Add ZhipuAI model wrappers (#181)

--------- Co-authored-by: wenhao <[email protected]>
modelscope · May 6, 2024 · be8db4c · be8db4c
1 parent 1c993f9
commit be8db4c
Show file tree

Hide file tree

Showing 13 changed files with 699 additions and 0 deletions.
diff --git a/README.md b/README.md
@@ -82,6 +82,8 @@ services and third-party model APIs.
 |                        | Multimodal      | [`DashScopeMultiModalWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/dashscope_model.py)     | [guidance](https://modelscope.github.io/agentscope/en/tutorial/203-model.html#dashscope-api) <br> [template](https://github.com/modelscope/agentscope/blob/main/examples/model_configs_template/dashscope_multimodal_template.json)    | qwen-vl-max, qwen-vl-chat-v1, qwen-audio-chat |
 | Gemini API             | Chat            | [`GeminiChatWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/gemini_model.py)                 | [guidance](https://modelscope.github.io/agentscope/en/tutorial/203-model.html#gemini-api) <br> [template](https://github.com/modelscope/agentscope/blob/main/examples/model_configs_template/gemini_chat_template.json)       | gemini-pro, ...                               |
 |                        | Embedding       | [`GeminiEmbeddingWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/gemini_model.py)            | [guidance](https://modelscope.github.io/agentscope/en/tutorial/203-model.html#gemini-api) <br> [template](https://github.com/modelscope/agentscope/blob/main/examples/model_configs_template/gemini_embedding_template.json)       | models/embedding-001, ...                     |
+| ZhipuAI API             | Chat            | [`ZhipuAIChatWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/zhipu_model.py)                 | [guidance](https://modelscope.github.io/agentscope/en/tutorial/203-model.html#zhipu-api) <br> [template](https://github.com/modelscope/agentscope/blob/main/examples/model_configs_template/zhipu_chat_template.json)       | glm-4, ...                               |
+|                        | Embedding       | [`ZhipuAIEmbeddingWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/zhipu_model.py)            | [guidance](https://modelscope.github.io/agentscope/en/tutorial/203-model.html#zhipu-api) <br> [template](https://github.com/modelscope/agentscope/blob/main/examples/model_configs_template/zhipu_embedding_template.json)       | embedding-2, ...                     |
 | ollama                 | Chat            | [`OllamaChatWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/ollama_model.py)                 | [guidance](https://modelscope.github.io/agentscope/en/tutorial/203-model.html#ollama-api) <br> [template](https://github.com/modelscope/agentscope/blob/main/examples/model_configs_template/ollama_chat_template.json)       | llama3, llama2, Mistral, ...                  |
 |                        | Embedding       | [`OllamaEmbeddingWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/ollama_model.py)            | [guidance](https://modelscope.github.io/agentscope/en/tutorial/203-model.html#ollama-api) <br> [template](https://github.com/modelscope/agentscope/blob/main/examples/model_configs_template/ollama_embedding_template.json)       | llama2, Mistral, ...                          |
 |                        | Generation      | [`OllamaGenerationWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/ollama_model.py)           | [guidance](https://modelscope.github.io/agentscope/en/tutorial/203-model.html#ollama-api) <br> [template](https://github.com/modelscope/agentscope/blob/main/examples/model_configs_template/ollama_generate_template.json)       | llama2, Mistral, ...                          |
@@ -118,6 +120,7 @@ the following libraries.
   - [Self-Organizing Conversation](./examples/conversation_self_organizing)
   - [Basic Conversation with LangChain library](./examples/conversation_with_langchain)
   - [Conversation with ReAct Agent](./examples/conversation_with_react_agent)
+  - [Conversation in Natural Language to Query SQL](./examples/conversation_nl2sql/)
   - [Conversation with RAG Agent](./examples/conversation_with_RAG_agents)
 
 - Game

diff --git a/README_ZH.md b/README_ZH.md
@@ -71,6 +71,8 @@ AgentScope提供了一系列`ModelWrapper`来支持本地模型服务和第三
 |                        | Multimodal      | [`DashScopeMultiModalWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/dashscope_model.py)     | [guidance](https://modelscope.github.io/agentscope/en/tutorial/203-model.html#dashscope-api) <br> [template](https://github.com/modelscope/agentscope/blob/main/examples/model_configs_template/dashscope_multimodal_template.json)    | qwen-vl-max, qwen-vl-chat-v1, qwen-audio-chat |
 | Gemini API             | Chat            | [`GeminiChatWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/gemini_model.py)                 | [guidance](https://modelscope.github.io/agentscope/en/tutorial/203-model.html#gemini-api) <br> [template](https://github.com/modelscope/agentscope/blob/main/examples/model_configs_template/gemini_chat_template.json)       | gemini-pro, ...                               |
 |                        | Embedding       | [`GeminiEmbeddingWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/gemini_model.py)            | [guidance](https://modelscope.github.io/agentscope/en/tutorial/203-model.html#gemini-api) <br> [template](https://github.com/modelscope/agentscope/blob/main/examples/model_configs_template/gemini_embedding_template.json)       | models/embedding-001, ...                     |
+| ZhipuAI API             | Chat            | [`ZhipuAIChatWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/zhipu_model.py)                 | [guidance](https://modelscope.github.io/agentscope/en/tutorial/203-model.html#zhipu-api) <br> [template](https://github.com/modelscope/agentscope/blob/main/examples/model_configs_template/zhipu_chat_template.json)       | glm-4, ...                               |
+|                        | Embedding       | [`ZhipuAIEmbeddingWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/zhipu_model.py)            | [guidance](https://modelscope.github.io/agentscope/en/tutorial/203-model.html#zhipu-api) <br> [template](https://github.com/modelscope/agentscope/blob/main/examples/model_configs_template/zhipu_embedding_template.json)       | embedding-2, ...                     |
 | ollama                 | Chat            | [`OllamaChatWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/ollama_model.py)                 | [guidance](https://modelscope.github.io/agentscope/en/tutorial/203-model.html#ollama-api) <br> [template](https://github.com/modelscope/agentscope/blob/main/examples/model_configs_template/ollama_chat_template.json)       | llama3, llama2, Mistral, ...                  |
 |                        | Embedding       | [`OllamaEmbeddingWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/ollama_model.py)            | [guidance](https://modelscope.github.io/agentscope/en/tutorial/203-model.html#ollama-api) <br> [template](https://github.com/modelscope/agentscope/blob/main/examples/model_configs_template/ollama_embedding_template.json)       | llama2, Mistral, ...                          |
 |                        | Generation      | [`OllamaGenerationWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/ollama_model.py)           | [guidance](https://modelscope.github.io/agentscope/en/tutorial/203-model.html#ollama-api) <br> [template](https://github.com/modelscope/agentscope/blob/main/examples/model_configs_template/ollama_generate_template.json)       | llama2, Mistral, ...                          |

diff --git a/docs/sphinx_doc/en/source/tutorial/203-model.md b/docs/sphinx_doc/en/source/tutorial/203-model.md
@@ -14,6 +14,7 @@ Currently, AgentScope supports the following model service APIs:
 - OpenAI API, including chat, image generation (DALL-E), and Embedding.
 - DashScope API, including chat, image sythesis and text embedding.
 - Gemini API, including chat and embedding.
+- ZhipuAI API, including chat and embedding.
 - Ollama API, including chat, embedding and generation.
 - Post Request API, model inference services based on Post
   requests, including Huggingface/ModelScope Inference API and various
@@ -81,6 +82,8 @@ In the current AgentScope, the supported `model_type` types, the corresponding
 |                        | Multimodal      | [`DashScopeMultiModalWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/dashscope_model.py)     | `"dashscope_multimodal"`      | qwen-vl-plus, qwen-vl-max, qwen-audio-turbo, ... |
 | Gemini API             | Chat            | [`GeminiChatWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/gemini_model.py)                 | `"gemini_chat"`               | gemini-pro, ...                                  |
 |                        | Embedding       | [`GeminiEmbeddingWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/gemini_model.py)            | `"gemini_embedding"`          | models/embedding-001, ...                        |
+| ZhipuAI API             | Chat            | [`ZhipuAIChatWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/zhipu_model.py)                 | `"zhipuai_chat"`               | glm4, ...                                  |
+|                        | Embedding       | [`ZhipuAIEmbeddingWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/zhipu_model.py)            | `"zhipuai_embedding"`          | embedding-2, ...                        |
 | ollama                 | Chat            | [`OllamaChatWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/ollama_model.py)                 | `"ollama_chat"`               | llama2, ...                                      |
 |                        | Embedding       | [`OllamaEmbeddingWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/ollama_model.py)            | `"ollama_embedding"`          | llama2, ...                                      |
 |                        | Generation      | [`OllamaGenerationWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/ollama_model.py)           | `"ollama_generate"`           | llama2, ...                                      |
@@ -303,6 +306,48 @@ Here we provide example configurations for different model wrappers.
 
 <br/>
 
+
+#### ZhipuAI API
+
+<details>
+<summary>ZhipuAI Chat API (<code><a href="https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/zhipu_model.py">agentscope.models.ZhipuAIChatWrapper</a></code>)</summary>
+
+```python
+{
+    "config_name": "my_zhipuai_chat_config",
+    "model_type": "zhipuai_chat",
+
+    # Required parameters
+    "model_name": "{model_name}",               # The model name in ZhipuAI API, e.g. glm-4
+
+    # Optional parameters
+    "api_key": "{your_api_key}"
+}
+```
+
+</details>
+
+<details>
+<summary>ZhipuAI Embedding API (<code><a href="https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/zhipu_model.py">agentscope.models.ZhipuAIEmbeddingWrapper</a></code>)</summary>
+
+```python
+{
+    "config_name": "my_zhipuai_embedding_config",
+    "model_type": "zhipuai_embedding",
+
+    # Required parameters
+    "model_name": "{model_name}",               # The model name in ZhipuAI API, e.g. embedding-2
+
+    # Optional parameters
+    "api_key": "{your_api_key}",
+}
+```
+
+</details>
+
+<br/>
+
+
 #### Ollama API
 
 <details>

diff --git a/docs/sphinx_doc/en/source/tutorial/206-prompt.md b/docs/sphinx_doc/en/source/tutorial/206-prompt.md
@@ -44,6 +44,7 @@ generation model APIs.
 - [OllamaChatWrapper](#ollamachatwrapper)
 - [OllamaGenerationWrapper](#ollamagenerationwrapper)
 - [GeminiChatWrapper](#geminichatwrapper)
+- [ZhipuAIChatWrapper](#zhipuaichatwrapper)
 
 These strategies are implemented in the `format` functions of the model
 wrapper classes.
@@ -365,6 +366,47 @@ print(prompt)
 ]
 ```
 
+### `ZhipuAIChatWrapper`
+
+`ZhipuAIChatWrapper` encapsulates the ZhipuAI chat API, which takes a list of messages as input. The message must obey the following rules:
+
+- Require `role` and `content` fields, and `role` must be either `"user"`
+  `"system"` or `"assistant"`.
+- There must be at least one `user` message.
+
+#### Prompt Strategy
+
+If the role field of the first message is `"system"`, it will be converted into a single message with the `role` field as `"system"` and the `content` field as the system message. The rest of the messages will be converted into a message with the `role` field as `"user"` and the `content` field as the dialogue history.
+
+An example is shown below:
+
+```python
+from agentscope.models import ZhipuAIChatWrapper
+from agentscope.message import Msg
+
+model = ZhipuAIChatWrapper(
+    config_name="", # empty since we directly initialize the model wrapper
+    model_name="glm-4",
+    api_key="your api key",
+)
+
+prompt = model.format(
+   Msg("system", "You're a helpful assistant", role="system"),   # Msg object
+   [                                                             # a list of Msg objects
+      Msg(name="Bob", content="Hi!", role="assistant"),
+      Msg(name="Alice", content="Nice to meet you!", role="assistant"),
+   ],
+)
+print(prompt)
+```
+
+```bash
+[
+  {"role": "system", "content": "You are a helpful assistant"},
+  {"role": "user", "content": "## Dialogue History\nBob: Hi!\nAlice: Nice to meet you!"},
+]
+```
+
 ## Prompt Engine (Will be deprecated in the future)
 
 AgentScope provides the `PromptEngine` class to simplify the process of crafting

diff --git a/docs/sphinx_doc/zh_CN/source/tutorial/203-model.md b/docs/sphinx_doc/zh_CN/source/tutorial/203-model.md
@@ -11,6 +11,7 @@ AgentScope中，模型的部署和调用是通过`ModelWrapper`来解耦开的
 - OpenAI API，包括对话（Chat），图片生成（DALL-E)和文本嵌入（Embedding）。
 - DashScope API，包括对话（Chat）和图片生成（Image Sythesis)和文本嵌入（Text Embedding)。
 - Gemini API，包括对话（Chat）和嵌入（Embedding）。
+- ZhipuAi API，包括对话（Chat）和嵌入（Embedding）。
 - Ollama API，包括对话（Chat），嵌入（Embedding）和生成（Generation）。
 - Post请求API，基于Post请求实现的模型推理服务，包括Huggingface/ModelScope
   Inference API和各种符合Post请求格式的API。
@@ -101,6 +102,8 @@ API如下：
 |                        | Multimodal      | [`DashScopeMultiModalWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/dashscope_model.py)     | `"dashscope_multimodal"`      | qwen-vl-plus, qwen-vl-max, qwen-audio-turbo, ... |
 | Gemini API             | Chat            | [`GeminiChatWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/gemini_model.py)                 | `"gemini_chat"`               | gemini-pro, ...                                  |
 |                        | Embedding       | [`GeminiEmbeddingWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/gemini_model.py)            | `"gemini_embedding"`          | models/embedding-001, ...                        |
+| ZhipuAI API             | Chat            | [`ZhipuAIChatWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/zhipu_model.py)                 | `"zhipuai_chat"`               | glm-4, ...                                  |
+|                        | Embedding       | [`ZhipuAIEmbeddingWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/zhipu_model.py)            | `"zhipuai_embedding"`          | embedding-2, ...                        |
 | ollama                 | Chat            | [`OllamaChatWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/ollama_model.py)                 | `"ollama_chat"`               | llama2, ...                                      |
 |                        | Embedding       | [`OllamaEmbeddingWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/ollama_model.py)            | `"ollama_embedding"`          | llama2, ...                                      |
 |                        | Generation      | [`OllamaGenerationWrapper`](https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/ollama_model.py)           | `"ollama_generate"`           | llama2, ...                                      |
@@ -323,6 +326,48 @@ API如下：
 
 <br/>
 
+
+#### ZhipuAI API
+
+<details>
+<summary>ZhipuAI Chat API (<code><a href="https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/zhipu_model.py">agentscope.models.ZhipuAIChatWrapper</a></code>)</summary>
+
+```python
+{
+    "config_name": "my_zhipuai_chat_config",
+    "model_type": "zhipuai_chat",
+
+    # Required parameters
+    "model_name": "{model_name}",               # The model name in ZhipuAI API, e.g. glm-4
+
+    # Optional parameters
+    "api_key": "{your_api_key}"
+}
+```
+
+</details>
+
+<details>
+<summary>ZhipuAI Embedding API (<code><a href="https://github.com/modelscope/agentscope/blob/main/src/agentscope/models/zhipu_model.py">agentscope.models.ZhipuAIEmbeddingWrapper</a></code>)</summary>
+
+```python
+{
+    "config_name": "my_zhipuai_embedding_config",
+    "model_type": "zhipuai_embedding",
+
+    # Required parameters
+    "model_name": "{model_name}",               # The model name in ZhipuAI API, e.g. embedding-2
+
+    # Optional parameters
+    "api_key": "{your_api_key}",
+}
+```
+
+</details>
+
+<br/>
+
+
 #### Ollama API
 
 <details>

diff --git a/docs/sphinx_doc/zh_CN/source/tutorial/206-prompt.md b/docs/sphinx_doc/zh_CN/source/tutorial/206-prompt.md
@@ -29,6 +29,7 @@ AgentScope为以下的模型API提供了内置的提示构建策略。
 - [OllamaChatWrapper](#ollamachatwrapper)
 - [OllamaGenerationWrapper](#ollamagenerationwrapper)
 - [GeminiChatWrapper](#geminichatwrapper)
+- [ZhipuAIChatWrapper](#zhipuaichatwrapper)
 
 这些策略是在对应Model Wrapper类的`format`函数中实现的。它接受`Msg`对象，`Msg`对象的列表或它们的混合作为输入。在`format`函数将会把输入重新组织成一个`Msg`对象的列表，因此为了方便解释，我们在下面的章节中认为`format`函数的输入是`Msg`对象的列表。
 
@@ -326,6 +327,49 @@ print(prompt)
 ]
 ```
 
+
+### `ZhipuAIChatWrapper`
+
+`ZhipuAIChatWrapper`封装了ZhipuAi聊天API，它接受消息列表或字符串提示作为输入。与DashScope聊天API类似，如果我们传递消息列表，它必须遵守以下规则：
+
+- 必须有 role 和 content 字段，且 role 必须是 "user"、"system" 或 "assistant" 中的一个。
+- 至少有一个 user 消息。
+
+当代理可能扮演多种不同角色并连续发言时，这些要求使得构建多代理对话变得困难。
+因此，我们决定在内置的`format`函数中将消息列表转换为字符串提示，并且封装在一条user信息中。
+
+#### 提示的构建策略
+
+如果第一条消息的 role 字段是 "system"，它将被转换为带有 role 字段为 "system" 和 content 字段为系统消息的单个消息。其余的消息会被转化为带有 role 字段为 "user" 和 content 字段为对话历史的消息。
+下面展示了一个示例：
+
+```python
+from agentscope.models import ZhipuAIChatWrapper
+from agentscope.message import Msg
+
+model = ZhipuAIChatWrapper(
+    config_name="", # empty since we directly initialize the model wrapper
+    model_name="glm-4",
+    api_key="your api key",
+)
+
+prompt = model.format(
+   Msg("system", "You're a helpful assistant", role="system"),   # Msg object
+   [                                                             # a list of Msg objects
+      Msg(name="Bob", content="Hi!", role="assistant"),
+      Msg(name="Alice", content="Nice to meet you!", role="assistant"),
+   ],
+)
+print(prompt)
+```
+
+```bash
+[
+  {"role": "system", "content": "You are a helpful assistant"},
+  {"role": "user", "content": "## Dialogue History\nBob: Hi!\nAlice: Nice to meet you!"},
+]
+```
+
 ## 关于`PromptEngine`类 （将会在未来版本弃用）
 
 `PromptEngine`类提供了一种结构化的方式来合并不同的提示组件，比如指令、提示、对话历史和用户输入，以适合底层语言模型的格式。

diff --git a/examples/model_configs_template/zhipu_chat_template.json b/examples/model_configs_template/zhipu_chat_template.json
@@ -0,0 +1,7 @@
+[{
+    "config_name": "zhipuai_chat-glm",
+    "model_type": "zhipuai_chat",
+    "model_name": "glm-4",
+    "api_key": "{your_api_key}"
+}
+]