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 | class SimpleChatEngine(BaseChatEngine):
"""Simple Chat Engine.
Have a conversation with the LLM.
This does not make use of a knowledge base.
"""
def __init__(
self,
llm: LLM,
memory: BaseMemory,
prefix_messages: List[ChatMessage],
callback_manager: Optional[CallbackManager] = None,
) -> None:
self._llm = llm
self._memory = memory
self._prefix_messages = prefix_messages
self.callback_manager = callback_manager or CallbackManager([])
@classmethod
def from_defaults(
cls,
chat_history: Optional[List[ChatMessage]] = None,
memory: Optional[BaseMemory] = None,
memory_cls: Type[BaseMemory] = ChatMemoryBuffer,
system_prompt: Optional[str] = None,
prefix_messages: Optional[List[ChatMessage]] = None,
llm: Optional[LLM] = None,
# deprecated
service_context: Optional[ServiceContext] = None,
**kwargs: Any,
) -> "SimpleChatEngine":
"""Initialize a SimpleChatEngine from default parameters."""
llm = llm or llm_from_settings_or_context(Settings, service_context)
chat_history = chat_history or []
memory = memory or memory_cls.from_defaults(chat_history=chat_history, llm=llm)
if system_prompt is not None:
if prefix_messages is not None:
raise ValueError(
"Cannot specify both system_prompt and prefix_messages"
)
prefix_messages = [
ChatMessage(content=system_prompt, role=llm.metadata.system_role)
]
prefix_messages = prefix_messages or []
return cls(
llm=llm,
memory=memory,
prefix_messages=prefix_messages,
callback_manager=callback_manager_from_settings_or_context(
Settings, service_context
),
)
@trace_method("chat")
def chat(
self, message: str, chat_history: Optional[List[ChatMessage]] = None
) -> AgentChatResponse:
if chat_history is not None:
self._memory.set(chat_history)
self._memory.put(ChatMessage(content=message, role="user"))
initial_token_count = len(
self._memory.tokenizer_fn(
" ".join([(m.content or "") for m in self._prefix_messages])
)
)
all_messages = self._prefix_messages + self._memory.get(
initial_token_count=initial_token_count
)
chat_response = self._llm.chat(all_messages)
ai_message = chat_response.message
self._memory.put(ai_message)
return AgentChatResponse(response=str(chat_response.message.content))
@trace_method("chat")
def stream_chat(
self, message: str, chat_history: Optional[List[ChatMessage]] = None
) -> StreamingAgentChatResponse:
if chat_history is not None:
self._memory.set(chat_history)
self._memory.put(ChatMessage(content=message, role="user"))
initial_token_count = len(
self._memory.tokenizer_fn(
" ".join([(m.content or "") for m in self._prefix_messages])
)
)
all_messages = self._prefix_messages + self._memory.get(
initial_token_count=initial_token_count
)
chat_response = StreamingAgentChatResponse(
chat_stream=self._llm.stream_chat(all_messages)
)
thread = Thread(
target=chat_response.write_response_to_history, args=(self._memory,)
)
thread.start()
return chat_response
@trace_method("chat")
async def achat(
self, message: str, chat_history: Optional[List[ChatMessage]] = None
) -> AgentChatResponse:
if chat_history is not None:
self._memory.set(chat_history)
self._memory.put(ChatMessage(content=message, role="user"))
initial_token_count = len(
self._memory.tokenizer_fn(
" ".join([(m.content or "") for m in self._prefix_messages])
)
)
all_messages = self._prefix_messages + self._memory.get(
initial_token_count=initial_token_count
)
chat_response = await self._llm.achat(all_messages)
ai_message = chat_response.message
self._memory.put(ai_message)
return AgentChatResponse(response=str(chat_response.message.content))
@trace_method("chat")
async def astream_chat(
self, message: str, chat_history: Optional[List[ChatMessage]] = None
) -> StreamingAgentChatResponse:
if chat_history is not None:
self._memory.set(chat_history)
self._memory.put(ChatMessage(content=message, role="user"))
initial_token_count = len(
self._memory.tokenizer_fn(
" ".join([(m.content or "") for m in self._prefix_messages])
)
)
all_messages = self._prefix_messages + self._memory.get(
initial_token_count=initial_token_count
)
chat_response = StreamingAgentChatResponse(
achat_stream=await self._llm.astream_chat(all_messages)
)
thread = Thread(
target=lambda x: asyncio.run(chat_response.awrite_response_to_history(x)),
args=(self._memory,),
)
thread.start()
return chat_response
def reset(self) -> None:
self._memory.reset()
@property
def chat_history(self) -> List[ChatMessage]:
"""Get chat history."""
return self._memory.get_all()
|