diff --git a/.env.example b/.env.example
index 97b68f3..91f6e1a 100644
--- a/.env.example
+++ b/.env.example
@@ -6,7 +6,9 @@ LOG_CHAT=true
 
 CACHE_CHAT_COMPLETION=true
 # `CACHE_BACKEND`: Options (MEMORY, LMDB, LevelDB)
-CACHE_BACKEND=LMDB
+CACHE_BACKEND=LevelDB
+CACHE_ROOT_PATH_OR_URL=./FLAXKV_DB
+DEFAULT_REQUEST_CACHING_VALUE=false
 
 BENCHMARK_MODE=true
 
diff --git a/.github/workflows/python-publish.yml b/.github/workflows/python-publish.yml
index e9187dc..2299792 100644
--- a/.github/workflows/python-publish.yml
+++ b/.github/workflows/python-publish.yml
@@ -10,22 +10,41 @@ on:
 
 
 jobs:
-  deploy:
+  release-build:
     runs-on: ubuntu-latest
+
     steps:
-    - uses: actions/checkout@v3
-    - name: Set up Python
-      uses: actions/setup-python@v4
-      with:
-        python-version: '3.10'
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install setuptools wheel twine build hatch
-    - name: Build and publish
-      env:
-        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
-        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
-      run: |
-        python -m build
-        twine upload dist/*
\ No newline at end of file
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+
+      - name: build release distributions
+        run: |
+          python -m pip install --upgrade pip
+          pip install setuptools wheel twine build hatch
+          python -m build
+
+      - name: upload dists
+        uses: actions/upload-artifact@v3
+        with:
+          name: release-dists
+          path: dist/
+
+  pypi-publish:
+    runs-on: ubuntu-latest
+    needs:
+      - release-build
+    permissions:
+      id-token: write
+
+    steps:
+      - name: Retrieve release distributions
+        uses: actions/download-artifact@v3
+        with:
+          name: release-dists
+          path: dist/
+
+      - name: Publish release distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
\ No newline at end of file
diff --git a/README.md b/README.md
index b927139..a25db85 100644
--- a/README.md
+++ b/README.md
@@ -196,15 +196,19 @@ curl --location 'https://api.openai-forward.com/v1/images/generations' \
 
 ### 代理其它云端模型
 
-- **适用场景：**
-  例如可通过 [LiteLLM](https://github.com/BerriAI/litellm) 可以将 众多云模型的 API 格式转换为 openai
-  的api格式，
-  然后使用本服务进行代理。
+- **场景1:**
+  使用通用转发,由环境变量中`EXTRA_BASE_URL`与`EXTRA_ROUTE_PREFIX` 两变量控制，可对任意来源服务进行转发，
+  可获得请求速率控制与token速率控制；但通用转发不支持自定义秘钥、实时日志和缓存AI响应.
+
+- **场景2：**
+  可通过 [LiteLLM](https://github.com/BerriAI/litellm) 可以将 众多云模型的 API 格式转换为 openai
+  的api格式，然后使用openai风格转发(即`OPENAI_BASE_URL`) 
+
 
 (更多)
 
 ### 代理ChatGPT
-参考根路径下 `docker-compose.yaml` 和 `.env.chatgpt`
+[参考](./deploy.md)
 
 
 <a>
@@ -248,6 +252,7 @@ curl --location 'https://api.openai-forward.com/v1/images/generations' \
 | LOG_CHAT              | 开关聊天内容的日志记录，用于调试和监控                                                  |        `false`         |
 | CACHE_BACKEND         | cache后端，支持内存后端和数据库后端，默认为内存后端，可选lmdb、leveldb数据库后端                     |         `lmdb`         |
 | CACHE_CHAT_COMPLETION | 是否缓存/v1/chat/completions 结果                                          |        `false`         |
+| DEFAULT_REQUEST_CACHING_VALUE | 是否默认开启缓存                                                           |        `false`         |
 
 详细配置说明可参见 [.env.example](.env.example) 文件。(待完善)
 
diff --git a/deploy.md b/deploy.md
index a27ce51..66e6e90 100644
--- a/deploy.md
+++ b/deploy.md
@@ -25,8 +25,12 @@
 **一键免费云平台部署**
 
 1. [Render一键部署](deploy.md#render-一键部署)
-2. [CloudFlare AI Gateway](https://developers.cloudflare.com/ai-gateway/get-started/creating-gateway/)
-3. 更多部署： https://github.com/KenyonY/openai-forward/blob/0.5.x/deploy.md
+2. 更多部署： https://github.com/KenyonY/openai-forward/blob/0.5.x/deploy.md
+
+**其它反代**  
+[CloudFlare AI Gateway](https://developers.cloudflare.com/ai-gateway/get-started/creating-gateway/)  
+[ChatGPT](https://github.com/pandora-next/deploy)  
+
 
 ---
 ## pip部署
diff --git a/docker-compose.yaml b/docker-compose.yaml
index 51d74d9..d8c7483 100644
--- a/docker-compose.yaml
+++ b/docker-compose.yaml
@@ -17,19 +17,3 @@ services:
     restart: unless-stopped
     depends_on:
       - chatgpt
-
-  chatgpt:
-      # use project: https://github.com/gngpp/ninja
-      image: ghcr.io/gngpp/ninja:latest
-      container_name: chatgpt
-      restart: unless-stopped
-      environment:
-        - TZ=Asia/Shanghai
-      command:
-        - run
-        - --arkose-gpt4-har-dir=/root/.gpt4
-#        - --level=debug
-      volumes:
-        - ./har:/root/.gpt4
-#      ports:
-#        - "7999:7999"
diff --git a/pyproject.toml b/pyproject.toml
index d865943..7d3c380 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -29,7 +29,7 @@ dependencies = [
     "pytz",
     "slowapi==0.1.8",
     "aiohttp>=3.8.5",
-    "flaxkv[client]>=0.2.2",
+    "flaxkv[client]>=0.2.4",
     "msgpack",
     "tiktoken>=0.5.1",
     "tomli",