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 | class SimpleSummarize(BaseSynthesizer):
def __init__(
self,
llm: Optional[LLMPredictorType] = None,
callback_manager: Optional[CallbackManager] = None,
prompt_helper: Optional[PromptHelper] = None,
text_qa_template: Optional[BasePromptTemplate] = None,
streaming: bool = False,
# deprecated
service_context: Optional[ServiceContext] = None,
) -> None:
if service_context is not None:
prompt_helper = service_context.prompt_helper
super().__init__(
llm=llm,
callback_manager=callback_manager,
prompt_helper=prompt_helper,
service_context=service_context,
streaming=streaming,
)
self._text_qa_template = text_qa_template or DEFAULT_TEXT_QA_PROMPT_SEL
def _get_prompts(self) -> PromptDictType:
"""Get prompts."""
return {"text_qa_template": self._text_qa_template}
def _update_prompts(self, prompts: PromptDictType) -> None:
"""Update prompts."""
if "text_qa_template" in prompts:
self._text_qa_template = prompts["text_qa_template"]
async def aget_response(
self,
query_str: str,
text_chunks: Sequence[str],
**response_kwargs: Any,
) -> RESPONSE_TEXT_TYPE:
text_qa_template = self._text_qa_template.partial_format(query_str=query_str)
single_text_chunk = "\n".join(text_chunks)
truncated_chunks = self._prompt_helper.truncate(
prompt=text_qa_template,
text_chunks=[single_text_chunk],
)
response: RESPONSE_TEXT_TYPE
if not self._streaming:
response = await self._llm.apredict(
text_qa_template,
context_str=truncated_chunks,
**response_kwargs,
)
else:
response = self._llm.stream(
text_qa_template,
context_str=truncated_chunks,
**response_kwargs,
)
if isinstance(response, str):
response = response or "Empty Response"
else:
response = cast(Generator, response)
return response
def get_response(
self,
query_str: str,
text_chunks: Sequence[str],
**kwargs: Any,
) -> RESPONSE_TEXT_TYPE:
text_qa_template = self._text_qa_template.partial_format(query_str=query_str)
single_text_chunk = "\n".join(text_chunks)
truncated_chunks = self._prompt_helper.truncate(
prompt=text_qa_template,
text_chunks=[single_text_chunk],
)
response: RESPONSE_TEXT_TYPE
if not self._streaming:
response = self._llm.predict(
text_qa_template,
context_str=truncated_chunks,
**kwargs,
)
else:
response = self._llm.stream(
text_qa_template,
context_str=truncated_chunks,
**kwargs,
)
if isinstance(response, str):
response = response or "Empty Response"
else:
response = cast(Generator, response)
return response
|