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 | class Generation(BaseSynthesizer):
def __init__(
self,
llm: Optional[LLM] = None,
callback_manager: Optional[CallbackManager] = None,
prompt_helper: Optional[PromptHelper] = None,
simple_template: Optional[BasePromptTemplate] = None,
streaming: bool = False,
) -> None:
super().__init__(
llm=llm,
callback_manager=callback_manager,
prompt_helper=prompt_helper,
streaming=streaming,
)
self._input_prompt = simple_template or DEFAULT_SIMPLE_INPUT_PROMPT
def _get_prompts(self) -> PromptDictType:
"""Get prompts."""
return {"simple_template": self._input_prompt}
def _update_prompts(self, prompts: PromptDictType) -> None:
"""Update prompts."""
if "simple_template" in prompts:
self._input_prompt = prompts["simple_template"]
async def aget_response(
self,
query_str: str,
text_chunks: Sequence[str],
**response_kwargs: Any,
) -> RESPONSE_TEXT_TYPE:
# NOTE: ignore text chunks and previous response
del text_chunks
if not self._streaming:
return await self._llm.apredict(
self._input_prompt,
query_str=query_str,
**response_kwargs,
)
else:
return await self._llm.astream(
self._input_prompt,
query_str=query_str,
**response_kwargs,
)
def get_response(
self,
query_str: str,
text_chunks: Sequence[str],
**response_kwargs: Any,
) -> RESPONSE_TEXT_TYPE:
# NOTE: ignore text chunks and previous response
del text_chunks
if not self._streaming:
return self._llm.predict(
self._input_prompt,
query_str=query_str,
**response_kwargs,
)
else:
return self._llm.stream(
self._input_prompt,
query_str=query_str,
**response_kwargs,
)
# NOTE: synthesize and asynthesize are copied from the base class,
# but modified to return when zero nodes are provided
@dispatcher.span
def synthesize(
self,
query: QueryType,
nodes: List[NodeWithScore],
additional_source_nodes: Optional[Sequence[NodeWithScore]] = None,
**response_kwargs: Any,
) -> RESPONSE_TYPE:
dispatcher.event(
SynthesizeStartEvent(
query=query,
)
)
if isinstance(query, str):
query = QueryBundle(query_str=query)
with self._callback_manager.event(
CBEventType.SYNTHESIZE,
payload={EventPayload.QUERY_STR: query.query_str},
) as event:
response_str = self.get_response(
query_str=query.query_str,
text_chunks=[
n.node.get_content(metadata_mode=MetadataMode.LLM) for n in nodes
],
**response_kwargs,
)
additional_source_nodes = additional_source_nodes or []
source_nodes = list(nodes) + list(additional_source_nodes)
response = self._prepare_response_output(response_str, source_nodes)
event.on_end(payload={EventPayload.RESPONSE: response})
dispatcher.event(
SynthesizeEndEvent(
query=query,
response=response,
)
)
return response
@dispatcher.span
async def asynthesize(
self,
query: QueryType,
nodes: List[NodeWithScore],
additional_source_nodes: Optional[Sequence[NodeWithScore]] = None,
**response_kwargs: Any,
) -> RESPONSE_TYPE:
dispatcher.event(
SynthesizeStartEvent(
query=query,
)
)
if isinstance(query, str):
query = QueryBundle(query_str=query)
with self._callback_manager.event(
CBEventType.SYNTHESIZE,
payload={EventPayload.QUERY_STR: query.query_str},
) as event:
response_str = await self.aget_response(
query_str=query.query_str,
text_chunks=[
n.node.get_content(metadata_mode=MetadataMode.LLM) for n in nodes
],
**response_kwargs,
)
additional_source_nodes = additional_source_nodes or []
source_nodes = list(nodes) + list(additional_source_nodes)
response = self._prepare_response_output(response_str, source_nodes)
event.on_end(payload={EventPayload.RESPONSE: response})
dispatcher.event(
SynthesizeEndEvent(
query=query,
response=response,
)
)
return response
|
