complete omics KG build

.env.example

@@ -1,6 +1,57 @@
-SYNTHESIZER_MODEL=
+# Tokenizer
+TOKENIZER_MODEL=
+
+# LLM
+# Support different backends: http_api, openai_api, ollama_api, ollama, huggingface, tgi, sglang, tensorrt
+
+# http_api / openai_api
+SYNTHESIZER_BACKEND=openai_api
+SYNTHESIZER_MODEL=gpt-4o-mini
 SYNTHESIZER_BASE_URL=
 SYNTHESIZER_API_KEY=
-TRAINEE_MODEL=
+TRAINEE_BACKEND=openai_api
+TRAINEE_MODEL=gpt-4o-mini
 TRAINEE_BASE_URL=
 TRAINEE_API_KEY=
+
+# azure_openai_api
+# SYNTHESIZER_BACKEND=azure_openai_api
+# The following is the same as your "Deployment name" in Azure
+# SYNTHESIZER_MODEL=<your-deployment-name>
+# SYNTHESIZER_BASE_URL=https://<your-resource-name>.openai.azure.com/openai/deployments/<your-deployment-name>/chat/completions
+# SYNTHESIZER_API_KEY=
+# SYNTHESIZER_API_VERSION=<api-version>
+
+# # ollama_api
+# SYNTHESIZER_BACKEND=ollama_api
+# SYNTHESIZER_MODEL=gemma3
+# SYNTHESIZER_BASE_URL=http://localhost:11434
+#
+# Note: TRAINEE with ollama_api backend is not supported yet as ollama_api does not support logprobs.
+
+# # huggingface
+# SYNTHESIZER_BACKEND=huggingface
+# SYNTHESIZER_MODEL=Qwen/Qwen2.5-0.5B-Instruct
+#
+# TRAINEE_BACKEND=huggingface
+# TRAINEE_MODEL=Qwen/Qwen2.5-0.5B-Instruct
+
+# # sglang
+# SYNTHESIZER_BACKEND=sglang
+# SYNTHESIZER_MODEL=Qwen/Qwen2.5-0.5B-Instruct
+# SYNTHESIZER_TP_SIZE=1
+# SYNTHESIZER_NUM_GPUS=1
+
+# TRAINEE_BACKEND=sglang
+# TRAINEE_MODEL=Qwen/Qwen2.5-0.5B-Instruct
+# SYNTHESIZER_TP_SIZE=1
+# SYNTHESIZER_NUM_GPUS=1
+
+# # vllm
+# SYNTHESIZER_BACKEND=vllm
+# SYNTHESIZER_MODEL=Qwen/Qwen2.5-0.5B-Instruct
+# SYNTHESIZER_NUM_GPUS=1
+
+# TRAINEE_BACKEND=vllm
+# TRAINEE_MODEL=Qwen/Qwen2.5-0.5B-Instruct
+# TRAINEE_NUM_GPUS=1

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,24 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**To Reproduce**
+Steps to reproduce the behavior:
+1. Go to '...'
+2. Click on '....'
+3. Scroll down to '....'
+4. See error
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Additional context**
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,20 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Is your feature request related to a problem? Please describe.**
+A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+
+**Describe the solution you'd like**
+A clear and concise description of what you want to happen.
+
+**Describe alternatives you've considered**
+A clear and concise description of any alternative solutions or features you've considered.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.

.github/contributing.md

@@ -0,0 +1,34 @@
+## Contribution Guide
+Here are the steps to contribute to this project:
+
+1. Star this repository.
+2. Fork this repository.
+
+   Type the following command on Git bash console:
+   ```bash
+   git clone https://github.com/open-sciencelab/GraphGen.git
+   ```
+
+3. Create a new branch
+
+    Now before making changes to the files, go to your terminal under the repo you just cloned, and type the following:
+
+    ```bash
+    git checkout -b add-my-name
+    ```
+
+    By running the above command, you just created a new branch called add-my-name and checked it out, what this does is that it creates a new branch with the commit history of the master branch or the branch that you were on previously.
+
+4. Make your changes and push your code.
+
+   ```
+   git add .
+   git commit -m "xxx"
+   git push
+   ```
+
+   This will create a new commit with the changes you made.
+
+5. Now create a pull request and add the title.
+
+     Sit back and relax while your pull request is being reviewed and merged.

.github/sync-config.yml

@@ -0,0 +1,17 @@
+sync:
+  - source: graphgen/
+    dest: graphgen/
+  - source: resources/nltk_data/
+    dest: resources/nltk_data/
+  - source: resources/examples/
+    dest: resources/examples/
+  - source: resources/images/logo.png
+    dest: resources/images/logo.png
+  - source: webui/
+    dest: webui/
+  - source: webui/app.py
+    dest: app.py
+  - source: requirements.txt
+    dest: requirements.txt
+  - source: LICENSE
+    dest: LICENSE

.github/workflows/push-to-hf.yml

@@ -0,0 +1,51 @@
+name: Push demo branch to Hugging Face
+
+on:
+  workflow_call:
+    inputs:
+      ref:
+        required: false
+        default: demo
+        type: string
+    secrets:
+      HF_TOKEN:
+        required: true
+
+jobs:
+  push-hf:
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v4
+      with:
+        ref: ${{ inputs.ref }}
+        token: ${{ secrets.GITHUB_TOKEN }}
+
+    - name: Configure Git identity
+      run: |
+        git config --global user.email "actions@github.com"
+        git config --global user.name  "github-actions[bot]"
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install huggingface_hub
+
+    - name: Push to Hugging Face
+      env:
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HF_REPO_TYPE: spaces
+        HF_REPO_ID: chenzihong/GraphGen
+      run: |
+        git config --global credential.helper store
+        echo "https://user:${HF_TOKEN}@huggingface.co" > ~/.git-credentials
+
+        [[ -d hf-repo ]] && rm -rf hf-repo
+        git clone https://huggingface.co/${HF_REPO_TYPE}/${HF_REPO_ID} hf-repo
+
+        rsync -a --delete --exclude='.git' --exclude='hf-repo' --exclude='README.md' ./ hf-repo/
+
+        cd hf-repo
+        git add .
+        git diff-index --quiet HEAD || \
+          (git commit -m "Auto-sync from ${{ inputs.ref }} at $(date -u)" && git push)

.github/workflows/push-to-ms.yml

@@ -0,0 +1,50 @@
+name: Push demo branch to ModelScope
+
+on:
+  workflow_call:
+    inputs:
+      ref:
+        required: false
+        default: demo
+        type: string
+    secrets:
+      MS_TOKEN:
+        required: true
+
+jobs:
+  push-ms:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref }}
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Configure Git identity
+        run: |
+          git config --global user.email "actions@github.com"
+          git config --global user.name  "github-actions[bot]"
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          # ModelScope official SDK (optional, install only if you need to call the platform API)
+          pip install modelscope
+
+      - name: Push to ModelScope
+        env:
+          MS_TOKEN: ${{ secrets.MS_TOKEN }}
+          MS_REPO_TYPE: studios
+          MS_REPO_ID: chenzihong/GraphGen
+        run: |
+          [[ -d ms-repo ]] && rm -rf ms-repo
+          git clone https://oauth2:${MS_TOKEN}@www.modelscope.cn/${MS_REPO_TYPE}/${MS_REPO_ID}.git ms-repo
+
+          rsync -a --delete --exclude='.git' --exclude='ms-repo' --exclude='README.md' ./ ms-repo/
+
+          cd ms-repo
+          git add .
+          git diff-index --quiet HEAD || \
+            (git commit -m "Auto-sync from ${{ inputs.ref }} at $(date -u)" && \
+              git push "https://oauth2:${MS_TOKEN}@www.modelscope.cn/${MS_REPO_TYPE}/${MS_REPO_ID}.git")

.github/workflows/pylint.yml

@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.10", "3.11"]
+        python-version: ["3.10", "3.11", "3.12"]
 
     steps:
     - uses: actions/checkout@v4

.github/workflows/sync-demo.yml

@@ -0,0 +1,96 @@
+name: Sync Demo Branch
+
+on:
+  push:
+    branches:
+      - main
+  workflow_dispatch:
+
+jobs:
+  sync-demo:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout main branch
+      uses: actions/checkout@v4
+      with:
+        ref: main
+        token: ${{ secrets.GITHUB_TOKEN }}
+
+    - name: Create demo branch if it doesn't exist
+      run: |
+        if ! git ls-remote --heads origin demo | grep -q demo; then
+        echo "Creating demo branch..."
+        git checkout -b demo
+        git push origin demo
+        else
+        echo "Demo branch already exists"
+        fi
+
+    - name: Checkout demo branch
+      uses: actions/checkout@v4
+      with:
+        ref: demo
+        token: ${{ secrets.GITHUB_TOKEN }}
+        path: demo
+
+    - name: Clean demo directory
+      run: |
+        cd demo
+        find . -mindepth 1 -path './.git' -prune -o -exec rm -rf {} + 2>/dev/null || true
+
+    - name: Copy files using config
+      run: |
+        yq eval '.sync[] | .source + ":" + .dest' .github/sync-config.yml | while IFS=: read -r src dst; do
+          src=$(echo "$src" | xargs)
+          dst=$(echo "$dst" | xargs)
+
+          [ -z "$src" ] && continue
+
+          if [ -e "$src" ]; then
+            target_path="demo/$dst"
+
+            # 处理目录（以/结尾或本身是目录）
+            if [[ "$dst" == */ ]] || [ -d "$src" ]; then
+              mkdir -p "$target_path"
+              # 复制目录里的内容，而不是目录本身
+              cp -r "$src"/* "$target_path"
+              echo "Copied $src/* → $target_path"
+            else
+              mkdir -p "$(dirname "$target_path")"
+              cp "$src" "$target_path"
+              echo "Copied $src → $target_path"
+            fi
+          else
+            echo "Source not found: $src"
+          fi
+        done
+
+    - name: Commit and push changes
+      run: |
+        cd demo
+        git config --global user.email "actions@github.com"
+        git config --global user.name  "github-actions[bot]"
+
+        # 检查是否有变化
+        if [[ -n $(git status --porcelain) ]]; then
+          git add .
+          git commit -m "Auto-sync demo branch with main branch"
+          git push origin demo
+          echo "Changes pushed to demo branch"
+        else
+          echo "No changes to sync"
+        fi
+
+  push-hf:
+    needs: sync-demo
+    uses: ./.github/workflows/push-to-hf.yml
+    secrets:
+      HF_TOKEN: ${{ secrets.HF_TOKEN }}
+  push-ms:
+    needs: sync-demo
+    uses: ./.github/workflows/push-to-ms.yml
+    secrets:
+      MS_TOKEN: ${{ secrets.MS_TOKEN }}
+    with:
+      ref: demo