context id changes

.github/workflows/docker_images.yml

@@ -11,6 +11,8 @@ jobs:
   release_tagged_image:
     if: startsWith(github.ref, 'refs/tags/v')
     runs-on: ubuntu-latest
+    permissions:
+      contents: write
     steps:
       - name: Check out the code
         uses: actions/checkout@v2
@@ -39,6 +41,14 @@ jobs:
             ragapp/ragapp:${{ steps.tag.outputs.TAG }}
             ragapp/ragapp:latest
 
+      - name: Create GitHub release
+        uses: ncipollo/release-action@v1
+        with:
+          artifacts: "README.md"
+          name: Release ${{ steps.tag.outputs.TAG }}
+          bodyFile: "CHANGELOG.md"
+          token: ${{ secrets.GITHUB_TOKEN }}
+
   release_dev_image:
     if: github.ref == 'refs/heads/main'
     runs-on: ubuntu-latest
@@ -60,7 +70,7 @@ jobs:
           password: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Build and push Docker image
-        uses: docker/build-push-action@v5
+        uses: docker/build-push-action@v6
         with:
           context: .
           file: ./Dockerfile

.github/workflows/lint_on_push_or_pull.yml

@@ -16,24 +16,26 @@ jobs:
     runs-on: ubuntu-latest
     defaults:
       run:
-        working-directory: 'admin'
+        working-directory: "admin"
     steps:
       - uses: actions/checkout@v4
 
+      - uses: pnpm/action-setup@v3
+
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
-          node-version: "18"
+          cache: "pnpm"
 
       - name: Install dependencies
-        run: npm install
+        run: pnpm install
 
       - name: Run lint
-        run: npm run lint
+        run: pnpm run lint
 
       - name: Run Prettier
-        run: npm run format
-  
+        run: pnpm run format
+
   linting-python:
     runs-on: ubuntu-latest
     strategy:

.github/workflows/release_pr.yml

@@ -44,14 +44,16 @@ jobs:
         with:
           commit: Release ${{ steps.get-changeset-status.outputs.new-version }}
           title: Release ${{ steps.get-changeset-status.outputs.new-version }}
-          publish: true
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
-      - name: Tag and Push Release
-        if: steps.changesets.outputs.published == 'true'
-        run: |
-          git tag v${{ steps.get-changeset-status.outputs.new-version }}
-          git push origin v${{ steps.get-changeset-status.outputs.new-version }}
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      # - name: Tag and Push Release
+      #   if: steps.changesets.outputs.hasChangesets == 'false'
+      #   run: |
+      #     # version is already in package.json - just tag and push
+      #     new_version=$(jq -r '.version' < package.json)
+      #     git tag v${new_version}
+      #     git push origin v${new_version}
+      #     # TODO: trigger job 'release_tagged_image' (is not triggered by git push)
+      #   env:
+      #     GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -5,9 +5,12 @@ storage/
 
 **/.env
 
+**/.mypy_cache/
+
 data/
 node_modules/
 create_llama/
 ollama/
+tool-output/
 
 !config/*

CHANGELOG.md

@@ -1,5 +1,72 @@
 # ragbox
 
+## 0.0.16
+
+### Patch Changes
+
+- ade3163: Add Mistral AI provider
+
+## 0.0.15
+
+### Patch Changes
+
+- b7b1f7f: Bump llama-index version to 0.10.53
+
+## 0.0.14
+
+### Patch Changes
+
+- 6c7f7aa: Add support for LlamaCloud
+
+## 0.0.13
+
+### Patch Changes
+
+- c7cbb6e: Bump create-llama version to 0.1.17
+- c7cbb6e: Add support for T-Systems provider
+
+## 0.0.12
+
+### Patch Changes
+
+- d901b4e: Add embedding model and base api config for OpenAI provider
+- debfe4e: Add loading state to forms
+- 0342480: Add custom tool prompt to system prompt
+
+## 0.0.11
+
+### Patch Changes
+
+- 1ceec37: Bump create-llama version to 0.1.13
+- 1ceec37: Add image generator tool
+
+## 0.0.10
+
+### Patch Changes
+
+- 4cfe656: Add OpenAPI tool config
+- 969374e: Add e2b code interpreter
+- 4cfe656: Bump create-llama version to 0.1.11
+- 4f178a6: Auto-submit forms on focus lost, clarified start up and improved UX for uploading files.
+
+## 0.0.9
+
+### Patch Changes
+
+- fef1d1a: Fix not showing file viewer
+- 67c3ac5: Fix the issue with losing chat config when switching providers
+- 9dd1704: Add a new config for Llama parse
+- 8803c69: Fix system prompt not working and improved Azure OpenAI validation
+- f7dc582: Bump create-llama version to 0.1.10
+- fef1d1a: Add timeout config for Ollama requests
+- e559534: Add config for conversation starter questions
+
+## 0.0.8
+
+### Patch Changes
+
+- 50537ff: Add support for Azure OpenAI provider
+
 ## 0.0.7
 
 ### Patch Changes

Dockerfile

@@ -1,6 +1,9 @@
 # ======= FRONT-END BUILD ==========
 FROM node:20-alpine as build
 
+# Install pnpm
+RUN npm install -g [email protected]
+
 # Install make
 RUN apk add --no-cache make
 
@@ -10,6 +13,7 @@ COPY Makefile .
 COPY admin ./admin
 COPY patch/frontend ./patch/frontend
 COPY patch/backend ./patch/backend
+COPY create_llama_local ./create_llama_local
 
 # Build static files for the Chat UI
 RUN make build-frontends
@@ -35,8 +39,8 @@ COPY poetry.lock pyproject.toml ./
 RUN poetry install --no-root --no-cache --only main
 
 # Copy static files from the build stage 
-COPY --from=build /app/create_llama/frontend/out /app/static
-COPY --from=build /app/admin/out /app/static/admin
+# COPY --from=build /app/create_llama/frontend/out /app/static
+# COPY --from=build /app/admin/out /app/static/admin
 COPY --from=build /app/create_llama/backend /app/create_llama/backend
 COPY . .
 

Makefile

@@ -1,47 +1,29 @@
 export PYTHONPATH := ${PYTHONPATH}:./create_llama/backend
-export CREATE_LLAMA_VERSION=0.1.7
+export CREATE_LLAMA_VERSION=0.1.18
 export NEXT_PUBLIC_API_URL=/api/chat
 
 create-llama-app:
-	@echo "\nCreating Llama App..."
-	rm -rf create_llama
-	npx -y create-llama@${CREATE_LLAMA_VERSION} \
-		--framework fastapi \
-		--template streaming \
-		--engine context \
-		--frontend \
-		--ui shadcn \
-		--observability none \
-		--open-ai-key none \
-		--tools none \
-		--post-install-action none \
-		--no-llama-parse \
-		--no-files \
-		--vector-db chroma \
-		-- create_llama
-	# We don't need the example data and default .env files
-	rm -rf create_llama/backend/data/*
-	rm -rf create_llama/backend/.env
-	rm -rf create_llama/frontend/.env
+	mkdir -p create_llama
+	cp -r ./create_llama_local/* create_llama/
 
 patch-chat: create-llama-app
 	cp -r ./patch/* ./create_llama/
 
 build-chat: patch-chat
 	@echo "\nBuilding Chat UI..."
-	cd ./create_llama/frontend && npm install && npm run build
+	cd ./create_llama/frontend && pnpm install && pnpm run build
 	@echo "\nCopying Chat UI to static folder..."
 	mkdir -p ./static && cp -r ./create_llama/frontend/out/* ./static/
 	@echo "\nDone!"
 
 build-admin:
 	@echo "\nBuilding Admin UI..."
-	cd ./admin && npm install && npm run build
+	cd ./admin && pnpm install && pnpm run build
 	@echo "\nCopying Admin UI to static folder..."
 	mkdir -p ./static/admin && cp -r ./admin/out/* ./static/admin/
 	@echo "\nDone!"
 
-build-frontends: build-chat build-admin
+build-frontends: patch-chat
 
 run:
 	poetry run python main.py
@@ -52,5 +34,5 @@ dev:
 	@export ENVIRONMENT=dev; \
 	trap 'kill 0' SIGINT; \
 	poetry run python main.py & \
-	npm run dev --prefix ./admin & \
+	pnpm --prefix ./admin run dev & \
 	wait

README.md

@@ -26,6 +26,8 @@ Then, access the Admin UI at http://localhost:8000/admin to configure your RAGap
 
 You can use hosted AI models from OpenAI or Gemini, and local models using [Ollama](https://ollama.com/).
 
+> _Note_: To avoid [running into any errors](https://github.com/ragapp/ragapp/issues/22), we recommend using the latest version of Docker and (if needed) Docker Compose.
+
 ## Endpoints
 
 The docker container exposes the following endpoints:
@@ -36,7 +38,17 @@ The docker container exposes the following endpoints:
 
 > _Note_: The Chat UI and API are only functional if the RAGapp is configured.
 
-RAGapp doesn't come with any authentication layer by design. Just protect the `/admin` path in your cloud environment to secure your RAGapp.
+## Security
+
+### Authentication
+
+RAGapp doesn't come with any authentication layer by design. You'll have to protect the `/admin` and `/api/management` paths in your cloud environment to secure your RAGapp.
+This step heavily depends on your cloud provider and the services you use.
+A common way to do so using Kubernetes is to use an [Ingress Controller](https://kubernetes.github.io/ingress-nginx/examples/auth/basic/).
+
+### Authorization
+
+Later versions of RAGapp will support to restrict access based on access tokens forwarded from an API Gateway or similar.
 
 ## Deployment
 
@@ -54,6 +66,8 @@ If you don't specify the `MODEL` variable, the default model used is `phi3`, whi
 
 > _Note_: The `setup` container in the `docker-compose.yml` file will download the selected model into the [`ollama`](./ollama/) folder - this will take a few minutes.
 
+#### Specify the Ollama host
+
 Using the `OLLAMA_BASE_URL` environment variables, you can specify which Ollama host to use.
 If you don't specify the `OLLAMA_BASE_URL` variable, the default points to the Ollama instance started by Docker Compose (`http://ollama:11434`).
 
@@ -63,7 +77,13 @@ If you're running a local Ollama instance, you can choose to connect it to RAGap
 MODEL=llama3 OLLAMA_BASE_URL=http://host.docker.internal:11434 docker-compose up
 ```
 
-This is necessary if you're running RAGapp on macOS, as Docker for Mac does not support GPU acceleration.
+> _Note_: `host.docker.internal` is not available on Linux machines, you'll have to use `172.17.0.1` instead. For details see [Issue #78](https://github.com/ragapp/ragapp/issues/78).
+
+#### GPU acceleration
+
+Using a local Ollama instance is necessary if you're running RAGapp on macOS, as Docker for Mac does not support GPU acceleration.
+
+To enable Docker access to NVIDIA GPUs on Linux, [install the NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html).
 
 ### Kubernetes
 
@@ -82,3 +102,7 @@ make dev
 ## Contact
 
 Questions, feature requests or found a bug? [Open an issue](https://github.com/ragapp/ragapp/issues/new/choose) or reach out to [marcusschiesser](https://github.com/marcusschiesser).
+
+## Star History
+
+[![Star History Chart](https://api.star-history.com/svg?repos=ragapp/ragapp&type=Date)](https://star-history.com/#ragapp/ragapp&Date)

admin/.prettierignore

@@ -0,0 +1,3 @@
+pnpm-lock.yaml
+lib/
+dist/

admin/client/chatConfig.ts

@@ -0,0 +1,34 @@
+import { z } from "zod";
+import { getBaseURL } from "./utils";
+
+// Chat config scheme
+export const ChatConfigSchema = z.object({
+  custom_prompt: z.string().optional(),
+  conversation_starters: z.array(z.string()),
+});
+
+export type ChatConfigFormType = z.TypeOf<typeof ChatConfigSchema>;
+
+export async function getChatConfig(): Promise<ChatConfigFormType> {
+  const res = await fetch(`${getBaseURL()}/api/management/config/chat`);
+  if (!res.ok) {
+    throw new Error("Failed to fetch chat config");
+  }
+  return res.json();
+}
+
+export async function updateChatConfig(
+  data: ChatConfigFormType,
+): Promise<ChatConfigFormType> {
+  const res = await fetch(`${getBaseURL()}/api/management/config/chat`, {
+    method: "POST",
+    headers: {
+      "Content-Type": "application/json",
+    },
+    body: JSON.stringify(data),
+  });
+  if (!res.ok) {
+    throw new Error("Failed to update chat config");
+  }
+  return res.json();
+}