Index
MultiModalLLM #
Bases: ChainableMixin
, BaseComponent
多模式LLM界面。
Source code in llama_index/core/multi_modal_llms/base.py
74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 |
|
complete
abstractmethod
#
complete(
prompt: str,
image_documents: Sequence[ImageDocument],
**kwargs: Any
) -> CompletionResponse
多模式LLM的完成端点。
Source code in llama_index/core/multi_modal_llms/base.py
95 96 97 98 99 |
|
stream_complete
abstractmethod
#
stream_complete(
prompt: str,
image_documents: Sequence[ImageDocument],
**kwargs: Any
) -> CompletionResponseGen
多模式LLM的流式完成端点。
Source code in llama_index/core/multi_modal_llms/base.py
101 102 103 104 105 |
|
chat
abstractmethod
#
chat(
messages: Sequence[ChatMessage], **kwargs: Any
) -> ChatResponse
多模式LLM的聊天端点。
Source code in llama_index/core/multi_modal_llms/base.py
107 108 109 110 111 112 113 |
|
stream_chat
abstractmethod
#
stream_chat(
messages: Sequence[ChatMessage], **kwargs: Any
) -> ChatResponseGen
多模式LLM的流式聊天端点。
Source code in llama_index/core/multi_modal_llms/base.py
115 116 117 118 119 120 121 |
|
acomplete
abstractmethod
async
#
acomplete(
prompt: str,
image_documents: Sequence[ImageDocument],
**kwargs: Any
) -> CompletionResponse
多模式LLM的异步完成端点。
Source code in llama_index/core/multi_modal_llms/base.py
125 126 127 128 129 |
|
astream_complete
abstractmethod
async
#
astream_complete(
prompt: str,
image_documents: Sequence[ImageDocument],
**kwargs: Any
) -> CompletionResponseAsyncGen
多模式LLM的异步流完成端点。
Source code in llama_index/core/multi_modal_llms/base.py
131 132 133 134 135 |
|
achat
abstractmethod
async
#
achat(
messages: Sequence[ChatMessage], **kwargs: Any
) -> ChatResponse
多模式LLM的异步聊天端点。
Source code in llama_index/core/multi_modal_llms/base.py
137 138 139 140 141 142 143 |
|
astream_chat
abstractmethod
async
#
astream_chat(
messages: Sequence[ChatMessage], **kwargs: Any
) -> ChatResponseAsyncGen
多模式LLM的异步流式聊天端点。
Source code in llama_index/core/multi_modal_llms/base.py
145 146 147 148 149 150 151 |
|
BaseMultiModalComponent #
Bases: QueryComponent
基础LLM组件。
Source code in llama_index/core/multi_modal_llms/base.py
162 163 164 165 166 167 168 169 170 171 172 |
|
set_callback_manager #
set_callback_manager(callback_manager: Any) -> None
设置回调管理器。
Source code in llama_index/core/multi_modal_llms/base.py
171 172 |
|
MultiModalCompleteComponent #
Bases: BaseMultiModalComponent
多模态完成组件。
Source code in llama_index/core/multi_modal_llms/base.py
176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 |
|