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 | class DenseXRetrievalPack(BaseLlamaPack):
def __init__(
self,
documents: List[Document],
proposition_llm: Optional[LLM] = None,
query_llm: Optional[LLM] = None,
embed_model: Optional[BaseEmbedding] = None,
text_splitter: TextSplitter = SentenceSplitter(),
similarity_top_k: int = 4,
streaming: bool = False,
) -> None:
"""初始化参数。"""
self._proposition_llm = proposition_llm or OpenAI(
model="gpt-3.5-turbo",
temperature=0.1,
max_tokens=750,
)
embed_model = embed_model or OpenAIEmbedding(embed_batch_size=128)
nodes = text_splitter.get_nodes_from_documents(documents)
sub_nodes = self._gen_propositions(nodes)
all_nodes = nodes + sub_nodes
all_nodes_dict = {n.node_id: n for n in all_nodes}
service_context = ServiceContext.from_defaults(
llm=query_llm or OpenAI(),
embed_model=embed_model,
num_output=self._proposition_llm.metadata.num_output,
)
self.vector_index = VectorStoreIndex(
all_nodes, service_context=service_context, show_progress=True
)
self.retriever = RecursiveRetriever(
"vector",
retriever_dict={
"vector": self.vector_index.as_retriever(
similarity_top_k=similarity_top_k
)
},
node_dict=all_nodes_dict,
)
self.query_engine = RetrieverQueryEngine.from_args(
self.retriever,
service_context=service_context,
streaming=streaming,
)
async def _aget_proposition(self, node: TextNode) -> List[TextNode]:
"""获取命题。"""
inital_output = await self._proposition_llm.apredict(
PROPOSITIONS_PROMPT, node_text=node.text
)
outputs = inital_output.split("\n")
all_propositions = []
for output in outputs:
if not output.strip():
continue
if not output.strip().endswith("]"):
if not output.strip().endswith('"') and not output.strip().endswith(
","
):
output = output + '"'
output = output + " ]"
if not output.strip().startswith("["):
if not output.strip().startswith('"'):
output = '"' + output
output = "[ " + output
try:
propositions = json.loads(output)
except Exception:
# fallback to yaml
try:
propositions = yaml.safe_load(output)
except Exception:
# fallback to next output
continue
if not isinstance(propositions, list):
continue
all_propositions.extend(propositions)
assert isinstance(all_propositions, list)
nodes = [TextNode(text=prop) for prop in all_propositions if prop]
return [IndexNode.from_text_node(n, node.node_id) for n in nodes]
def _gen_propositions(self, nodes: List[TextNode]) -> List[TextNode]:
"""获取命题。"""
sub_nodes = asyncio.run(
run_jobs(
[self._aget_proposition(node) for node in nodes],
show_progress=True,
workers=8,
)
)
# Flatten list
return [node for sub_node in sub_nodes for node in sub_node]
def get_modules(self) -> Dict[str, Any]:
"""获取模块。"""
return {
"query_engine": self.query_engine,
"retriever": self.retriever,
}
def run(self, query_str: str, **kwargs: Any) -> RESPONSE_TYPE:
"""运行流水线。"""
return self.query_engine.query(query_str)
|