diff --git a/.dockerignore b/.dockerignore new file mode 100644 index 0000000000000000000000000000000000000000..d600b6c76dd93f7b2472160d42b2797cae50c8e5 --- /dev/null +++ b/.dockerignore @@ -0,0 +1,25 @@ +# Logs +logs +*.log +npm-debug.log* +yarn-debug.log* +yarn-error.log* +pnpm-debug.log* +lerna-debug.log* + +node_modules +dist +dist-ssr +*.local + +# Editor directories and files +.vscode/* +!.vscode/extensions.json +.idea +.DS_Store +*.suo +*.ntvs* +*.njsproj +*.sln +*.sw? + diff --git a/.editorconfig b/.editorconfig new file mode 100644 index 0000000000000000000000000000000000000000..a78447ebf932f1bb3a5b124b472bea8b3a86f80f --- /dev/null +++ b/.editorconfig @@ -0,0 +1,7 @@ +[*] +charset = utf-8 +insert_final_newline = true +end_of_line = lf +indent_style = space +indent_size = 2 +max_line_length = 80 \ No newline at end of file diff --git a/.env.example b/.env.example new file mode 100644 index 0000000000000000000000000000000000000000..cfefe7af70d5c96e5a66856ebc2424ed7515ad6c --- /dev/null +++ b/.env.example @@ -0,0 +1,33 @@ +# A comma-separated list of access keys. Example: `ACCESS_KEYS="ABC123,JUD71F,HUWE3"`. Leave blank for unrestricted access. +ACCESS_KEYS="" + +# The timeout in hours for access key validation. Set to 0 to require validation on every page load. +ACCESS_KEY_TIMEOUT_HOURS="24" + +# The default model ID for WebLLM with F16 shaders. +WEBLLM_DEFAULT_F16_MODEL_ID="Qwen2.5-0.5B-Instruct-q4f16_1-MLC" + +# The default model ID for WebLLM with F32 shaders. +WEBLLM_DEFAULT_F32_MODEL_ID="Qwen2.5-0.5B-Instruct-q4f32_1-MLC" + +# The default model ID for Wllama. +WLLAMA_DEFAULT_MODEL_ID="qwen-2.5-0.5b" + +# The base URL for the internal OpenAI compatible API. Example: `INTERNAL_OPENAI_COMPATIBLE_API_BASE_URL="https://api.openai.com/v1"`. Leave blank to disable internal OpenAI compatible API. +INTERNAL_OPENAI_COMPATIBLE_API_BASE_URL="" + +# The access key for the internal OpenAI compatible API. +INTERNAL_OPENAI_COMPATIBLE_API_KEY="" + +# The model for the internal OpenAI compatible API. +INTERNAL_OPENAI_COMPATIBLE_API_MODEL="" + +# The name of the internal OpenAI compatible API, displayed in the UI. +INTERNAL_OPENAI_COMPATIBLE_API_NAME="Internal API" + +# The type of inference to use by default. The possible values are: +# "browser" -> In the browser (Private) +# "openai" -> Remote Server (API) +# "horde" -> AI Horde (Pre-configured) +# "internal" -> $INTERNAL_OPENAI_COMPATIBLE_API_NAME +DEFAULT_INFERENCE_TYPE="browser" diff --git a/.github/workflows/deploy.yml b/.github/workflows/deploy.yml new file mode 100644 index 0000000000000000000000000000000000000000..945fa830dd3258e5313257f6ed90ca5916bd5eea --- /dev/null +++ b/.github/workflows/deploy.yml @@ -0,0 +1,54 @@ +name: Deploy + +on: + workflow_dispatch: + +jobs: + build-and-push-image: + name: Publish Docker image to GitHub Packages + runs-on: ubuntu-latest + env: + REGISTRY: ghcr.io + IMAGE_NAME: ${{ github.repository }} + permissions: + contents: read + packages: write + steps: + - name: Checkout repository + uses: actions/checkout@v4 + - name: Log in to the Container registry + uses: docker/login-action@v3 + with: + registry: ${{ env.REGISTRY }} + username: ${{ github.actor }} + password: ${{ secrets.GITHUB_TOKEN }} + - name: Extract metadata (tags, labels) for Docker + id: meta + uses: docker/metadata-action@v5 + with: + images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }} + - name: Set up Docker Buildx + uses: docker/setup-buildx-action@v3 + - name: Build and push Docker image + uses: docker/build-push-action@v6 + with: + context: . + push: true + tags: ${{ steps.meta.outputs.tags }} + labels: ${{ steps.meta.outputs.labels }} + platforms: linux/amd64,linux/arm64 + + sync-to-hf: + name: Sync to HuggingFace Spaces + runs-on: ubuntu-latest + steps: + - uses: actions/checkout@v4 + with: + lfs: true + - uses: JacobLinCool/huggingface-sync@v1 + with: + github: ${{ secrets.GITHUB_TOKEN }} + user: ${{ vars.HF_SPACE_OWNER }} + space: ${{ vars.HF_SPACE_NAME }} + token: ${{ secrets.HF_TOKEN }} + configuration: "hf-space-config.yml" diff --git a/.github/workflows/llama-cpp.yml b/.github/workflows/llama-cpp.yml new file mode 100644 index 0000000000000000000000000000000000000000..146aad384497a072d3415ad6a1b23a5d1ce2e4cd --- /dev/null +++ b/.github/workflows/llama-cpp.yml @@ -0,0 +1,175 @@ +name: Review Pull Request with llama.cpp + +on: + pull_request: + types: [opened, synchronize, reopened] + branches: ["main"] + +concurrency: + group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }} + cancel-in-progress: true + +jobs: + llama-cpp: + if: ${{ !contains(github.event.pull_request.labels.*.name, 'skip-ai-review') }} + continue-on-error: true + runs-on: ubuntu-latest + name: llama.cpp + permissions: + pull-requests: write + contents: read + timeout-minutes: 120 + env: + HF_MODEL_NAME: Qwen2.5.1-Coder-7B-Instruct-GGUF + steps: + - name: Checkout Repository + uses: actions/checkout@v4 + + - name: Create temporary directory + run: mkdir -p /tmp/llama_review + + - name: Process PR description + id: process_pr + run: | + PR_BODY_ESCAPED=$(cat << 'EOF' + ${{ github.event.pull_request.body }} + EOF + ) + PROCESSED_BODY=$(echo "$PR_BODY_ESCAPED" | sed -E 's/\[(.*?)\]\(.*?\)/\1/g') + echo "$PROCESSED_BODY" > /tmp/llama_review/processed_body.txt + + - name: Fetch branches and output the diff in this step + run: | + git fetch origin main:main + git fetch origin pull/${{ github.event.pull_request.number }}/head:pr-branch + git diff main..pr-branch > /tmp/llama_review/diff.txt + + - name: Write prompt to file + id: build_prompt + run: | + PR_TITLE=$(echo "${{ github.event.pull_request.title }}" | sed 's/[()]/\\&/g') + DIFF_CONTENT=$(cat /tmp/llama_review/diff.txt) + PROCESSED_BODY=$(cat /tmp/llama_review/processed_body.txt) + echo "<|im_start|>system + You are an experienced developer reviewing a Pull Request. You focus only on what matters and provide concise, actionable feedback. + + Review Context: + Repository Name: \"${{ github.event.repository.name }}\" + Repository Description: \"${{ github.event.repository.description }}\" + Branch: \"${{ github.event.pull_request.head.ref }}\" + PR Title: \"$PR_TITLE\" + + Guidelines: + 1. Only comment on issues that: + - Could cause bugs or security issues + - Significantly impact performance + - Make the code harder to maintain + - Violate critical best practices + + 2. For each issue: + - Point to the specific line/file + - Explain why it's a problem + - Suggest a concrete fix + + 3. Praise exceptional solutions briefly, only if truly innovative + + 4. Skip commenting on: + - Minor style issues + - Obvious changes + - Working code that could be marginally improved + - Things that are just personal preference + + Remember: + Less is more. If the code is good and working, just say so, with a short message.<|im_end|> + <|im_start|>user + This is the description of the pull request: + \`\`\`markdown + $PROCESSED_BODY + \`\`\` + + And here is the diff of the changes, for you to review: + \`\`\`diff + $DIFF_CONTENT + \`\`\` + <|im_end|> + <|im_start|>assistant + ### Overall Summary + " > /tmp/llama_review/prompt.txt + + - name: Show Prompt + run: cat /tmp/llama_review/prompt.txt + + - name: Set up Homebrew + uses: Homebrew/actions/setup-homebrew@master + + - name: Install and cache Homebrew tools + uses: tecolicom/actions-use-homebrew-tools@v1 + with: + tools: llama.cpp + + - name: Cache the LLM + id: cache_llama_cpp + uses: actions/cache@v4 + with: + path: ~/.cache/llama.cpp/ + key: llama-cpp-${{ env.HF_MODEL_NAME }} + + - name: Download and cache the LLM + if: steps.cache_llama_cpp.outputs.cache-hit != 'true' + run: | + mkdir -p ~/.cache/llama.cpp/ + curl -L -o ~/.cache/llama.cpp/model.gguf https://huggingface.co/bartowski/${{ env.HF_MODEL_NAME }}/resolve/main/Qwen2.5.1-Coder-7B-Instruct-IQ4_XS.gguf + + - name: Run llama.cpp + run: | + llama-server \ + --model ~/.cache/llama.cpp/model.gguf \ + --ctx-size 32768 \ + --threads -1 \ + --predict -1 \ + --temp 0.5 \ + --top-p 0.9 \ + --min-p 0.1 \ + --top-k 0 \ + --cache-type-k q8_0 \ + --cache-type-v q8_0 \ + --flash-attn \ + --port 11434 & + + - name: cURL llama-server to get the completion and timings + run: | + DATA=$(jq -n --arg prompt "$(cat /tmp/llama_review/prompt.txt)" '{"prompt": $prompt}') + echo -e '### Review\n\n' > /tmp/llama_review/response.txt + # Save the full response to a temporary file + curl \ + --silent \ + --request POST \ + --url http://localhost:11434/completion \ + --header "Content-Type: application/json" \ + --data "$DATA" > /tmp/llama_review/full_response.json + + # Extract and append content to response.txt + jq -r '.content' /tmp/llama_review/full_response.json >> /tmp/llama_review/response.txt + + # Pretty print the timings information + echo "=== Performance Metrics ===" + jq -r '.timings | to_entries | .[] | "\(.key): \(.value)"' /tmp/llama_review/full_response.json + + - name: Show Response + run: cat /tmp/llama_review/response.txt + + - name: Find Comment + uses: peter-evans/find-comment@v3 + id: find_comment + with: + issue-number: ${{ github.event.pull_request.number }} + comment-author: "github-actions[bot]" + body-includes: "### Review" + + - name: Post or Update PR Review + uses: peter-evans/create-or-update-comment@v4 + with: + comment-id: ${{ steps.find_comment.outputs.comment-id }} + issue-number: ${{ github.event.pull_request.number }} + body-path: /tmp/llama_review/response.txt + edit-mode: replace diff --git a/.github/workflows/on-pull-request-to-main.yml b/.github/workflows/on-pull-request-to-main.yml new file mode 100644 index 0000000000000000000000000000000000000000..6eae98e615c1c1f2c899a9a5f1d785dd3883ff62 --- /dev/null +++ b/.github/workflows/on-pull-request-to-main.yml @@ -0,0 +1,9 @@ +name: On Pull Request To Main +on: + pull_request: + types: [opened, synchronize, reopened] + branches: ["main"] +jobs: + test-lint-ping: + if: ${{ !contains(github.event.pull_request.labels.*.name, 'skip-test-lint-ping') }} + uses: ./.github/workflows/reusable-test-lint-ping.yml diff --git a/.github/workflows/on-push-to-main.yml b/.github/workflows/on-push-to-main.yml new file mode 100644 index 0000000000000000000000000000000000000000..8ce693215c4351bab8b54ccac302345e1202ba03 --- /dev/null +++ b/.github/workflows/on-push-to-main.yml @@ -0,0 +1,7 @@ +name: On Push To Main +on: + push: + branches: ["main"] +jobs: + test-lint-ping: + uses: ./.github/workflows/reusable-test-lint-ping.yml diff --git a/.github/workflows/reusable-test-lint-ping.yml b/.github/workflows/reusable-test-lint-ping.yml new file mode 100644 index 0000000000000000000000000000000000000000..63c8e7c09f4a8598702dd4a30cd4a920d770043d --- /dev/null +++ b/.github/workflows/reusable-test-lint-ping.yml @@ -0,0 +1,25 @@ +on: + workflow_call: +jobs: + check-code-quality: + name: Check Code Quality + runs-on: ubuntu-latest + steps: + - uses: actions/checkout@v4 + - uses: actions/setup-node@v4 + with: + node-version: 20 + cache: "npm" + - run: npm ci --ignore-scripts + - run: npm test + - run: npm run lint + check-docker-container: + needs: [check-code-quality] + name: Check Docker Container + runs-on: ubuntu-latest + steps: + - uses: actions/checkout@v4 + - run: docker compose -f docker-compose.production.yml up -d + - name: Check if main page is available + run: until curl -s -o /dev/null -w "%{http_code}" localhost:7860 | grep 200; do sleep 1; done + - run: docker compose -f docker-compose.production.yml down diff --git a/.github/workflows/update-searxng-docker-image.yml b/.github/workflows/update-searxng-docker-image.yml new file mode 100644 index 0000000000000000000000000000000000000000..50261a76e8453bc473fa6e487d81a45cebe7cd1a --- /dev/null +++ b/.github/workflows/update-searxng-docker-image.yml @@ -0,0 +1,44 @@ +name: Update SearXNG Docker Image + +on: + schedule: + - cron: "0 14 * * *" + workflow_dispatch: + +permissions: + contents: write + +jobs: + update-searxng-image: + runs-on: ubuntu-latest + steps: + - name: Checkout code + uses: actions/checkout@v4 + with: + token: ${{ secrets.GITHUB_TOKEN }} + + - name: Get latest SearXNG image tag + id: get_latest_tag + run: | + LATEST_TAG=$(curl -s "https://hub.docker.com/v2/repositories/searxng/searxng/tags/?page_size=3&ordering=last_updated" | jq -r '.results[] | select(.name != "latest-build-cache" and .name != "latest") | .name' | head -n 1) + echo "LATEST_TAG=${LATEST_TAG}" >> $GITHUB_OUTPUT + + - name: Update Dockerfile + run: | + sed -i 's|FROM searxng/searxng:.*|FROM searxng/searxng:${{ steps.get_latest_tag.outputs.LATEST_TAG }}|' Dockerfile + + - name: Check for changes + id: git_status + run: | + git diff --exit-code || echo "changes=true" >> $GITHUB_OUTPUT + + - name: Commit and push if changed + if: steps.git_status.outputs.changes == 'true' + run: | + git config --local user.email "github-actions[bot]@users.noreply.github.com" + git config --local user.name "github-actions[bot]" + git add Dockerfile + git commit -m "Update SearXNG Docker image to tag ${{ steps.get_latest_tag.outputs.LATEST_TAG }}" + git push + env: + GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000000000000000000000000000000000000..f1b26f1ea73cad18af0078381a02bbc532714a0a --- /dev/null +++ b/.gitignore @@ -0,0 +1,7 @@ +node_modules +.DS_Store +/client/dist +/server/models +.vscode +/vite-build-stats.html +.env diff --git a/.npmrc b/.npmrc new file mode 100644 index 0000000000000000000000000000000000000000..80bcbed90c4f2b3d895d5086dc775e1bd8b32b43 --- /dev/null +++ b/.npmrc @@ -0,0 +1 @@ +legacy-peer-deps = true diff --git a/Dockerfile b/Dockerfile new file mode 100644 index 0000000000000000000000000000000000000000..e9e36b3c40344a1a86cad4739e1f9da63d394f6e --- /dev/null +++ b/Dockerfile @@ -0,0 +1,82 @@ +# Use the SearXNG image as the base +FROM searxng/searxng:2024.12.16-65c970bdf + +# Set the default port to 7860 if not provided +ENV PORT=7860 + +# Expose the port specified by the PORT environment variable +EXPOSE $PORT + +# Install necessary packages using Alpine's package manager +RUN apk add --update \ + nodejs \ + npm \ + git \ + build-base \ + cmake \ + ccache + +# Set the SearXNG settings folder path +ARG SEARXNG_SETTINGS_FOLDER=/etc/searxng + +# Modify SearXNG configuration: +# 1. Change output format from HTML to JSON +# 2. Remove user switching in the entrypoint script +# 3. Create and set permissions for the settings folder +RUN sed -i 's/- html/- json/' /usr/local/searxng/searx/settings.yml \ + && sed -i 's/su-exec searxng:searxng //' /usr/local/searxng/dockerfiles/docker-entrypoint.sh \ + && mkdir -p ${SEARXNG_SETTINGS_FOLDER} \ + && chmod 777 ${SEARXNG_SETTINGS_FOLDER} + +# Set up user and directory structure +ARG USERNAME=user +ARG HOME_DIR=/home/${USERNAME} +ARG APP_DIR=${HOME_DIR}/app + +# Create a non-root user and set up the application directory +RUN adduser -D -u 1000 ${USERNAME} \ + && mkdir -p ${APP_DIR} \ + && chown -R ${USERNAME}:${USERNAME} ${HOME_DIR} + +# Switch to the non-root user +USER ${USERNAME} + +# Set the working directory to the application directory +WORKDIR ${APP_DIR} + +# Define environment variables that can be passed to the container during build. +# This approach allows for dynamic configuration without relying on a `.env` file, +# which might not be suitable for all deployment scenarios. +ARG ACCESS_KEYS +ARG ACCESS_KEY_TIMEOUT_HOURS +ARG WEBLLM_DEFAULT_F16_MODEL_ID +ARG WEBLLM_DEFAULT_F32_MODEL_ID +ARG WLLAMA_DEFAULT_MODEL_ID +ARG INTERNAL_OPENAI_COMPATIBLE_API_BASE_URL +ARG INTERNAL_OPENAI_COMPATIBLE_API_KEY +ARG INTERNAL_OPENAI_COMPATIBLE_API_MODEL +ARG INTERNAL_OPENAI_COMPATIBLE_API_NAME +ARG DEFAULT_INFERENCE_TYPE + +# Copy package.json, package-lock.json, and .npmrc files +COPY --chown=${USERNAME}:${USERNAME} ./package.json ./package.json +COPY --chown=${USERNAME}:${USERNAME} ./package-lock.json ./package-lock.json +COPY --chown=${USERNAME}:${USERNAME} ./.npmrc ./.npmrc + +# Install Node.js dependencies +RUN npm ci + +# Copy the rest of the application files +COPY --chown=${USERNAME}:${USERNAME} . . + +# Configure Git to treat the app directory as safe +RUN git config --global --add safe.directory ${APP_DIR} + +# Build the application +RUN npm run build + +# Set the entrypoint to use a shell +ENTRYPOINT [ "/bin/sh", "-c" ] + +# Run SearXNG in the background and start the Node.js application using PM2 +CMD [ "(/usr/local/searxng/dockerfiles/docker-entrypoint.sh -f > /dev/null 2>&1) & (npx pm2 start ecosystem.config.cjs && npx pm2 logs production-server)" ] diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..be10c3348b43bb632442a3e1ed7bb0ee94ac2912 --- /dev/null +++ b/README.md @@ -0,0 +1,139 @@ +--- +title: MiniSearch +emoji: 👌🔍 +colorFrom: yellow +colorTo: yellow +sdk: docker +short_description: Minimalist web-searching app with browser-based AI assistant +pinned: true +custom_headers: + cross-origin-embedder-policy: require-corp + cross-origin-opener-policy: same-origin + cross-origin-resource-policy: cross-origin +--- + +# MiniSearch + +A minimalist web-searching app with an AI assistant that runs directly from your browser. + +Live demo: https://felladrin-minisearch.hf.space + +## Screenshot + +![MiniSearch Screenshot](https://github.com/user-attachments/assets/f8d72a8e-a725-42e9-9358-e6ebade2acb2) + +## Features + +- **Privacy-focused**: [No tracking, no ads, no data collection](https://docs.searxng.org/own-instance.html#how-does-searxng-protect-privacy) +- **Easy to use**: Minimalist yet intuitive interface for all users +- **Cross-platform**: Models run inside the browser, both on desktop and mobile +- **Integrated**: Search from the browser address bar by setting it as the default search engine +- **Efficient**: Models are loaded and cached only when needed +- **Customizable**: Tweakable settings for search results and text generation +- **Open-source**: [The code is available for inspection and contribution at GitHub](https://github.com/felladrin/MiniSearch) + +## Prerequisites + +- [Docker](https://docs.docker.com/get-docker/) + +## Getting started + +Here are the easiest ways to get started with MiniSearch. Pick the one that suits you best. + +**Option 1** - Use [MiniSearch's Docker Image](https://github.com/felladrin/MiniSearch/pkgs/container/minisearch) by running in your terminal: + +```bash +docker run -p 7860:7860 ghcr.io/felladrin/minisearch:main +``` + +**Option 2** - Add MiniSearch's Docker Image to your existing Docker Compose file: + +```yaml +services: + minisearch: + image: ghcr.io/felladrin/minisearch:main + ports: + - "7860:7860" +``` + +**Option 3** - Build from source by [downloading the repository files](https://github.com/felladrin/MiniSearch/archive/refs/heads/main.zip) and running: + +```bash +docker compose -f docker-compose.production.yml up --build +``` + +Once the container is running, open http://localhost:7860 in your browser and start searching! + +## Frequently asked questions + +
+ How do I search via the browser's address bar? +

+ You can set MiniSearch as your browser's address-bar search engine using the pattern http://localhost:7860/?q=%s, in which your search term replaces %s. +

+
+ +
+ How do I search via Raycast? +

+ You can add this Quicklink to Raycast, so typying your query will open MiniSearch with the search results. You can also edit it to point to your own domain. +

+ image +
+ +
+ Can I use custom models via OpenAI-Compatible API? +

+ Yes! For this, open the Menu and change the "AI Processing Location" to Remote server (API). Then configure the Base URL, and optionally set an API Key and a Model to use. +

+
+ +
+ How do I restrict the access to my MiniSearch instance via password? +

+ Create a .env file and set a value for ACCESS_KEYS. Then reset the MiniSearch docker container. +

+

+ For example, if you to set the password to PepperoniPizza, then this is what you should add to your .env:
+ ACCESS_KEYS="PepperoniPizza" +

+

+ You can find more examples in the .env.example file. +

+
+ +
+ I want to serve MiniSearch to other users, allowing them to use my own OpenAI-Compatible API key, but without revealing it to them. Is it possible? +

Yes! In MiniSearch, we call this text-generation feature "Internal OpenAI-Compatible API". To use this it:

+
    +
  1. Set up your OpenAI-Compatible API endpoint by configuring the following environment variables in your .env file: +
      +
    • INTERNAL_OPENAI_COMPATIBLE_API_BASE_URL: The base URL for your API
      • +
    • INTERNAL_OPENAI_COMPATIBLE_API_KEY: Your API access key
      • +
    • INTERNAL_OPENAI_COMPATIBLE_API_MODEL: The model to use
      • +
    • INTERNAL_OPENAI_COMPATIBLE_API_NAME: The name to display in the UI
      • +
    +
    2. +
  2. Restart MiniSearch server.
    3. +
  3. In the MiniSearch menu, select the new option (named as per your INTERNAL_OPENAI_COMPATIBLE_API_NAME setting) from the "AI Processing Location" dropdown.
    4. +
+
+ +
+ How can I contribute to the development of this tool? +

Fork this repository and clone it. Then, start the development server by running the following command:

+

docker compose up

+

Make your changes, push them to your fork, and open a pull request! All contributions are welcome!

+
+ +
+ Why is MiniSearch built upon SearXNG's Docker Image and using a single image instead of composing it from multiple services? +

There are a few reasons for this:

+ +
diff --git a/biome.json b/biome.json new file mode 100644 index 0000000000000000000000000000000000000000..adaa75db32e7a7e5bf6eb2ae2df5a99cdd4352bf --- /dev/null +++ b/biome.json @@ -0,0 +1,30 @@ +{ + "$schema": "https://biomejs.dev/schemas/1.9.4/schema.json", + "vcs": { + "enabled": false, + "clientKind": "git", + "useIgnoreFile": false + }, + "files": { + "ignoreUnknown": false, + "ignore": [] + }, + "formatter": { + "enabled": true, + "indentStyle": "space" + }, + "organizeImports": { + "enabled": true + }, + "linter": { + "enabled": true, + "rules": { + "recommended": true + } + }, + "javascript": { + "formatter": { + "quoteStyle": "double" + } + } +} diff --git a/client/components/AiResponse/AiModelDownloadAllowanceContent.tsx b/client/components/AiResponse/AiModelDownloadAllowanceContent.tsx new file mode 100644 index 0000000000000000000000000000000000000000..227cec2d8152fb4ddcb9a4e91e4c8e3034b0feba --- /dev/null +++ b/client/components/AiResponse/AiModelDownloadAllowanceContent.tsx @@ -0,0 +1,62 @@ +import { Alert, Button, Group, Text } from "@mantine/core"; +import { IconCheck, IconInfoCircle, IconX } from "@tabler/icons-react"; +import { usePubSub } from "create-pubsub/react"; +import { useState } from "react"; +import { addLogEntry } from "../../modules/logEntries"; +import { settingsPubSub } from "../../modules/pubSub"; + +export default function AiModelDownloadAllowanceContent() { + const [settings, setSettings] = usePubSub(settingsPubSub); + const [hasDeniedDownload, setDeniedDownload] = useState(false); + + const handleAccept = () => { + setSettings({ + ...settings, + allowAiModelDownload: true, + }); + addLogEntry("User allowed the AI model download"); + }; + + const handleDecline = () => { + setDeniedDownload(true); + addLogEntry("User denied the AI model download"); + }; + + return hasDeniedDownload ? null : ( + } + > + + To obtain AI responses, a language model needs to be downloaded to your + browser. Enabling this option lets the app store it and load it + instantly on subsequent uses. + + + Please note that the download size ranges from 100 MB to 4 GB, depending + on the model you select in the Menu, so it's best to avoid using mobile + data for this. + + + + + + + ); +} diff --git a/client/components/AiResponse/AiResponseContent.tsx b/client/components/AiResponse/AiResponseContent.tsx new file mode 100644 index 0000000000000000000000000000000000000000..2d49718702735a4d3ced77d63e6def9cfee22355 --- /dev/null +++ b/client/components/AiResponse/AiResponseContent.tsx @@ -0,0 +1,199 @@ +import { + ActionIcon, + Alert, + Badge, + Box, + Card, + Group, + ScrollArea, + Text, + Tooltip, +} from "@mantine/core"; +import { + IconArrowsMaximize, + IconArrowsMinimize, + IconHandStop, + IconInfoCircle, + IconRefresh, + IconVolume2, +} from "@tabler/icons-react"; +import type { PublishFunction } from "create-pubsub"; +import { usePubSub } from "create-pubsub/react"; +import { type ReactNode, Suspense, lazy, useMemo, useState } from "react"; +import { settingsPubSub } from "../../modules/pubSub"; +import { searchAndRespond } from "../../modules/textGeneration"; + +const FormattedMarkdown = lazy(() => import("./FormattedMarkdown")); +const CopyIconButton = lazy(() => import("./CopyIconButton")); + +export default function AiResponseContent({ + textGenerationState, + response, + setTextGenerationState, +}: { + textGenerationState: string; + response: string; + setTextGenerationState: PublishFunction< + | "failed" + | "awaitingSearchResults" + | "preparingToGenerate" + | "idle" + | "loadingModel" + | "generating" + | "interrupted" + | "completed" + >; +}) { + const [settings, setSettings] = usePubSub(settingsPubSub); + const [isSpeaking, setIsSpeaking] = useState(false); + + const ConditionalScrollArea = useMemo( + () => + ({ children }: { children: ReactNode }) => { + return settings.enableAiResponseScrolling ? ( + + {children} + + ) : ( + {children} + ); + }, + [settings.enableAiResponseScrolling], + ); + + function speakResponse(text: string) { + if (isSpeaking) { + self.speechSynthesis.cancel(); + setIsSpeaking(false); + return; + } + + const cleanText = text.replace(/[#*`_~\[\]]/g, ""); + const utterance = new SpeechSynthesisUtterance(cleanText); + + const voices = self.speechSynthesis.getVoices(); + + if (voices.length > 0 && settings.selectedVoiceId) { + const voice = voices.find( + (voice) => voice.voiceURI === settings.selectedVoiceId, + ); + + if (voice) { + utterance.voice = voice; + utterance.lang = voice.lang; + } + } + + utterance.onend = () => setIsSpeaking(false); + + setIsSpeaking(true); + self.speechSynthesis.speak(utterance); + } + + return ( + + + + + + {textGenerationState === "generating" + ? "Generating AI Response..." + : "AI Response"} + + {textGenerationState === "interrupted" && ( + + Interrupted + + )} + + + {textGenerationState === "generating" ? ( + + setTextGenerationState("interrupted")} + variant="subtle" + color="gray" + > + + + + ) : ( + + searchAndRespond()} + variant="subtle" + color="gray" + > + + + + )} + + speakResponse(response)} + variant="subtle" + color={isSpeaking ? "blue" : "gray"} + > + + + + {settings.enableAiResponseScrolling ? ( + + { + setSettings({ + ...settings, + enableAiResponseScrolling: false, + }); + }} + variant="subtle" + color="gray" + > + + + + ) : ( + + { + setSettings({ + ...settings, + enableAiResponseScrolling: true, + }); + }} + variant="subtle" + color="gray" + > + + + + )} + + + + + + + + + + {response} + + + {textGenerationState === "failed" && ( + } + > + Could not generate response. It's possible that your browser or your + system is out of memory. + + )} + + + ); +} diff --git a/client/components/AiResponse/AiResponseSection.tsx b/client/components/AiResponse/AiResponseSection.tsx new file mode 100644 index 0000000000000000000000000000000000000000..540b5c209d4631eea592037fda05290a106c05c8 --- /dev/null +++ b/client/components/AiResponse/AiResponseSection.tsx @@ -0,0 +1,105 @@ +import { usePubSub } from "create-pubsub/react"; +import { Suspense, lazy, useMemo } from "react"; +import { + modelLoadingProgressPubSub, + modelSizeInMegabytesPubSub, + queryPubSub, + responsePubSub, + settingsPubSub, + textGenerationStatePubSub, +} from "../../modules/pubSub"; + +const AiResponseContent = lazy(() => import("./AiResponseContent")); +const PreparingContent = lazy(() => import("./PreparingContent")); +const LoadingModelContent = lazy(() => import("./LoadingModelContent")); +const ChatInterface = lazy(() => import("./ChatInterface")); +const AiModelDownloadAllowanceContent = lazy( + () => import("./AiModelDownloadAllowanceContent"), +); + +export default function AiResponseSection() { + const [query] = usePubSub(queryPubSub); + const [response] = usePubSub(responsePubSub); + const [textGenerationState, setTextGenerationState] = usePubSub( + textGenerationStatePubSub, + ); + const [modelLoadingProgress] = usePubSub(modelLoadingProgressPubSub); + const [settings] = usePubSub(settingsPubSub); + const [modelSizeInMegabytes] = usePubSub(modelSizeInMegabytesPubSub); + + return useMemo(() => { + if (!settings.enableAiResponse || textGenerationState === "idle") { + return null; + } + + const generatingStates = [ + "generating", + "interrupted", + "completed", + "failed", + ]; + if (generatingStates.includes(textGenerationState)) { + return ( + <> + + + + {textGenerationState === "completed" && ( + + + + )} + + ); + } + + if (textGenerationState === "loadingModel") { + return ( + + + + ); + } + + if (textGenerationState === "preparingToGenerate") { + return ( + + + + ); + } + + if (textGenerationState === "awaitingSearchResults") { + return ( + + + + ); + } + + if (textGenerationState === "awaitingModelDownloadAllowance") { + return ( + + + + ); + } + + return null; + }, [ + settings.enableAiResponse, + textGenerationState, + response, + query, + modelLoadingProgress, + modelSizeInMegabytes, + setTextGenerationState, + ]); +} diff --git a/client/components/AiResponse/ChatInterface.tsx b/client/components/AiResponse/ChatInterface.tsx new file mode 100644 index 0000000000000000000000000000000000000000..e6ca0d021992141f1746fcbe70a37a6b88e88539 --- /dev/null +++ b/client/components/AiResponse/ChatInterface.tsx @@ -0,0 +1,186 @@ +import { + Button, + Card, + Group, + Paper, + Stack, + Text, + Textarea, +} from "@mantine/core"; +import { IconSend } from "@tabler/icons-react"; +import { usePubSub } from "create-pubsub/react"; +import type { ChatMessage } from "gpt-tokenizer/GptEncoding"; +import { + type KeyboardEvent, + Suspense, + lazy, + useEffect, + useRef, + useState, +} from "react"; +import { handleEnterKeyDown } from "../../modules/keyboard"; +import { addLogEntry } from "../../modules/logEntries"; +import { settingsPubSub } from "../../modules/pubSub"; +import { generateChatResponse } from "../../modules/textGeneration"; + +const FormattedMarkdown = lazy(() => import("./FormattedMarkdown")); +const CopyIconButton = lazy(() => import("./CopyIconButton")); + +export default function ChatInterface({ + initialQuery, + initialResponse, +}: { + initialQuery: string; + initialResponse: string; +}) { + const [messages, setMessages] = useState([]); + const [input, setInput] = useState(""); + const [isGenerating, setIsGenerating] = useState(false); + const [streamedResponse, setStreamedResponse] = useState(""); + const latestResponseRef = useRef(""); + const [settings] = usePubSub(settingsPubSub); + + useEffect(() => { + setMessages([ + { role: "user", content: initialQuery }, + { role: "assistant", content: initialResponse }, + ]); + }, [initialQuery, initialResponse]); + + const handleSend = async () => { + if (input.trim() === "" || isGenerating) return; + + const newMessages: ChatMessage[] = [ + ...messages, + { role: "user", content: input }, + ]; + setMessages(newMessages); + setInput(""); + setIsGenerating(true); + setStreamedResponse(""); + latestResponseRef.current = ""; + + try { + addLogEntry("User sent a follow-up question"); + await generateChatResponse(newMessages, (partialResponse) => { + setStreamedResponse(partialResponse); + latestResponseRef.current = partialResponse; + }); + setMessages((prevMessages) => [ + ...prevMessages, + { role: "assistant", content: latestResponseRef.current }, + ]); + addLogEntry("AI responded to follow-up question"); + } catch (error) { + addLogEntry(`Error generating chat response: ${error}`); + setMessages((prevMessages) => [ + ...prevMessages, + { + role: "assistant", + content: "Sorry, I encountered an error while generating a response.", + }, + ]); + } finally { + setIsGenerating(false); + setStreamedResponse(""); + } + }; + + const handleKeyDown = (event: KeyboardEvent) => { + handleEnterKeyDown(event, settings, handleSend); + }; + + const getChatContent = () => { + return messages + .slice(2) + .map( + (msg, index) => + `${index + 1}. ${msg.role?.toUpperCase()}\n\n${msg.content}`, + ) + .join("\n\n"); + }; + + return ( + + + + Follow-up questions + {messages.length > 2 && ( + + + + )} + + + + {messages.slice(2).length > 0 && ( + + {messages.slice(2).map((message, index) => ( + + + {message.content} + + + ))} + {isGenerating && streamedResponse.length > 0 && ( + + + {streamedResponse} + + + )} + + )} + +