Spaces:
Runtime error
Runtime error
File size: 14,177 Bytes
ed4d993 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 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 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 |
import json
from typing import Any, AsyncIterator, Dict, Iterator, List, Optional, Union, cast
from langchain_core._api import deprecated
from langchain_core.callbacks import (
AsyncCallbackManagerForLLMRun,
CallbackManagerForLLMRun,
)
from langchain_core.language_models.chat_models import BaseChatModel, LangSmithParams
from langchain_core.messages import (
AIMessage,
AIMessageChunk,
BaseMessage,
ChatMessage,
HumanMessage,
SystemMessage,
)
from langchain_core.outputs import ChatGeneration, ChatGenerationChunk, ChatResult
from langchain_community.llms.ollama import OllamaEndpointNotFoundError, _OllamaCommon
@deprecated("0.0.3", alternative="_chat_stream_response_to_chat_generation_chunk")
def _stream_response_to_chat_generation_chunk(
stream_response: str,
) -> ChatGenerationChunk:
"""Convert a stream response to a generation chunk."""
parsed_response = json.loads(stream_response)
generation_info = parsed_response if parsed_response.get("done") is True else None
return ChatGenerationChunk(
message=AIMessageChunk(content=parsed_response.get("response", "")),
generation_info=generation_info,
)
def _chat_stream_response_to_chat_generation_chunk(
stream_response: str,
) -> ChatGenerationChunk:
"""Convert a stream response to a generation chunk."""
parsed_response = json.loads(stream_response)
generation_info = parsed_response if parsed_response.get("done") is True else None
return ChatGenerationChunk(
message=AIMessageChunk(
content=parsed_response.get("message", {}).get("content", "")
),
generation_info=generation_info,
)
class ChatOllama(BaseChatModel, _OllamaCommon):
"""Ollama locally runs large language models.
To use, follow the instructions at https://ollama.ai/.
Example:
.. code-block:: python
from langchain_community.chat_models import ChatOllama
ollama = ChatOllama(model="llama2")
"""
@property
def _llm_type(self) -> str:
"""Return type of chat model."""
return "ollama-chat"
@classmethod
def is_lc_serializable(cls) -> bool:
"""Return whether this model can be serialized by Langchain."""
return False
def _get_ls_params(
self, stop: Optional[List[str]] = None, **kwargs: Any
) -> LangSmithParams:
"""Get standard params for tracing."""
params = self._get_invocation_params(stop=stop, **kwargs)
ls_params = LangSmithParams(
ls_provider="ollama",
ls_model_name=self.model,
ls_model_type="chat",
ls_temperature=params.get("temperature", self.temperature),
)
if ls_max_tokens := params.get("num_predict", self.num_predict):
ls_params["ls_max_tokens"] = ls_max_tokens
if ls_stop := stop or params.get("stop", None) or self.stop:
ls_params["ls_stop"] = ls_stop
return ls_params
@deprecated("0.0.3", alternative="_convert_messages_to_ollama_messages")
def _format_message_as_text(self, message: BaseMessage) -> str:
if isinstance(message, ChatMessage):
message_text = f"\n\n{message.role.capitalize()}: {message.content}"
elif isinstance(message, HumanMessage):
if isinstance(message.content, List):
first_content = cast(List[Dict], message.content)[0]
content_type = first_content.get("type")
if content_type == "text":
message_text = f"[INST] {first_content['text']} [/INST]"
elif content_type == "image_url":
message_text = first_content["image_url"]["url"]
else:
message_text = f"[INST] {message.content} [/INST]"
elif isinstance(message, AIMessage):
message_text = f"{message.content}"
elif isinstance(message, SystemMessage):
message_text = f"<<SYS>> {message.content} <</SYS>>"
else:
raise ValueError(f"Got unknown type {message}")
return message_text
def _format_messages_as_text(self, messages: List[BaseMessage]) -> str:
return "\n".join(
[self._format_message_as_text(message) for message in messages]
)
def _convert_messages_to_ollama_messages(
self, messages: List[BaseMessage]
) -> List[Dict[str, Union[str, List[str]]]]:
ollama_messages: List = []
for message in messages:
role = ""
if isinstance(message, HumanMessage):
role = "user"
elif isinstance(message, AIMessage):
role = "assistant"
elif isinstance(message, SystemMessage):
role = "system"
else:
raise ValueError("Received unsupported message type for Ollama.")
content = ""
images = []
if isinstance(message.content, str):
content = message.content
else:
for content_part in cast(List[Dict], message.content):
if content_part.get("type") == "text":
content += f"\n{content_part['text']}"
elif content_part.get("type") == "image_url":
if isinstance(content_part.get("image_url"), str):
image_url_components = content_part["image_url"].split(",")
# Support data:image/jpeg;base64,<image> format
# and base64 strings
if len(image_url_components) > 1:
images.append(image_url_components[1])
else:
images.append(image_url_components[0])
else:
raise ValueError(
"Only string image_url " "content parts are supported."
)
else:
raise ValueError(
"Unsupported message content type. "
"Must either have type 'text' or type 'image_url' "
"with a string 'image_url' field."
)
ollama_messages.append(
{
"role": role,
"content": content,
"images": images,
}
)
return ollama_messages
def _create_chat_stream(
self,
messages: List[BaseMessage],
stop: Optional[List[str]] = None,
**kwargs: Any,
) -> Iterator[str]:
payload = {
"model": self.model,
"messages": self._convert_messages_to_ollama_messages(messages),
}
yield from self._create_stream(
payload=payload, stop=stop, api_url=f"{self.base_url}/api/chat", **kwargs
)
async def _acreate_chat_stream(
self,
messages: List[BaseMessage],
stop: Optional[List[str]] = None,
**kwargs: Any,
) -> AsyncIterator[str]:
payload = {
"model": self.model,
"messages": self._convert_messages_to_ollama_messages(messages),
}
async for stream_resp in self._acreate_stream(
payload=payload, stop=stop, api_url=f"{self.base_url}/api/chat", **kwargs
):
yield stream_resp
def _chat_stream_with_aggregation(
self,
messages: List[BaseMessage],
stop: Optional[List[str]] = None,
run_manager: Optional[CallbackManagerForLLMRun] = None,
verbose: bool = False,
**kwargs: Any,
) -> ChatGenerationChunk:
final_chunk: Optional[ChatGenerationChunk] = None
for stream_resp in self._create_chat_stream(messages, stop, **kwargs):
if stream_resp:
chunk = _chat_stream_response_to_chat_generation_chunk(stream_resp)
if final_chunk is None:
final_chunk = chunk
else:
final_chunk += chunk
if run_manager:
run_manager.on_llm_new_token(
chunk.text,
chunk=chunk,
verbose=verbose,
)
if final_chunk is None:
raise ValueError("No data received from Ollama stream.")
return final_chunk
async def _achat_stream_with_aggregation(
self,
messages: List[BaseMessage],
stop: Optional[List[str]] = None,
run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
verbose: bool = False,
**kwargs: Any,
) -> ChatGenerationChunk:
final_chunk: Optional[ChatGenerationChunk] = None
async for stream_resp in self._acreate_chat_stream(messages, stop, **kwargs):
if stream_resp:
chunk = _chat_stream_response_to_chat_generation_chunk(stream_resp)
if final_chunk is None:
final_chunk = chunk
else:
final_chunk += chunk
if run_manager:
await run_manager.on_llm_new_token(
chunk.text,
chunk=chunk,
verbose=verbose,
)
if final_chunk is None:
raise ValueError("No data received from Ollama stream.")
return final_chunk
def _generate(
self,
messages: List[BaseMessage],
stop: Optional[List[str]] = None,
run_manager: Optional[CallbackManagerForLLMRun] = None,
**kwargs: Any,
) -> ChatResult:
"""Call out to Ollama's generate endpoint.
Args:
messages: The list of base messages to pass into the model.
stop: Optional list of stop words to use when generating.
Returns:
Chat generations from the model
Example:
.. code-block:: python
response = ollama([
HumanMessage(content="Tell me about the history of AI")
])
"""
final_chunk = self._chat_stream_with_aggregation(
messages,
stop=stop,
run_manager=run_manager,
verbose=self.verbose,
**kwargs,
)
chat_generation = ChatGeneration(
message=AIMessage(content=final_chunk.text),
generation_info=final_chunk.generation_info,
)
return ChatResult(generations=[chat_generation])
async def _agenerate(
self,
messages: List[BaseMessage],
stop: Optional[List[str]] = None,
run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
**kwargs: Any,
) -> ChatResult:
"""Call out to Ollama's generate endpoint.
Args:
messages: The list of base messages to pass into the model.
stop: Optional list of stop words to use when generating.
Returns:
Chat generations from the model
Example:
.. code-block:: python
response = ollama([
HumanMessage(content="Tell me about the history of AI")
])
"""
final_chunk = await self._achat_stream_with_aggregation(
messages,
stop=stop,
run_manager=run_manager,
verbose=self.verbose,
**kwargs,
)
chat_generation = ChatGeneration(
message=AIMessage(content=final_chunk.text),
generation_info=final_chunk.generation_info,
)
return ChatResult(generations=[chat_generation])
def _stream(
self,
messages: List[BaseMessage],
stop: Optional[List[str]] = None,
run_manager: Optional[CallbackManagerForLLMRun] = None,
**kwargs: Any,
) -> Iterator[ChatGenerationChunk]:
try:
for stream_resp in self._create_chat_stream(messages, stop, **kwargs):
if stream_resp:
chunk = _chat_stream_response_to_chat_generation_chunk(stream_resp)
if run_manager:
run_manager.on_llm_new_token(
chunk.text,
chunk=chunk,
verbose=self.verbose,
)
yield chunk
except OllamaEndpointNotFoundError:
yield from self._legacy_stream(messages, stop, **kwargs)
async def _astream(
self,
messages: List[BaseMessage],
stop: Optional[List[str]] = None,
run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
**kwargs: Any,
) -> AsyncIterator[ChatGenerationChunk]:
async for stream_resp in self._acreate_chat_stream(messages, stop, **kwargs):
if stream_resp:
chunk = _chat_stream_response_to_chat_generation_chunk(stream_resp)
if run_manager:
await run_manager.on_llm_new_token(
chunk.text,
chunk=chunk,
verbose=self.verbose,
)
yield chunk
@deprecated("0.0.3", alternative="_stream")
def _legacy_stream(
self,
messages: List[BaseMessage],
stop: Optional[List[str]] = None,
run_manager: Optional[CallbackManagerForLLMRun] = None,
**kwargs: Any,
) -> Iterator[ChatGenerationChunk]:
prompt = self._format_messages_as_text(messages)
for stream_resp in self._create_generate_stream(prompt, stop, **kwargs):
if stream_resp:
chunk = _stream_response_to_chat_generation_chunk(stream_resp)
if run_manager:
run_manager.on_llm_new_token(
chunk.text,
chunk=chunk,
verbose=self.verbose,
)
yield chunk
|