-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
0 parents
commit 0ab044b
Showing
11 changed files
with
5,594 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,17 @@ | ||
{ | ||
"env": { | ||
"node": true | ||
}, | ||
"parserOptions": { | ||
"ecmaVersion": 2018, | ||
"sourceType": "module" | ||
}, | ||
"extends": "eslint:recommended", | ||
"rules": { | ||
"no-console": "warn", | ||
"no-var": "error", | ||
"prefer-const": "error", | ||
"eqeqeq": "error", | ||
"indent": ["error", 2] | ||
} | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,38 @@ | ||
name: Test Flowise Flow | ||
|
||
on: | ||
push: | ||
branches: ['main'] | ||
pull_request: | ||
branches: ['main'] | ||
|
||
jobs: | ||
build: | ||
runs-on: ubuntu-latest | ||
|
||
strategy: | ||
matrix: | ||
node-version: [18.x] | ||
|
||
steps: | ||
- uses: actions/checkout@v3 | ||
|
||
- name: Use Node.js ${{ matrix.node-version }} | ||
uses: actions/setup-node@v3 | ||
with: | ||
node-version: ${{ matrix.node-version }} | ||
|
||
- name: install flowise | ||
run: npm install -g flowise | ||
|
||
- name: install wait-on | ||
run: npm install -g wait-on | ||
|
||
- name: install dependencies | ||
run: npm install | ||
|
||
- name: main | ||
run: npx flowise start & | ||
wait-on tcp:3000 && | ||
OPENAI_API_KEY=${{ secrets.OPENAI_API_KEY }} npm run load && | ||
npm test |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,16 @@ | ||
coverage/ | ||
node_modules/ | ||
.DS_Store | ||
*.log | ||
|
||
# Editor directories and files | ||
.idea | ||
.vscode | ||
*.suo | ||
*.ntvs* | ||
*.njsproj | ||
*.sln | ||
*.sw* | ||
/test-results/ | ||
/playwright-report/* | ||
/playwright/.cache/ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,128 @@ | ||
# Chatea con tus archivos | ||
|
||
## Índice | ||
|
||
- [1. Consideraciones generales](#1-consideraciones-generales) | ||
- [2. Preámbulo](#2-preámbulo) | ||
- [3. Resumen del proyecto](#3-resumen-del-proyecto) | ||
- [4. Objetivos de aprendizaje](#4-objetivos-de-aprendizaje) | ||
- [5. Criterios de aceptación](#5-criterios-de-aceptación) | ||
- [6. Getting started](#6-getting-started) | ||
- [7. Valida tu solución](#7-valida-tu-solución) | ||
- [8. Recursos](#8-recursos) | ||
|
||
*** | ||
|
||
## 1. Consideraciones generales | ||
|
||
- Este proyecto lo resolvemos de manera **individual**. | ||
- El rango de tiempo estimado para completar el proyecto es de 1 a 2 Sprints. | ||
|
||
## 2. Preámbulo | ||
|
||
En los últimos años, la inteligencia artificial (IA) ha desempeñado un papel | ||
fundamental en prácticamente todos los aspectos de nuestra vida. No se limita | ||
solo al campo de la tecnología de la información, sino que se ha convertido en | ||
un campo donde las personas han desarrollado algoritmos "inteligentes" que | ||
tienen la capacidad de "entender" de manera similar a los seres humanos. Estos | ||
algoritmos tienen la capacidad de redactar ensayos, sistematizar información y | ||
hasta mantener conversaciones coherentes. | ||
|
||
La habilidad de dirigir eficazmente la IA y entender los diferentes tipos de | ||
herramientas que componen el ecosistema, son una competencia excepcionalmente | ||
poderosa, ya que nos permite aprovechar al máximo sus capacidades para | ||
automatizar tareas, optimizar procesos, generar contenido de alta calidad, | ||
analizar datos y mucho más. | ||
|
||
## 3. Resumen del proyecto | ||
|
||
Crearás un chatbot con la habilidad de contestar preguntas basadas en la | ||
información de un documento, por ejemplo un archivo `txt` o `pdf`, para esto | ||
podrás utilizar la herramienta [Flowise](https://flowiseai.com/) para extender | ||
la funcionalidad de un chatbot tradicional, crearás un chatflow utilizando las | ||
herramientas disponibles para darle esta capacidades a tu chatbot. | ||
|
||
![image](https://github.com/Laboratoria/DEV006-md-links/assets/5282075/2ef997e5-22b8-4f92-b4a0-9d000e31c4f1) | ||
|
||
## 4. Objetivos de aprendizaje | ||
|
||
Familiarizarse con los principales conceptos alrededor de la | ||
[Inteligencia Artificial Generativa](https://es.wikipedia.org/wiki/Inteligencia_artificial_generativa) | ||
y trabajar con [Flowise](https://docs.flowiseai.com/) para implementar | ||
soluciones AI expuestas atraves de una API. | ||
Flowise es una herramienta basada en [LangChain](https://docs.langchain.com/docs/), | ||
por lo que además deberás poder entender los conceptos fundamentales de esta | ||
herramienta. | ||
|
||
- [ ] [Flowise basics](https://www.youtube.com/watch?v=tD6fwQyUIJE&list=PL4HikwTaYE0HDOuXMm5sU6DH6_ZrHBLSJ) | ||
- [ ] [Langchain Components](https://docs.langchain.com/docs/category/components) | ||
- [ ] [Chat models](https://docs.flowiseai.com/chat-models) | ||
- [ ] [Chat Flows Basics](https://www.youtube.com/watch?v=fn4GCZuiwdk&list=PL4HikwTaYE0HDOuXMm5sU6DH6_ZrHBLSJ&index=3) | ||
|
||
- [ ] Document Labels | ||
+ [Flowise: Document loaders](https://docs.flowiseai.com/document-loaders) | ||
+ [Langchain Concepts: Document loaders](https://docs.langchain.com/docs/components/indexing/document-loaders) | ||
- [ ] Text Splitters | ||
+ [Text Splitters demo](https://www.youtube.com/watch?v=kMtf9sNIcao&list=PL4HikwTaYE0HDOuXMm5sU6DH6_ZrHBLSJ&index=3) | ||
+ [Langchain Concepts: Text Splitters](https://docs.langchain.com/docs/components/indexing/text-splitters) | ||
- [ ] [Embeddings](https://docs.flowiseai.com/embeddings/azure-openai-embeddings) | ||
- [ ] Vector Stores: | ||
+ [Flowise: Vector Stores](https://docs.flowiseai.com/vector-stores) | ||
+ [Langchain Concepts: Vector Stores](https://docs.langchain.com/docs/components/indexing/vectorstore) | ||
|
||
## 5. Criterios de aceptación | ||
|
||
1. Deberás configurar tu chatflow de manera que acepta la carga de al menos 1 | ||
archivo de texto, en formato `txt` o `pdf`. | ||
|
||
2. Utilizar el módelo `gpt-3.5-turbo`. | ||
|
||
3. El chatbot generado debe ser capaz de contestar preguntas usando la | ||
información de el/los archivos cargados. | ||
|
||
4. Tus github actions deben pasar exitosamente. | ||
|
||
5. Debes utilizar al menos lo siguientes nodos: | ||
|
||
- Conversational Retrival QA Chain | ||
- Document Loaders | ||
- Text Splitters | ||
- Vector Stores | ||
- Embeddings | ||
- Memory | ||
- Conversational Agent | ||
|
||
## 6. Getting started | ||
|
||
### Instalar Flowise | ||
|
||
Seguir las indicaciones para instalar globalmente [flowise](https://github.com/FlowiseAI/Flowise) | ||
|
||
```bash | ||
npm install -g flowise | ||
|
||
npx flowise start | ||
``` | ||
|
||
## 7. Valida tu solución | ||
|
||
Necesitarás definir una variable de ambiente con el nombre `OPENAI_API_KEY` y | ||
darle el valor de api key de OpenAI que utilizarás | ||
|
||
Antes de ejecutar los test copiar en la carpeta `/test` con el nombre | ||
`'flow.json'` el archivo de exportación del flow implementado | ||
|
||
```bash | ||
OPENAI_API_KEY=<TODO: poner tu api key> npm test | ||
``` | ||
|
||
Una vez inicializada la herramienta podrás acceder [aquí](http://localhost:3000/) | ||
|
||
Utilizarás esta herramienta para crear y configurar tu propia aplicación AI, | ||
la cual podrás utilizar por medio de la UI proporcionada y también a través de | ||
peticiones HTTP. | ||
|
||
## 8. Recursos | ||
|
||
- [Serie de tutoriales en youtube (inglés)](https://www.youtube.com/watch?v=tD6fwQyUIJE&list=PL4HikwTaYE0HDOuXMm5sU6DH6_ZrHBLSJ) | ||
- [Webscrap QnA](https://docs.flowiseai.com/use-cases/web-scrape-qna) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,196 @@ | ||
/** | ||
* For a detailed explanation regarding each configuration property, visit: | ||
* https://jestjs.io/docs/configuration | ||
*/ | ||
|
||
/** @type {import('jest').Config} */ | ||
module.exports = { | ||
// All imported modules in your tests should be mocked automatically | ||
// automock: false, | ||
|
||
// Stop running tests after `n` failures | ||
// bail: 0, | ||
|
||
// The directory where Jest should store its cached dependency information | ||
// cacheDirectory: "/private/var/folders/gf/65r9cr7x6t1874dxr5nktff80000gn/T/jest_dx", | ||
|
||
// Automatically clear mock calls, instances, contexts and results before every test | ||
clearMocks: true, | ||
|
||
// Indicates whether the coverage information should be collected while executing the test | ||
collectCoverage: true, | ||
|
||
// An array of glob patterns indicating a set of files for which coverage information should be collected | ||
// collectCoverageFrom: undefined, | ||
|
||
// The directory where Jest should output its coverage files | ||
coverageDirectory: 'coverage', | ||
|
||
// An array of regexp pattern strings used to skip coverage collection | ||
// coveragePathIgnorePatterns: [ | ||
// "/node_modules/" | ||
// ], | ||
|
||
// Indicates which provider should be used to instrument code for coverage | ||
// coverageProvider: "babel", | ||
|
||
// A list of reporter names that Jest uses when writing coverage reports | ||
// coverageReporters: [ | ||
// "json", | ||
// "text", | ||
// "lcov", | ||
// "clover" | ||
// ], | ||
|
||
// An object that configures minimum threshold enforcement for coverage results | ||
// coverageThreshold: undefined, | ||
|
||
// A path to a custom dependency extractor | ||
// dependencyExtractor: undefined, | ||
|
||
// Make calling deprecated APIs throw helpful error messages | ||
// errorOnDeprecated: false, | ||
|
||
// The default configuration for fake timers | ||
// fakeTimers: { | ||
// "enableGlobally": false | ||
// }, | ||
|
||
// Force coverage collection from ignored files using an array of glob patterns | ||
// forceCoverageMatch: [], | ||
|
||
// A path to a module which exports an async function that is triggered once before all test suites | ||
// globalSetup: undefined, | ||
|
||
// A path to a module which exports an async function that is triggered once after all test suites | ||
// globalTeardown: undefined, | ||
|
||
// A set of global variables that need to be available in all test environments | ||
// globals: {}, | ||
|
||
// The maximum amount of workers used to run your tests. Can be specified as % or a number. E.g. maxWorkers: 10% will use 10% of your CPU amount + 1 as the maximum worker number. maxWorkers: 2 will use a maximum of 2 workers. | ||
// maxWorkers: "50%", | ||
|
||
// An array of directory names to be searched recursively up from the requiring module's location | ||
// moduleDirectories: [ | ||
// "node_modules" | ||
// ], | ||
|
||
// An array of file extensions your modules use | ||
// moduleFileExtensions: [ | ||
// "js", | ||
// "mjs", | ||
// "cjs", | ||
// "jsx", | ||
// "ts", | ||
// "tsx", | ||
// "json", | ||
// "node" | ||
// ], | ||
|
||
// A map from regular expressions to module names or to arrays of module names that allow to stub out resources with a single module | ||
// moduleNameMapper: {}, | ||
|
||
// An array of regexp pattern strings, matched against all module paths before considered 'visible' to the module loader | ||
// modulePathIgnorePatterns: [], | ||
|
||
// Activates notifications for test results | ||
// notify: false, | ||
|
||
// An enum that specifies notification mode. Requires { notify: true } | ||
// notifyMode: "failure-change", | ||
|
||
// A preset that is used as a base for Jest's configuration | ||
// preset: undefined, | ||
|
||
// Run tests from one or more projects | ||
// projects: undefined, | ||
|
||
// Use this configuration option to add custom reporters to Jest | ||
// reporters: undefined, | ||
|
||
// Automatically reset mock state before every test | ||
// resetMocks: false, | ||
|
||
// Reset the module registry before running each individual test | ||
// resetModules: false, | ||
|
||
// A path to a custom resolver | ||
// resolver: undefined, | ||
|
||
// Automatically restore mock state and implementation before every test | ||
// restoreMocks: false, | ||
|
||
// The root directory that Jest should scan for tests and modules within | ||
// rootDir: undefined, | ||
|
||
// A list of paths to directories that Jest should use to search for files in | ||
// roots: [ | ||
// "<rootDir>" | ||
// ], | ||
|
||
// Allows you to use a custom runner instead of Jest's default test runner | ||
// runner: "jest-runner", | ||
|
||
// The paths to modules that run some code to configure or set up the testing environment before each test | ||
// setupFiles: [], | ||
|
||
// A list of paths to modules that run some code to configure or set up the testing framework before each test | ||
// setupFilesAfterEnv: [], | ||
|
||
// The number of seconds after which a test is considered as slow and reported as such in the results. | ||
// slowTestThreshold: 5, | ||
|
||
// A list of paths to snapshot serializer modules Jest should use for snapshot testing | ||
// snapshotSerializers: [], | ||
|
||
// The test environment that will be used for testing | ||
// testEnvironment: "jest-environment-node", | ||
|
||
// Options that will be passed to the testEnvironment | ||
// testEnvironmentOptions: {}, | ||
|
||
// Adds a location field to test results | ||
// testLocationInResults: false, | ||
|
||
// The glob patterns Jest uses to detect test files | ||
// testMatch: [ | ||
// "**/__tests__/**/*.[jt]s?(x)", | ||
// "**/?(*.)+(spec|test).[tj]s?(x)" | ||
// ], | ||
|
||
// An array of regexp pattern strings that are matched against all test paths, matched tests are skipped | ||
// testPathIgnorePatterns: [ | ||
// "/node_modules/" | ||
// ], | ||
|
||
// The regexp pattern or array of patterns that Jest uses to detect test files | ||
// testRegex: [], | ||
|
||
// This option allows the use of a custom results processor | ||
// testResultsProcessor: undefined, | ||
|
||
// This option allows use of a custom test runner | ||
// testRunner: "jest-circus/runner", | ||
|
||
// A map from regular expressions to paths to transformers | ||
// transform: undefined, | ||
|
||
// An array of regexp pattern strings that are matched against all source file paths, matched files will skip transformation | ||
// transformIgnorePatterns: [ | ||
// "/node_modules/", | ||
// "\\.pnp\\.[^\\/]+$" | ||
// ], | ||
|
||
// An array of regexp pattern strings that are matched against all modules before the module loader will automatically return a mock for them | ||
// unmockedModulePathPatterns: undefined, | ||
|
||
// Indicates whether each individual test should be reported during the run | ||
// verbose: undefined, | ||
|
||
// An array of regexp patterns that are matched against all source file paths before re-running tests in watch mode | ||
// watchPathIgnorePatterns: [], | ||
|
||
// Whether to use watchman for file crawling | ||
// watchman: true, | ||
}; |
Oops, something went wrong.