base on A Third-party GPTs store # GPTs Works GPTs Works is a Third-party GPTs store. ## Introduction This project consists of the following three parts👇 1. Website code located in the `web` directory. you can view a live demo at: [https://gpts.works](https://gpts.works)  2. Index System code located in the `index` directory. index system is used for searching GPTs with vector. there is a GPTs built with index system: [https://chat.openai.com/g/g-EBKM6RsBl-gpts-works](https://chat.openai.com/g/g-EBKM6RsBl-gpts-works)  3. Browser Extension code located in the `extension` directory. browser extension is used to show Third-party GPTs beside ChatGPT Explore page.  ## Dependencies - [Vercel](https://vercel.com/): used for deploying website - [Vercel Storage Postgres](https://vercel.com/docs/storage/vercel-postgres): used for storing data. - [Zilliz Cloud](https://cloud.zilliz.com/): used for vector storing and searching ## Deploy with Vercel [](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Fall-in-aigc%2Fgpts-works&env=POSTGRES_URL,INDEX_API_BASE_URI,INDEX_API_KEY&envDescription=Create%20your%20Vercel%20Postgres%20DB%20firstly%20before%20set%20POSTGRES_URL%20value.&envLink=https%3A%2F%2Fgithub.com%2Fall-in-aigc%2Fgpts-works%3Ftab%3Dreadme-ov-file%23dependencies&project-name=my-gpts-works&repository-name=my-gpts-works&redirect-url=https%3A%2F%2Fgpts.works&demo-title=GPTs%20Works&demo-description=A%20Third-party%20GPTs%20Store.&demo-url=https%3A%2F%2Fgpts.works&demo-image=https%3A%2F%2Fgpts.works%2Flogo.png) ## Local development ### Clone project ```shell git clone https://github.com/all-in-aigc/gpts-works.git path-to-project ``` ### Prepare data 1. create table in your postgres database with sql: ```sql CREATE TABLE gpts ( id SERIAL PRIMARY KEY, uuid VARCHAR(255) UNIQUE NOT NULL, org_id VARCHAR(255), name VARCHAR(255), description TEXT, avatar_url TEXT, short_url VARCHAR(255), author_id VARCHAR(255), author_name VARCHAR(255), created_at timestamptz, updated_at timestamptz, detail JSON, index_updated_at INT NOT NULL DEFAULT 0 ); ``` 2. insert your own GPTs data into your postgres database ### Start with Website 1. locate a .env file in dir `path-to-project/web` with content: ``` POSTGRES_URL="postgres://default:[email protected]/verceldb" INDEX_API_BASE_URI="http://127.0.0.1:8068" INDEX_API_KEY="gsk-xxx" ``` 2. install dependencies ```shell pnpm install ``` 3. start web server ``` make dev ``` 4. preview website open `http://localhost:8067` ### Start with Index System 1. locate a .env file in `path-to-project/index` with content ``` DATABASE_URL=postgres://default:[email protected]:5432/verceldb AZURE_API_KEY=xxx AZURE_API_BASE=https://xxx.openai.azure.com/ AZURE_API_VERSION=2023-07-01-preview AZURE_LLM_MODEL=gpt-35-turbo-16k AZURE_EMBED_MODEL=text-embedding-ada-002 STORE_TYPE=zilliz STORE_URI=https://xxx.zillizcloud.com STORE_TOKEN=xxx STORE_DIM=1536 STORE_COLLECTION=gpts INDEX_API_KEY=gsk-xxx ``` 2. install dependencies ```shell pip install -r requirements.txt ``` 3. start api server ``` make dev ``` 4. build index for gpts data ``` curl -X POST -H "Authorization: Bearer gsk-xxx" http://127.0.0.1:8068/gpts/index ``` 5. search gpts from index ``` curl -X POST -H "Authorization: Bearer gsk-xxx" -H "Content-Type: application/json" -d '{"question": "What GPTs are used for coding?"}' http://127.0.0.1:8068/gpts/index ``` ### Start with Extension goto `path-to-project/extension` 1. install dependencies ``` pnpm install ``` 2. start server ``` make dev ``` 3. debug extension open `chrome://extensions/`, click `Load unpacked` ## Thanks to - [GPTs Hunter](https://www.gptshunter.com) for sharing gpts-data - [next.js](https://github.com/vercel/next.js) for web deployment - [fastapi](https://github.com/tiangolo/fastapi) for building index system - [plasmo](https://github.com/PlasmoHQ/plasmo) for browser extension development > if this project is helpful to you, buy me a coffee😄 <a href="https://www.buymeacoffee.com/idoubi" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/default-orange.png" alt="Buy Me A Coffee" height="41" width="174"></a> ## Star History [](https://star-history.com/#all-in-aigc/gpts-works&Date) ", Assign "at most 3 tags" to the expected json: {"id":"4993","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"