|
|
@@ -240,3 +240,34 @@ This technique was mainly implemented in the [the Self-Refine: Iterative Refinem
|
|
|
For more detailed usage and code examples check `./examples`.
|
|
|
|
|
|
|
|
|
+## 源码分析
|
|
|
+
|
|
|
+上下文记忆功能：
|
|
|
+
|
|
|
+上下文记忆其实就是每次提问都把之前的问题作为一个list，重复发给openai接口，ThinkGPT 提供记忆函数 llm.remember() ，具体实现如下：
|
|
|
+
|
|
|
+```
|
|
|
+ def remember(self, concept: Union[str, Document] = None, limit: int = 5, sort_by_order: bool = False, max_tokens: Optional[int] = None) -> List[str]:
|
|
|
+ if len(self.memory) == 0:
|
|
|
+ return []
|
|
|
+ if concept is None:
|
|
|
+ return [doc.text for doc in self.memory[-limit:]]
|
|
|
+ elif isinstance(concept, str):
|
|
|
+ query_input = Document(embedding=np.asarray(self.embeddings_model.embed_query(concept)))
|
|
|
+ elif isinstance(concept, Document):
|
|
|
+ assert concept.embedding is not None
|
|
|
+ query_input = concept
|
|
|
+ else:
|
|
|
+ raise ValueError('wrong type, must be either str or Document')
|
|
|
+
|
|
|
+ docs = self.memory.find(query_input, limit=limit)[0]
|
|
|
+ # memory needs to be sorted in chronological order
|
|
|
+ if sort_by_order:
|
|
|
+ docs = sorted(docs, key=lambda doc: doc.tags['mem_cnt'])
|
|
|
+ text_results = [doc.text for doc in docs]
|
|
|
+ if max_tokens:
|
|
|
+ text_results = fit_context(text_results, max_tokens)
|
|
|
+ return text_results
|
|
|
+
|
|
|
+```
|
|
|
+上面函数就是对 embeddings_model 处理，把 concept 加入，排序，标准化（不能超过最大tokens）等。
|
