docs: add vllm llama_cpp docs and standardize configs (#2386)

configs/dbgpt-graphrag.toml

@@ -53,5 +53,3 @@ name = "${env:EMBEDDING_MODEL_NAME:-text-embedding-3-small}"
 provider = "${env:EMBEDDING_MODEL_PROVIDER:-proxy/openai}"
 api_url = "${env:EMBEDDING_MODEL_API_URL:-https://api.openai.com/v1/embeddings}"
 api_key = "${env:OPENAI_API_KEY}"
-
-

configs/dbgpt-local-glm.toml

@@ -26,6 +26,7 @@ provider = "hf"
 # If not provided, the model will be downloaded from the Hugging Face model hub
 # uncomment the following line to specify the model path in the local file system
 # path = "the-model-path-in-the-local-file-system"
+path = "models/THUDM/glm-4-9b-chat-hf"
 
 [[models.embeddings]]
 name = "BAAI/bge-large-zh-v1.5"
@@ -33,4 +34,4 @@ provider = "hf"
 # If not provided, the model will be downloaded from the Hugging Face model hub
 # uncomment the following line to specify the model path in the local file system
 # path = "the-model-path-in-the-local-file-system"
-
+path = "models/BAAI/glm-4-9b-chat-hf"

configs/dbgpt-local-llama-cpp-server.toml

@@ -21,20 +21,13 @@ persist_path = "pilot/data"
 # Model Configurations
 [models]
 [[models.llms]]
-name = "Qwen2.5-Coder-0.5B-Instruct"
+name = "DeepSeek-R1-Distill-Qwen-1.5B"
-# Please make sure install DB-GPT with '--extra llama_cpp_server' extra
 provider = "llama.cpp.server"
 # If not provided, the model will be downloaded from the Hugging Face model hub
 # uncomment the following line to specify the model path in the local file system
-# path = "the-model-path-in-the-local-file-system"
-path = "/data/models/qwen2.5-coder-0.5b-instruct-q4_k_m.gguf"
-
-[[models.llms]]
-name = "DeepSeek-R1-Distill-Qwen-1.5B"
-provider = "llama.cpp.server"
 # https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF
-path = "/data/models/DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf"
+# path = "the-model-path-in-the-local-file-system"
-
+path = "models/DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf"
 
 [[models.embeddings]]
 name = "BAAI/bge-large-zh-v1.5"
@@ -42,5 +35,4 @@ provider = "hf"
 # If not provided, the model will be downloaded from the Hugging Face model hub
 # uncomment the following line to specify the model path in the local file system
 # path = "the-model-path-in-the-local-file-system"
-path = "/data/models/bge-large-zh-v1.5"
+path = "models/BAAI/bge-large-zh-v1.5"
-

configs/dbgpt-local-llama-cpp.toml

@@ -21,19 +21,13 @@ persist_path = "pilot/data"
 # Model Configurations
 [models]
 [[models.llms]]
-name = "Qwen2.5-Coder-0.5B-Instruct"
+name = "DeepSeek-R1-Distill-Qwen-1.5B"
-# Please make sure install DB-GPT with '--extra llama_cpp' extra
 provider = "llama.cpp"
 # If not provided, the model will be downloaded from the Hugging Face model hub
 # uncomment the following line to specify the model path in the local file system
-# path = "the-model-path-in-the-local-file-system"
-path = "/data/models/qwen2.5-coder-0.5b-instruct-q4_k_m.gguf"
-
-[[models.llms]]
-name = "DeepSeek-R1-Distill-Qwen-1.5B"
-provider = "llama.cpp"
 # https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-1.5B-GGUF
-path = "/data/models/DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf"
+# path = "the-model-path-in-the-local-file-system"
+path = "models/DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf"
 
 
 [[models.embeddings]]
@@ -42,5 +36,5 @@ provider = "hf"
 # If not provided, the model will be downloaded from the Hugging Face model hub
 # uncomment the following line to specify the model path in the local file system
 # path = "the-model-path-in-the-local-file-system"
-path = "/data/models/bge-large-zh-v1.5"
+path = "models/BAAI/bge-large-zh-v1.5"
 

configs/dbgpt-local-qwen.toml

@@ -26,7 +26,7 @@ provider = "hf"
 # If not provided, the model will be downloaded from the Hugging Face model hub
 # uncomment the following line to specify the model path in the local file system
 # path = "the-model-path-in-the-local-file-system"
-path = "/data/models/Qwen2.5-Coder-0.5B-Instruct"
+path = "models/Qwen2.5-Coder-0.5B-Instruct"
 
 [[models.embeddings]]
 name = "BAAI/bge-large-zh-v1.5"
@@ -34,5 +34,5 @@ provider = "hf"
 # If not provided, the model will be downloaded from the Hugging Face model hub
 # uncomment the following line to specify the model path in the local file system
 # path = "the-model-path-in-the-local-file-system"
-path = "/data/models/bge-large-zh-v1.5"
+path = "models/BAAI/bge-large-zh-v1.5"
 

configs/dbgpt-local-vllm.toml

@@ -21,21 +21,13 @@ persist_path = "pilot/data"
 # Model Configurations
 [models]
 [[models.llms]]
-name = "Qwen2.5-Coder-0.5B-Instruct"
+name = "DeepSeek-R1-Distill-Qwen-1.5B"
 provider = "vllm"
 # If not provided, the model will be downloaded from the Hugging Face model hub
 # uncomment the following line to specify the model path in the local file system
 # path = "the-model-path-in-the-local-file-system"
-path = "/data/models/Qwen2.5-Coder-0.5B-Instruct"
+path = "models/DeepSeek-R1-Distill-Qwen-1.5B"
-# dtype="float32"
+# dtype = "float32"
-
-# [[models.llms]]
-# name = "DeepSeek-R1-Distill-Qwen-1.5B"
-# provider = "vllm"
-# # If not provided, the model will be downloaded from the Hugging Face model hub
-# # uncomment the following line to specify the model path in the local file system
-# # path = "the-model-path-in-the-local-file-system"
-# path = "/data/models/DeepSeek-R1-Distill-Qwen-1.5B"
 
 [[models.embeddings]]
 name = "BAAI/bge-large-zh-v1.5"

configs/dbgpt-proxy-deepseek.toml

@@ -24,13 +24,9 @@ persist_path = "pilot/data"
 [models]
 [[models.llms]]
 name = "deepseek-reasoner"
+# name = "deepseek-chat"
 provider = "proxy/deepseek"
-api_key = "${env:DEEPSEEK_API_KEY}"
+api_key = "your_deepseek_api_key"
-
-[[models.llms]]
-name = "deepseek-chat"
-provider = "proxy/deepseek"
-api_key = "${env:DEEPSEEK_API_KEY}"
 
 [[models.embeddings]]
 name = "BAAI/bge-large-zh-v1.5"
@@ -38,4 +34,4 @@ provider = "hf"
 # If not provided, the model will be downloaded from the Hugging Face model hub
 # uncomment the following line to specify the model path in the local file system
 # path = "the-model-path-in-the-local-file-system"
-path = "/data/models/bge-large-zh-v1.5"
+path = "models/bge-large-zh-v1.5"

docs/README.md

@@ -7,7 +7,7 @@
 - Install docusaurus dependencies, generate node_modules folder.
 
 ```
-sudo yarn install
+yarn install
 ```
 
 ### launch

docs/docs/quickstart.md

@@ -74,6 +74,19 @@ uv --version
 ```
 
 ## Deploy DB-GPT 
+:::tip
+If you are in the China region, you can add --index-url=https://pypi.tuna.tsinghua.edu.cn/simple at the end of the command.Like this:
+```bash
+uv sync --all-packages \
+--extra "base" \
+--extra "proxy_openai" \
+--extra "rag" \
+--extra "storage_chromadb" \
+--extra "dbgpts" \
+--index-url=https://pypi.tuna.tsinghua.edu.cn/simple
+```
+This tutorial assumes that you can establish network communication with the dependency download sources.
+:::
 
 ### Install Dependencies
 
@@ -83,13 +96,15 @@ uv --version
     {label: 'OpenAI (proxy)', value: 'openai'},
     {label: 'DeepSeek (proxy)', value: 'deepseek'},
     {label: 'GLM4 (local)', value: 'glm-4'},
+    {label: 'VLLM (local)', value: 'vllm'},
+    {label: 'LLAMA_CPP (local)', value: 'llama_cpp'},
   ]}>
 
   <TabItem value="openai" label="OpenAI(proxy)">
 
 ```bash
 # Use uv to install dependencies needed for OpenAI proxy
-uv sync --all-packages --frozen \
+uv sync --all-packages \
 --extra "base" \
 --extra "proxy_openai" \
 --extra "rag" \
@@ -129,7 +144,7 @@ uv run python packages/dbgpt-app/src/dbgpt_app/dbgpt_server.py --config configs/
 
 ```bash
 # Use uv to install dependencies needed for OpenAI proxy
-uv sync --all-packages --frozen \
+uv sync --all-packages \
 --extra "base" \
 --extra "proxy_openai" \
 --extra "rag" \
@@ -141,8 +156,17 @@ uv sync --all-packages --frozen \
 
 To run DB-GPT with DeepSeek proxy, you must provide the DeepSeek API key in the `configs/dbgpt-proxy-deepseek.toml`.
 
-And you can specify your embedding model in the `configs/dbgpt-proxy-deepseek.toml` configuration file, the default embedding model is `BAAI/bge-large-zh-v1.5`. If you want to use other embedding models, you can modify the `configs/dbgpt-proxy-deepseek.toml` configuration file and specify the `name` and `provider` of the embedding model in the `[[models.embeddings]]` section. The provider can be `hf`.
+And you can specify your embedding model in the `configs/dbgpt-proxy-deepseek.toml` configuration file, the default embedding model is `BAAI/bge-large-zh-v1.5`. If you want to use other embedding models, you can modify the `configs/dbgpt-proxy-deepseek.toml` configuration file and specify the `name` and `provider` of the embedding model in the `[[models.embeddings]]` section. The provider can be `hf`.Finally, you need to append `--extra "hf"` at the end of the dependency installation command. Here's the updated command:
-
+```bash
+uv sync --all-packages \
+--extra "base" \
+--extra "proxy_openai" \
+--extra "rag" \
+--extra "storage_chromadb" \
+--extra "dbgpts" \
+--extra "hf" 
+```
+**Model Configurations**:
 ```toml
 # Model Configurations
 [models]
@@ -178,7 +202,7 @@ uv run python packages/dbgpt-app/src/dbgpt_app/dbgpt_server.py --config configs/
 ```bash
 # Use uv to install dependencies needed for GLM4
 # Install core dependencies and select desired extensions
-uv sync --all-packages --frozen \
+uv sync --all-packages \
 --extra "base" \
 --extra "hf" \
 --extra "rag" \
@@ -214,6 +238,94 @@ Then run the following command to start the webserver:
 
 ```bash
 uv run dbgpt start webserver --config configs/dbgpt-local-glm.toml
+```
+
+  </TabItem>
+    <TabItem value="vllm" label="VLLM(local)">
+
+```bash
+# Use uv to install dependencies needed for vllm
+# Install core dependencies and select desired extensions
+uv sync --all-packages \
+--extra "base" \
+--extra "vllm" \
+--extra "rag" \
+--extra "storage_chromadb" \
+--extra "quant_bnb" \
+--extra "dbgpts"
+```
+
+### Run Webserver
+
+To run DB-GPT with the local model. You can modify the `configs/dbgpt-local-vllm.toml` configuration file to specify the model path and other parameters.
+
+```toml
+# Model Configurations
+[models]
+[[models.llms]]
+name = "THUDM/glm-4-9b-chat-hf"
+provider = "vllm"
+# If not provided, the model will be downloaded from the Hugging Face model hub
+# uncomment the following line to specify the model path in the local file system
+# path = "the-model-path-in-the-local-file-system"
+
+[[models.embeddings]]
+name = "BAAI/bge-large-zh-v1.5"
+provider = "hf"
+# If not provided, the model will be downloaded from the Hugging Face model hub
+# uncomment the following line to specify the model path in the local file system
+# path = "the-model-path-in-the-local-file-system"
+```
+In the above configuration file, `[[models.llms]]` specifies the LLM model, and `[[models.embeddings]]` specifies the embedding model. If you not provide the `path` parameter, the model will be downloaded from the Hugging Face model hub according to the `name` parameter.
+
+Then run the following command to start the webserver:
+
+```bash
+uv run dbgpt start webserver --config configs/dbgpt-local-vllm.toml
+```
+
+  </TabItem>
+      <TabItem value="llama_cpp" label="LLAMA_CPP(local)">
+
+```bash
+# Use uv to install dependencies needed for llama-cpp
+# Install core dependencies and select desired extensions
+uv sync --all-packages \
+--extra "base" \
+--extra "llama_cpp" \
+--extra "rag" \
+--extra "storage_chromadb" \
+--extra "quant_bnb" \
+--extra "dbgpts"
+```
+
+### Run Webserver
+
+To run DB-GPT with the local model. You can modify the `configs/dbgpt-local-llama-cpp.toml` configuration file to specify the model path and other parameters.
+
+```toml
+# Model Configurations
+[models]
+[[models.llms]]
+name = "DeepSeek-R1-Distill-Qwen-1.5B"
+provider = "llama.cpp"
+# If not provided, the model will be downloaded from the Hugging Face model hub
+# uncomment the following line to specify the model path in the local file system
+# path = "the-model-path-in-the-local-file-system"
+
+[[models.embeddings]]
+name = "BAAI/bge-large-zh-v1.5"
+provider = "hf"
+# If not provided, the model will be downloaded from the Hugging Face model hub
+# uncomment the following line to specify the model path in the local file system
+# path = "the-model-path-in-the-local-file-system"
+```
+In the above configuration file, `[[models.llms]]` specifies the LLM model, and `[[models.embeddings]]` specifies the embedding model. If you not provide the `path` parameter, the model will be downloaded from the Hugging Face model hub according to the `name` parameter.
+
+Then run the following command to start the webserver:
+
+```bash
+uv run dbgpt start webserver --config configs/dbgpt-local-llama-cpp.toml
 ```
 
   </TabItem>