├── .cargo └── config.toml ├── .gitignore ├── Cargo.toml ├── LICENSE ├── README.md ├── pg_gpt.control └── src └── lib.rs /.cargo/config.toml: -------------------------------------------------------------------------------- 1 | [target.'cfg(target_os="macos")'] 2 | # Postgres symbols won't be available until runtime 3 | rustflags = ["-Clink-arg=-Wl,-undefined,dynamic_lookup"] 4 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | .DS_Store 2 | .idea/ 3 | /target 4 | *.iml 5 | **/*.rs.bk 6 | Cargo.lock 7 | -------------------------------------------------------------------------------- /Cargo.toml: -------------------------------------------------------------------------------- 1 | [package] 2 | name = "pg_gpt" 3 | version = "0.0.0" 4 | edition = "2021" 5 | 6 | [lib] 7 | crate-type = ["cdylib"] 8 | 9 | [features] 10 | default = ["pg13"] 11 | pg11 = ["pgx/pg11", "pgx-tests/pg11" ] 12 | pg12 = ["pgx/pg12", "pgx-tests/pg12" ] 13 | pg13 = ["pgx/pg13", "pgx-tests/pg13" ] 14 | pg14 = ["pgx/pg14", "pgx-tests/pg14" ] 15 | pg15 = ["pgx/pg15", "pgx-tests/pg15" ] 16 | pg_test = [] 17 | 18 | [dependencies] 19 | openai = "1.0.0-alpha.7" 20 | pgx = "=0.7.4" 21 | tokio = { version = "1.26.0", features = ["full"] } 22 | 23 | [dev-dependencies] 24 | pgx-tests = "=0.7.4" 25 | 26 | [profile.dev] 27 | panic = "unwind" 28 | 29 | [profile.release] 30 | panic = "unwind" 31 | opt-level = 3 32 | lto = "fat" 33 | codegen-units = 1 34 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright 2023 CloudQuery Inc. 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Postgres <> ChatGPT 2 | 3 | Experimental PostgreSQL extension that enables the use of OpenAI GPT API inside PostgreSQL, allowing for queries to be written using natural language. 4 | 5 | ## Demo 6 | 7 | https://user-images.githubusercontent.com/1121616/228234378-40c796d3-0a38-465a-92da-9370fb21b93b.mp4 8 | 9 | (This demo uses data from the [Hacker News](https://www.cloudquery.io/integrations/hackernews/postgresql) and [Azure](https://www.cloudquery.io/integrations/azure/postgresql) CloudQuery plugins) 10 | 11 | ## How does it work? 12 | 13 | The extension sends a subset of the database schema to ChatGPT and asks it to generate a query based on this and the user input. 14 | 15 | ## Before you start 16 | 17 | - **Note**: This plugins sends schema (without the data) to OpenAI GPT API, so it is not recommended to use it on production databases. 18 | - **Note**: This is an experimental plugin and not officially supported by CloudQuery. 19 | 20 | ## Installation 21 | 22 | Requires [pgx](https://github.com/tcdi/pgx). Install this first: 23 | 24 | ```bash 25 | cargo install --locked cargo-pgx 26 | cargo pgx init 27 | ``` 28 | 29 | Now you can install the extension: 30 | 31 | ```bash 32 | git clone https://github.com/cloudquery/pg_gpt 33 | cd pg_gpt 34 | export OPENAI_KEY= 35 | cargo pgx run 36 | # will drop into psql shell 37 | ``` 38 | 39 | ```sql 40 | create extension pg_gpt; 41 | set openai.key = ''; -- set your key 42 | select gpt('show me all open aws s3 buckets'); 43 | -- will output the following query, so you can execute it 44 | -- select * from aws_s3_bucket; 45 | ``` 46 | 47 | ## Available Functions 48 | 49 | - `gpt(text)` - Generates a query based on the user input and the full database schema. This works fine for databases with small schemas. 50 | - `gpt_tables(table_pattern, text)` - Similar to gpt, but only uses the tables that match the pattern. The pattern is passed to a `table_name LIKE` query, so `%` can be used as wildcard. 51 | 52 | ## Installing the extension on an existing Postgres instance 53 | 54 | First run: 55 | 56 | ```bash 57 | cargo pgx install 58 | ``` 59 | 60 | This places the extension in the postgres extensions directory. Then, in your postgres instance, run: 61 | 62 | ```sql 63 | create extension pg_gpt; 64 | set openai.key = ''; 65 | -- proceed to use the extension 66 | ``` 67 | 68 | ## Limitations 69 | 70 | * Schema Size - Currently we use gpt-3.5-turbo, which is limited to 4096 tokens. Use `gpt_tables` to narrow down the set of tables. 71 | -------------------------------------------------------------------------------- /pg_gpt.control: -------------------------------------------------------------------------------- 1 | comment = 'pg_gpt: Created by pgx' 2 | default_version = '@CARGO_VERSION@' 3 | module_pathname = '$libdir/pg_gpt' 4 | relocatable = false 5 | superuser = true 6 | -------------------------------------------------------------------------------- /src/lib.rs: -------------------------------------------------------------------------------- 1 | use pgx::{prelude::*}; 2 | use tokio::runtime::Runtime; 3 | 4 | use openai::{ 5 | chat::{ChatCompletion, ChatCompletionMessage, ChatCompletionMessageRole}, 6 | set_key, 7 | }; 8 | 9 | use std::{ 10 | env, 11 | }; 12 | 13 | pgx::pg_module_magic!(); 14 | 15 | 16 | #[pg_extern] 17 | fn gpt(input: &str) -> String { 18 | gpt_tables("%", input) 19 | } 20 | 21 | #[pg_extern] 22 | fn gpt_tables(table_pattern: &str, input: &str) -> String { 23 | match env::var("OPENAI_KEY") { 24 | Ok(val) => set_key(val), 25 | Err(_) => { 26 | let open_ai_key_sql = "SELECT current_setting('openai.key');"; 27 | let open_ai_key: Result, pgx::spi::Error> = Spi::get_one(open_ai_key_sql); 28 | if open_ai_key.is_err() { 29 | return format!("Error: {}", open_ai_key.err().unwrap()); 30 | } 31 | if open_ai_key.as_ref().unwrap().is_none() { 32 | return format!("Error: {}", "openai.key not set"); 33 | } 34 | set_key(open_ai_key.unwrap().unwrap()); 35 | }, 36 | } 37 | 38 | let schema_sql = format!("SELECT json_object_agg(table_name, columns)::text 39 | FROM ( 40 | SELECT table_name, json_object_agg(column_name, data_type) AS columns 41 | FROM information_schema.columns 42 | WHERE table_schema = 'public' AND table_name SIMILAR TO '{}' AND table_name NOT LIKE '_pg%' 43 | GROUP BY table_name 44 | ) subquery;", table_pattern); 45 | 46 | let rt = Runtime::new().unwrap(); 47 | // let mut schema = String::new(); 48 | let mut schema: Result, pgx::spi::Error> = Spi::get_one(schema_sql.as_str()); 49 | if schema.is_err() { 50 | return format!("Error: {}", schema.err().unwrap()); 51 | } 52 | if schema.as_ref().unwrap().is_none() { 53 | return format!("Error: {}", "No result"); 54 | } 55 | 56 | let mut schema_str = schema.unwrap().unwrap(); 57 | if schema_str.len() > 10000 { 58 | // if results are too long, take out the data types 59 | let schema_sql = format!("SELECT json_object_agg(table_name, columns)::text 60 | FROM ( 61 | SELECT table_name, json_agg(column_name) AS columns 62 | FROM information_schema.columns 63 | WHERE table_schema = 'public' AND table_name SIMILAR TO '{}' AND table_name NOT LIKE '_pg%' 64 | GROUP BY table_name 65 | ) subquery;", table_pattern); 66 | 67 | schema = Spi::get_one(schema_sql.as_str()); 68 | if schema.is_err() { 69 | return format!("Error: {}", schema.err().unwrap()); 70 | } 71 | if schema.as_ref().unwrap().is_none() { 72 | return format!("Error: {}", "No result"); 73 | } 74 | schema_str = schema.unwrap().unwrap(); 75 | } 76 | 77 | let mut messages = vec![ChatCompletionMessage { 78 | role: ChatCompletionMessageRole::System, 79 | content: "You are a SQL assistant that helps translate questions into SQL.".to_string(), 80 | name: None, 81 | }]; 82 | 83 | println!("Schema: {}", schema_str.as_str()); 84 | 85 | messages.push(ChatCompletionMessage { 86 | role: ChatCompletionMessageRole::User, 87 | content: format!("Here is a schema for the database in json format: {}", schema_str), 88 | name: None, 89 | }); 90 | messages.push(ChatCompletionMessage { 91 | role: ChatCompletionMessageRole::User, 92 | content: format!("Please return an SQL statement as a single string for the following question. You must respond ONLY with SQL, nothing else. Do NOT use any tables other than the ones provided. The question is: {}", input), 93 | name: None, 94 | }); 95 | 96 | let chat_completion = rt.block_on(async move { 97 | ChatCompletion::builder("gpt-3.5-turbo", messages.clone()) 98 | .create() 99 | .await 100 | .unwrap() 101 | .unwrap() 102 | }); 103 | let returned_message = chat_completion.choices.first().unwrap().message.clone(); 104 | 105 | returned_message.content.to_string() 106 | } 107 | 108 | #[cfg(any(test, feature = "pg_test"))] 109 | #[pg_schema] 110 | mod tests { 111 | use pgx::prelude::*; 112 | 113 | #[pg_test] 114 | fn test_gpt() { 115 | extension_sql!( 116 | r#" 117 | CREATE TABLE examples ( 118 | id serial8 not null primary key, 119 | title text 120 | ); 121 | "#, 122 | name = "create_example_table", 123 | ); 124 | assert_eq!("SELECT title FROM examples;", crate::gpt("list all example titles")); 125 | 126 | // now test with a table pattern 127 | extension_sql!( 128 | r#" 129 | CREATE TABLE book_authors ( 130 | id serial8 not null primary key, 131 | name text 132 | ); 133 | CREATE TABLE books ( 134 | id serial8 not null primary key, 135 | author_id serial8 not null references book_authors(id), 136 | title text 137 | ); 138 | "#, 139 | name = "create_book_tables", 140 | ); 141 | assert_eq!("SELECT title \nFROM books \nJOIN book_authors ON books.author_id = book_authors.id \nWHERE book_authors.name = 'Shakespeare';", crate::gpt_tables("book%" ,"list all books written by Shakespeare")); 142 | } 143 | } 144 | 145 | /// This module is required by `cargo pgx test` invocations. 146 | /// It must be visible at the root of your extension crate. 147 | #[cfg(test)] 148 | pub mod pg_test { 149 | pub fn setup(_options: Vec<&str>) { 150 | // perform one-off initialization when the pg_test framework starts 151 | } 152 | 153 | pub fn postgresql_conf_options() -> Vec<&'static str> { 154 | // return any postgresql.conf settings that are required for your tests 155 | vec![] 156 | } 157 | } 158 | --------------------------------------------------------------------------------