Index
MultiModalLLMMetadata #
Bases: BaseModel
Parameters:
Name | Type | Description | Default |
---|---|---|---|
context_window
|
int | None
|
Total number of tokens the model can be input when generating a response. |
3900
|
num_output
|
int | None
|
Number of tokens the model can output when generating a response. |
256
|
num_input_files
|
int | None
|
Number of input files the model can take when generating a response. |
10
|
is_function_calling_model
|
bool | None
|
Set True if the model supports function calling messages, similar to OpenAI's function calling API. For example, converting 'Email Anya to see if she wants to get coffee next Friday' to a function call like |
False
|
model_name
|
str
|
The model's name used for logging, testing, and sanity checking. For some models this can be automatically discerned. For other models, like locally loaded models, this must be manually specified. |
'unknown'
|
is_chat_model
|
bool
|
Set True if the model exposes a chat interface (i.e. can be passed a sequence of messages, rather than text), like OpenAI's /v1/chat/completions endpoint. |
False
|
Source code in llama-index-core/llama_index/core/multi_modal_llms/base.py
36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 |
|
MultiModalLLM #
Bases: ChainableMixin
, BaseComponent
, DispatcherSpanMixin
Multi-Modal LLM interface.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
callback_manager
|
CallbackManager
|
|
<llama_index.core.callbacks.base.CallbackManager object at 0x7f4a66328d40>
|
Source code in llama-index-core/llama_index/core/multi_modal_llms/base.py
81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 |
|
complete
abstractmethod
#
complete(prompt: str, image_documents: List[ImageNode], **kwargs: Any) -> CompletionResponse
Completion endpoint for Multi-Modal LLM.
Source code in llama-index-core/llama_index/core/multi_modal_llms/base.py
94 95 96 97 98 |
|
stream_complete
abstractmethod
#
stream_complete(prompt: str, image_documents: List[ImageNode], **kwargs: Any) -> CompletionResponseGen
Streaming completion endpoint for Multi-Modal LLM.
Source code in llama-index-core/llama_index/core/multi_modal_llms/base.py
100 101 102 103 104 |
|
chat
abstractmethod
#
chat(messages: Sequence[ChatMessage], **kwargs: Any) -> ChatResponse
Chat endpoint for Multi-Modal LLM.
Source code in llama-index-core/llama_index/core/multi_modal_llms/base.py
106 107 108 109 110 111 112 |
|
stream_chat
abstractmethod
#
stream_chat(messages: Sequence[ChatMessage], **kwargs: Any) -> ChatResponseGen
Stream chat endpoint for Multi-Modal LLM.
Source code in llama-index-core/llama_index/core/multi_modal_llms/base.py
114 115 116 117 118 119 120 |
|
acomplete
abstractmethod
async
#
acomplete(prompt: str, image_documents: List[ImageNode], **kwargs: Any) -> CompletionResponse
Async completion endpoint for Multi-Modal LLM.
Source code in llama-index-core/llama_index/core/multi_modal_llms/base.py
124 125 126 127 128 |
|
astream_complete
abstractmethod
async
#
astream_complete(prompt: str, image_documents: List[ImageNode], **kwargs: Any) -> CompletionResponseAsyncGen
Async streaming completion endpoint for Multi-Modal LLM.
Source code in llama-index-core/llama_index/core/multi_modal_llms/base.py
130 131 132 133 134 |
|
achat
abstractmethod
async
#
achat(messages: Sequence[ChatMessage], **kwargs: Any) -> ChatResponse
Async chat endpoint for Multi-Modal LLM.
Source code in llama-index-core/llama_index/core/multi_modal_llms/base.py
136 137 138 139 140 141 142 |
|
astream_chat
abstractmethod
async
#
astream_chat(messages: Sequence[ChatMessage], **kwargs: Any) -> ChatResponseAsyncGen
Async streaming chat endpoint for Multi-Modal LLM.
Source code in llama-index-core/llama_index/core/multi_modal_llms/base.py
144 145 146 147 148 149 150 |
|
BaseMultiModalComponent #
Bases: QueryComponent
Base LLM component.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
multi_modal_llm
|
MultiModalLLM
|
LLM |
required |
streaming
|
bool
|
Streaming mode |
False
|
Source code in llama-index-core/llama_index/core/multi_modal_llms/base.py
183 184 185 186 187 188 189 190 191 |
|
set_callback_manager #
set_callback_manager(callback_manager: Any) -> None
Set callback manager.
Source code in llama-index-core/llama_index/core/multi_modal_llms/base.py
190 191 |
|
MultiModalCompleteComponent #
Bases: BaseMultiModalComponent
Multi-modal completion component.
Source code in llama-index-core/llama_index/core/multi_modal_llms/base.py
195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 |
|