dependencies = [ + "cfg-if", + "digest", +] + [[package]] name = "memchr" version = "2.7.4" @@ -1718,6 +1814,29 @@ version = "0.1.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "b15813163c1d831bf4a13c3610c05c0d03b39feb07f7e09fa234dac9b15aaf39" +[[package]] +name = "parking_lot" +version = "0.12.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f1bf18183cf54e8d6059647fc3063646a1801cf30896933ec2311622cc4b9a27" +dependencies = [ + "lock_api", + "parking_lot_core", +] + +[[package]] +name = "parking_lot_core" +version = "0.9.10" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1e401f977ab385c9e4e3ab30627d6f26d00e2c73eef317493c4ec6d468726cf8" +dependencies = [ + "cfg-if", + "libc", + "redox_syscall", + "smallvec", + "windows-targets 0.52.6", +] + [[package]] name = "paste" version = "1.0.15" @@ -1730,6 +1849,24 @@ version = "2.3.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "e3148f5046208a5d56bcfc03053e3ca6334e51da8dfb19b6cdc8b306fae3283e" +[[package]] +name = "phf" +version = "0.11.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ade2d8b8f33c7333b51bcf0428d37e217e9f32192ae4772156f65063b8ce03dc" +dependencies = [ + "phf_shared", +] + +[[package]] +name = "phf_shared" +version = "0.11.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "90fcb95eef784c2ac79119d1dd819e162b5da872ce6f3c3abe1e8ca1c082f72b" +dependencies = [ + "siphasher", +] + [[package]] name = "pin-project-lite" version = "0.2.15" @@ -1767,6 +1904,49 @@ version = "1.10.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "280dc24453071f1b63954171985a0b0d30058d287960968b9b2aca264c8d4ee6" +[[package]] +name = "postgres" +version = "0.19.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "95c918733159f4d55d2ceb262950f00b0aebd6af4aa97b5a47bb0655120475ed" +dependencies = [ + "bytes", + "fallible-iterator", + "futures-util", + "log", + "tokio", + "tokio-postgres", +] + +[[package]] +name = "postgres-protocol" +version = "0.6.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "acda0ebdebc28befa84bee35e651e4c5f09073d668c7aed4cf7e23c3cda84b23" +dependencies = [ + "base64 0.22.1", + "byteorder", + "bytes", + "fallible-iterator", + "hmac", + "md-5", + "memchr", + "rand", + "sha2", + "stringprep", +] + +[[package]] +name = "postgres-types" +version = "0.2.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f66ea23a2d0e5734297357705193335e0a957696f34bed2f2faefacb2fec336f" +dependencies = [ + "bytes", + "fallible-iterator", + "postgres-protocol", +] + [[package]] name = "ppv-lite86" version = "0.2.20" @@ -1901,6 +2081,15 @@ version = "0.5.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "03251193000f4bd3b042892be858ee50e8b3719f2b08e5833ac4353724632430" +[[package]] +name = "redox_syscall" +version = "0.5.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9b6dfecf2c74bce2466cabf93f6664d6998a69eb21e39f4207930065b27b771f" +dependencies = [ + "bitflags 2.6.0", +] + [[package]] name = "redox_users" version = "0.4.6" @@ -2093,6 +2282,12 @@ dependencies = [ "windows-sys 0.59.0", ] +[[package]] +name = "scopeguard" +version = "1.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49" + [[package]] name = "security-framework" version = "2.11.1" @@ -2175,6 +2370,17 @@ dependencies = [ "serde", ] +[[package]] +name = "sha2" +version = "0.10.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "793db75ad2bcafc3ffa7c68b215fee268f537982cd901d132f89c6343f3a3dc8" +dependencies = [ + "cfg-if", + "cpufeatures", + "digest", +] + [[package]] name = "sharded-slab" version = "0.1.7" @@ -2196,6 +2402,12 @@ version = "0.3.7" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "d66dc143e6b11c1eddc06d5c423cfc97062865baf299914ab64caa38182078fe" +[[package]] +name = "siphasher" +version = "0.3.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "38b58827f4464d87d377d175e90bf58eb00fd8716ff0a62f80356b5e61555d0d" + [[package]] name = "slab" version = "0.4.9" @@ -2256,6 +2468,17 @@ version = "1.2.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "a8f112729512f8e442d81f95a8a7ddf2b7c6b8a1a6f509a95864142b30cab2d3" +[[package]] +name = "stringprep" +version = "0.1.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7b4df3d392d81bd458a8a621b8bffbd2302a12ffe288a9d931670948749463b1" +dependencies = [ + "unicode-bidi", + "unicode-normalization", + "unicode-properties", +] + [[package]] name = "strsim" version = "0.11.1" @@ -2387,6 +2610,21 @@ dependencies = [ "zerovec", ] +[[package]] +name = "tinyvec" +version = "1.8.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "445e881f4f6d382d5f27c034e25eb92edd7c784ceab92a0937db7f2e9471b938" +dependencies = [ + "tinyvec_macros", +] + +[[package]] +name = "tinyvec_macros" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20" + [[package]] name = "tokenizers" version = "0.19.1" @@ -2487,6 +2725,32 @@ dependencies = [ "tokio", ] +[[package]] +name = "tokio-postgres" +version = "0.7.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3b5d3742945bc7d7f210693b0c58ae542c6fd47b17adbbda0885f3dcb34a6bdb" +dependencies = [ + "async-trait", + "byteorder", + "bytes", + "fallible-iterator", + "futures-channel", + "futures-util", + "log", + "parking_lot", + "percent-encoding", + "phf", + "pin-project-lite", + "postgres-protocol", + "postgres-types", + "rand", + "socket2", + "tokio", + "tokio-util", + "whoami", +] + [[package]] name = "tokio-rustls" version = "0.26.0" @@ -2608,6 +2872,12 @@ version = "0.2.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "e421abadd41a4225275504ea4d6566923418b7f05506fbc9c0fe86ba7396114b" +[[package]] +name = "typenum" +version = "1.17.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "42ff0bf0c66b8238c6f3b578df37d0b7848e55df8577b3f74f92a69acceeb825" + [[package]] name = "ug" version = "0.0.2" @@ -2621,12 +2891,27 @@ dependencies = [ "thiserror", ] +[[package]] +name = "unicode-bidi" +version = "0.3.17" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5ab17db44d7388991a428b2ee655ce0c212e862eff1768a455c58f9aad6e7893" + [[package]] name = "unicode-ident" version = "1.0.14" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "adb9e6ca4f869e1180728b7950e35922a7fc6397f7b641499e8f3ef06e50dc83" +[[package]] +name = "unicode-normalization" +version = "0.1.24" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5033c97c4262335cded6d6fc3e5c18ab755e1a3dc96376350f3d8e9f009ad956" +dependencies = [ + "tinyvec", +] + [[package]] name = "unicode-normalization-alignments" version = "0.1.12" @@ -2636,6 +2921,12 @@ dependencies = [ "smallvec", ] +[[package]] +name = "unicode-properties" +version = "0.1.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e70f2a8b45122e719eb623c01822704c4e0907e7e426a05927e1a1cfff5b75d0" + [[package]] name = "unicode-segmentation" version = "1.12.0" @@ -2727,6 +3018,12 @@ version = "0.2.15" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "accd4ea62f7bb7a82fe23066fb0957d48ef677f6eeb8215f372f52e48bb32426" +[[package]] +name = "version_check" +version = "0.9.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a" + [[package]] name = "walkdir" version = "2.5.0" @@ -2752,6 +3049,12 @@ version = "0.11.0+wasi-snapshot-preview1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423" +[[package]] +name = "wasite" +version = "0.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b8dad83b4f25e74f184f64c43b150b91efe7647395b42289f38e50566d82855b" + [[package]] name = "wasm-bindgen" version = "0.2.95" @@ -2848,6 +3151,17 @@ dependencies = [ "rustls-pki-types", ] +[[package]] +name = "whoami" +version = "1.5.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "372d5b87f58ec45c384ba03563b03544dc5fadc3983e434b286913f5b4a9bb6d" +dependencies = [ + "redox_syscall", + "wasite", + "web-sys", +] + [[package]] name = "winapi" version = "0.3.9" diff --git a/Cargo.toml b/Cargo.toml index 6dc903b..ccd6a2c 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -9,8 +9,9 @@ candle-core = "0.8.0" candle-examples = "0.8.0" candle-nn = "0.8.0" candle-transformers = "0.8.0" -clap = { version = "4.5.21", features = ["derive"] } +clap = { version = "4.5.21", features = ["derive", "env"] } hf-hub = "0.3.2" +postgres = "0.19.9" serde_json = "1.0.133" tokenizers = "0.20.3" tracing-chrome = "0.7.2" diff --git a/src/main.rs b/src/main.rs index 3b641ad..2c25a7f 100644 --- a/src/main.rs +++ b/src/main.rs @@ -5,13 +5,24 @@ use candle_core::Tensor; use candle_nn::VarBuilder; use clap::{Parser,Subcommand}; use hf_hub::{api::sync::Api, Repo, RepoType}; +use postgres::NoTls; use tokenizers::Tokenizer; #[derive(Subcommand,Debug)] enum Action { /// Initialize the database when the table doesn't exist already - InitDatabase, + InitDatabase { + + #[arg(long)] + host: String, + + #[arg(long)] + user: String, + + #[arg(long)] + password: String, + }, /// Add one document to the database index Index, @@ -127,5 +138,19 @@ fn main() -> Result<()> { println!("Took {:?}", start.elapsed()); } } + + match args.action { + Action::InitDatabase{ host, user, password } => { + println!("initializing the database with user {}", user); + let _client = postgres::Config::new() + .dbname("postgres") + .host(&host.to_string()) + .user(&user.to_string()) + .password(password) + .connect(NoTls)?; + } + _ => {} + } + Ok(()) } -- 2.52.0