0.11.0: Added optional password authentication

.env.template

@@ -2,6 +2,7 @@ REPO_NAME=MyRepo
 REPO_URL=https://github.com/user/MyRepo.git
 REPO_PATH=./examples
 INGEST_SECRET=9640f515-fd2c-4403-845f-71b25fc9086c
+INTERFACE_PASSWORD=f4bccbf2-cfdc-452d-b39a-fea61b1687fe  # leave empty for no password on interface
 OPENAI_API_KEY=XXX
 MODEL_TYPE_INFERENCE=gpt-4o-mini
 MODEL_TYPE_EMBEDDING=text-embedding-3-small

.github/workflows/deploy.yml

@@ -15,11 +15,12 @@ jobs:
               name: 'Deploy Repochat'
               id: deploy_repochat
               with:
-                dirs_to_scan: "README.md,package.json,Dockerfile,api,action,app" # comma-separated glob dirs to analyze from this repo
+                dirs_to_scan: "README.md,package.json,Dockerfile,api,action,app"
+                interface_password: ${{ secrets.INTERFACE_PASSWORD }}
                 openai_api_key: ${{ secrets.OPENAI_API_KEY }}
                 openai_model_type_inference: "gpt-4o-mini"
                 openai_model_type_embedding : "text-embedding-3-small"
-                cloud_provider: 'scaleway'
+                provider_name: 'scaleway'
                 provider_key_id: ${{ secrets.PROVIDER_KEY_ID }}
                 provider_key_secret: ${{ secrets.PROVIDER_KEY_SECRET }}
                 provider_project_id: ${{ secrets.PROVIDER_PROJECT_ID }}

README.md

@@ -4,13 +4,18 @@
 [![GitHub release](https://img.shields.io/github/v/release/flavienbwk/repochat-action)](https://github.com/flavienbwk/repochat-action/releases/latest)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
-> [!CAUTION]
-> This project is currently NOT ready.
-> This project is in early development and may contain bugs or incomplete features. Use with caution in production environments.
+> [!WARNING]
+> This project is in early development and may contain bugs. Use with caution in production environments.
 
-Chat with your repo in under 2 minutes using GitHub Actions on supported Cloud providers.
+Chat with your repo in under 2 minutes using GitHub Actions on [supported Cloud providers](#supported-cloud-providers).
 
-Repochat is a LLM chatbot with stateless data ingestion capabilities through its API.
+Features:
+
+- :sparkles: A nice web UI
+- :octocat: Available as a GitHub Action
+- :floppy_disk: Stateful ingestion mode ([directory mode](./dir.docker-compose.yml#L6))
+- :arrows_counterclockwise: Sateless ingestion via API ([api mode](./api.docker-compose.yml#L6))
+- :closed_lock_with_key: Optional password on web UI
 
 ## Requirements
 
@@ -19,26 +24,29 @@ Repochat is a LLM chatbot with stateless data ingestion capabilities through its
 
 ## Usage for GitHub Actions
 
+Easily add RepoChat to your project using GitHub Actions:
+
 ```yaml
 jobs:
     steps:
     - name: Deploy a convenient chatbot for your repo
       id: deploy_repochat
       uses: flavienbwk/repochat-action@v0
-      if: github.ref == 'refs/heads/main'
       with:
-        dirs_to_scan: "./example,README.md"  # comma-separated glob dirs to analyze from this repo (required)
-        openai_api_key: ${{ secrets.OPENAI_API_KEY }}  # (required)
-        openai_model_type_inference: "gpt-4o-mini"  # (required)
-        openai_model_type_embedding : "text-embedding-3-small"  # (required)
-        cloud_provider: 'scaleway'  # (required)
+        # All parameters not explicitly marked as "optional" are required
+        dirs_to_scan: "./example,README.md"  # comma-separated glob dirs to analyze
+        interface_password: ${{ secrets.INTERFACE_PASSWORD }}  # optional
+        openai_api_key: ${{ secrets.OPENAI_API_KEY }}
+        openai_model_type_inference: "gpt-4o-mini"
+        openai_model_type_embedding : "text-embedding-3-small"
+        provider_name: 'scaleway'
         provider_key_id: ${{ secrets.PROVIDER_KEY_ID }}
         provider_key_secret: ${{ secrets.PROVIDER_KEY_SECRET }}
         provider_project_id: ${{ secrets.PROVIDER_PROJECT_ID }}
         provider_default_region: 'fr-par'
         provider_default_zone: 'fr-par-2'
 
-    - name: Get container domain from precedent step
+    - name: Get RepoChat domain
       run: echo "DOMAIN=${{ steps.deploy_repochat.outputs.domain }}" >> $GITHUB_OUTPUT
       id: repochat_domain
 ```
@@ -48,12 +56,15 @@ jobs:
 - **[Scaleway](https://www.scaleway.com/en/)**
   - Refer to [Scaleway's documentation to generate API keys](https://www.scaleway.com/en/docs/identity-and-access-management/iam/how-to/create-api-keys/).
   - Additional required parameters:
-    - `cloud_provider`: 'scaleway'
-    - `provider_key_id`: ${{ secrets.PROVIDER_KEY_ID }}
-    - `provider_key_secret`: ${{ secrets.PROVIDER_KEY_SECRET }}
-    - `provider_project_id`: ${{ secrets.PROVIDER_PROJECT_ID }}
-    - `provider_default_region`: 'fr-par'  # example
-    - `provider_default_zone`: 'fr-par-2'  # example
+
+    ```txt
+    provider_name: 'scaleway'
+    provider_key_id: ${{ secrets.PROVIDER_KEY_ID }}
+    provider_key_secret: ${{ secrets.PROVIDER_KEY_SECRET }}
+    provider_project_id: ${{ secrets.PROVIDER_PROJECT_ID }}
+    provider_default_region: 'fr-par'  # example
+    provider_default_zone: 'fr-par-2'  # example
+    ```
 
 ## Other deployments
 
@@ -105,9 +116,28 @@ jobs:
 
 ## Development
 
-```bash
-make dev
-```
+<details>
+<summary>👉 Run RepoChat for development...</summary>
+
+1. Clone this repo
+
+    ```bash
+    [email protected]:flavienbwk/repochat-action.git
+    ```
+
+2. Copy and update env variables
+
+    ```bash
+    cp .env.example .env
+    ```
+
+3. Run the local stack
+
+    ```bash
+    make dev
+    ```
+
+</details>
 
 ## Release Action
 
@@ -130,8 +160,9 @@ make dev
 - [x] API data chat
 - [x] GitHub Actions release
 - [x] Secure ingestion endpoint (/api/ingest)
-- [ ] Secure RepoChat with optional password
+- [x] Secure RepoChat with optional password
+- [ ] Maintain state over S3
 
 ## Why not use Vercel ?
 
-Vercel is very limited when deploying everything but JS. First, ChromaDB (and any sqlite-based library) [is not supported in Vercel](https://vercel.community/t/is-vercel-incompatible-with-chromadb-sqlite/787). Then, this project uses a FastAPI Python API that requires more storage than [Vercel's 250MB bundle limit](https://vercel.com/docs/functions/runtimes#bundle-size-limits).
+Vercel is very limited when it comes to deploying everything but JS. First, ChromaDB (and any sqlite-based library) [is not supported in Vercel](https://vercel.community/t/is-vercel-incompatible-with-chromadb-sqlite/787). Then, this project uses a FastAPI Python API that requires more storage than [Vercel's 250MB bundle limit](https://vercel.com/docs/functions/runtimes#bundle-size-limits).

action.yml

@@ -5,6 +5,10 @@ inputs:
   dirs_to_scan:
     description: 'Comma-separated list of directories that you want to chat about'
     required: true
+  interface_password:
+    description: 'Password to access the interface'
+    required: false
+    default: ''
   openai_api_key:
     description: 'Your OpenAI API key'
     required: true
@@ -16,7 +20,7 @@ inputs:
     description: 'OpenAI model type for embedding'
     default: 'text-embedding-3-small'
     required: false
-  cloud_provider:
+  provider_name:
     description: 'Cloud provider'
     default: 'scaleway'
     required: false

action/index.js

@@ -83,10 +83,11 @@ async function ingestFiles(directoryPath, apiUrl, ingestSecret, excludeFiles = [
 
 try {
   const dirsToScan = core.getInput('dirs_to_scan');
+  const interfacePassword = core.getInput('interface_password');
   const openaiApiKey = core.getInput('openai_api_key');
   const openaiModelTypeInference = core.getInput('openai_model_type_inference');
   const openaiModelTypeEmbedding = core.getInput('openai_model_type_embedding');
-  const cloudProvider = core.getInput('cloud_provider');
+  const cloudProvider = core.getInput('provider_name');
   const providerKeyId = core.getInput('provider_key_id');
   const providerKeySecret = core.getInput('provider_key_secret');
   const providerProjectId = core.getInput('provider_project_id');
@@ -188,8 +189,12 @@ try {
     console.log('Namespace is ready');
 
 
-    const openaiApiKeySecret = { key: 'OPENAI_API_KEY', value: openaiApiKey }
-    const parIngestSecretSecret = { key: 'INGEST_SECRET', value: parIngestSecret }
+    let listOfSecrets  = [];
+    listOfSecrets.push({ key: 'OPENAI_API_KEY', value: openaiApiKey })
+    listOfSecrets.push({ key: 'INGEST_SECRET', value: parIngestSecret })
+    if (interfacePassword) {
+      listOfSecrets.push({ key: 'INTERFACE_PASSWORD', value: interfacePassword })
+    }
     const containerConfig = {
       name: containerName,
       namespaceId: namespace.id,
@@ -207,10 +212,7 @@ try {
         REPO_URL: `https://github.com/${process.env.GITHUB_REPOSITORY}`,
         MODE: 'api'
       },
-      secretEnvironmentVariables: [
-        openaiApiKeySecret,
-        parIngestSecretSecret
-      ]
+      secretEnvironmentVariables: listOfSecrets
     };
 
     try {

api.docker-compose.yml

@@ -3,13 +3,14 @@ services:
   repochat:
     build: .
     environment:
+      MODE: api
       REPO_NAME: ${REPO_NAME}
       REPO_URL: ${REPO_URL}
       OPENAI_API_KEY: ${OPENAI_API_KEY}
       INGEST_SECRET: ${INGEST_SECRET}
       MODEL_TYPE_INFERENCE: ${MODEL_TYPE_INFERENCE}
       MODEL_TYPE_EMBEDDING: ${MODEL_TYPE_EMBEDDING}
       CLEAR_DB_AT_RESTART: ${CLEAR_DB_AT_RESTART}
-      MODE: api
+      INTERFACE_PASSWORD: ${INTERFACE_PASSWORD}
     ports:
       - "3001:80"

api/config.py

@@ -12,6 +12,7 @@
 REPO_URL = os.getenv('REPO_URL', '').strip()
 REPO_PATH = os.getenv('REPO_PATH', '').strip()
 INGEST_SECRET = os.environ['INGEST_SECRET'].strip()
+INTERFACE_PASSWORD = os.getenv('INTERFACE_PASSWORD', '').strip()
 OPEN_AI_API_KEY = os.environ['OPENAI_API_KEY'].strip()
 MODEL_TYPE_INFERENCE = os.environ['MODEL_TYPE_INFERENCE'].strip()
 MODEL_TYPE_EMBEDDING = os.environ['MODEL_TYPE_EMBEDDING'].strip()