文章目录
上下文关联
上下文关联相关参数:
- 知识相关度阈值score_threshold
- 内容条数k
- 是否启用上下文关联chunk_conent
- 上下文最大长度chunk_size
其主要作用是在所在文档中扩展与当前query相似度较高的知识库的内容,作为相关信息与query按照prompt规则组合后作为输入获得模型的回答。
- 获取查询句query嵌入:
faiss.py
py
def similarity_search_with_score(
self, query: str, k: int = 4
) -> List[Tuple[Document, float]]:
"""Return docs most similar to query.
Args:
query: Text to look up documents similar to.
k: Number of Documents to return. Defaults to 4.
Returns:
List of Documents most similar to the query and score for each
"""
embedding = self.embedding_function(query)
docs = self.similarity_search_with_score_by_vector(embedding, k)
return docs
- 上下文生成:
MyFAISS.py
py
def seperate_list(self, ls: List[int]) -> List[List[int]]:
# TODO: 增加是否属于同一文档的判断
lists = []
ls1 = [ls[0]]
for i in range(1, len(ls)):
if ls[i - 1] + 1 == ls[i]:
ls1.append(ls[i])
else:
lists.append(ls1)
ls1 = [ls[i]]
lists.append(ls1)
return lists
def similarity_search_with_score_by_vector(
self, embedding: List[float], k: int = 4
) -> List[Document]:
faiss = dependable_faiss_import()
# (1,1024)
vector = np.array([embedding], dtype=np.float32)
# 默认FALSE
if self._normalize_L2:
faiss.normalize_L2(vector)
# shape均为(1, k),这步获取与query有top-k相似度的知识库
scores, indices = self.index.search(vector, k)
docs = []
id_set = set()
store_len = len(self.index_to_docstore_id)
rearrange_id_list = False
# 遍历找到的k个最相似知识库的索引
# k是第一次的筛选条件,score是第二次的筛选条件
for j, i in enumerate(indices[0]):
if i == -1 or 0 < self.score_threshold < scores[0][j]:
# This happens when not enough docs are returned.
continue
if i in self.index_to_docstore_id:
_id = self.index_to_docstore_id[i]
# 执行接下来的操作
else:
continue
# index→id→content
doc = self.docstore.search(_id)
if (not self.chunk_conent) or ("context_expand" in doc.metadata and not doc.metadata["context_expand"]):
# 匹配出的文本如果不需要扩展上下文则执行如下代码
if not isinstance(doc, Document):
raise ValueError(f"Could not find document for id {_id}, got {doc}")
doc.metadata["score"] = int(scores[0][j])
docs.append(doc)
continue
# 其实存的都是index
id_set.add(i)
docs_len = len(doc.page_content)
# 跟外部变量定义的k重名了,烂
# 一个知识库是分句后得到的一句话,i是当前知识库在总知识库中的位置,store_len是总知识库大小
# 所以k说的是扩充上下文时最多能跨多少个知识库
for k in range(1, max(i, store_len - i)):
break_flag = False
if "context_expand_method" in doc.metadata and doc.metadata["context_expand_method"] == "forward":
expand_range = [i + k]
elif "context_expand_method" in doc.metadata and doc.metadata["context_expand_method"] == "backward":
expand_range = [i - k]
else:
# i=4922, k=1 → [4923, 4921]
expand_range = [i + k, i - k]
for l in expand_range:
# 确保扩展上下文时不会造成重复
if l not in id_set and 0 <= l < len(self.index_to_docstore_id):
_id0 = self.index_to_docstore_id[l]
doc0 = self.docstore.search(_id0)
# 如果当前字数大于250或者是知识库跨了文件,扩充上下文过程终止
# 这一句有些问题,有一端跨文件就终止,应该是两端同时跨才终止才对
if docs_len + len(doc0.page_content) > self.chunk_size or doc0.metadata["source"] != \
doc.metadata["source"]:
break_flag = True
break
elif doc0.metadata["source"] == doc.metadata["source"]:
docs_len += len(doc0.page_content)
id_set.add(l)
rearrange_id_list = True
if break_flag:
break
# 如果没有扩展上下文(不需要或是不能)
if (not self.chunk_conent) or (not rearrange_id_list):
return docs
if len(id_set) == 0 and self.score_threshold > 0:
return []
id_list = sorted(list(id_set))
# 连续必然属于同一文档,但不连续也可能在同一文档
# 返回二级列表,第一级是连续的index列表,第二级是具体index
id_lists = self.seperate_list(id_list)
for id_seq in id_lists:
for id in id_seq:
if id == id_seq[0]:
_id = self.index_to_docstore_id[id]
# doc = self.docstore.search(_id)
doc = copy.deepcopy(self.docstore.search(_id))
else:
_id0 = self.index_to_docstore_id[id]
doc0 = self.docstore.search(_id0)
doc.page_content += " " + doc0.page_content
if not isinstance(doc, Document):
raise ValueError(f"Could not find document for id {_id}, got {doc}")
# indices为相关文件的索引
# 因为可能会将多个连续的id合并,因此需要将同一seq内所有位于top-k的知识库的分数取最小值作为seq对应的分数
doc_score = min([scores[0][id] for id in [indices[0].tolist().index(i) for i in id_seq if i in indices[0]]])
doc.metadata["score"] = int(doc_score)
docs.append(doc)
# 注意这里docs没有按相似度排序,可以自行加个sort
return docs
- prompt生成:
local_doc_qa.py
py
def get_knowledge_based_answer(self, query, vs_path, chat_history=[], streaming: bool = STREAMING):
related_docs_with_score = vector_store.similarity_search_with_score(query, k=self.top_k)
torch_gc()
if len(related_docs_with_score) > 0:
prompt = generate_prompt(related_docs_with_score, query)
else:
prompt = query
answer_result_stream_result = self.llm_model_chain(
{"prompt": prompt, "history": chat_history, "streaming": streaming})
def generate_prompt(related_docs: List[str],
query: str,
prompt_template: str = PROMPT_TEMPLATE, ) -> str:
context = "\n".join([doc.page_content for doc in related_docs])
prompt = prompt_template.replace("{question}", query).replace("{context}", context)
return prompt
对话轮数
其实就是要存多少历史记录,如果为0的话就是在执行当前对话时不考虑历史问答
- 模型内部调用时使用,以chatglm为例:
chatglm_llm.py
py
def _generate_answer(self,
inputs: Dict[str, Any],
run_manager: Optional[CallbackManagerForChainRun] = None,
generate_with_callback: AnswerResultStream = None) -> None:
history = inputs[self.history_key]
streaming = inputs[self.streaming_key]
prompt = inputs[self.prompt_key]
print(f"__call:{prompt}")
# Create the StoppingCriteriaList with the stopping strings
stopping_criteria_list = transformers.StoppingCriteriaList()
# 定义模型stopping_criteria 队列,在每次响应时将 torch.LongTensor, torch.FloatTensor同步到AnswerResult
listenerQueue = AnswerResultQueueSentinelTokenListenerQueue()
stopping_criteria_list.append(listenerQueue)
if streaming:
history += [[]]
for inum, (stream_resp, _) in enumerate(self.checkPoint.model.stream_chat(
self.checkPoint.tokenizer,
prompt,
# 为0时history返回[]
history=history[-self.history_len:-1] if self.history_len > 0 else [],
max_length=self.max_token,
temperature=self.temperature,
top_p=self.top_p,
top_k=self.top_k,
stopping_criteria=stopping_criteria_list
)):
向量匹配 top k
虽然放在了模型配置那一页,但实际上还是用来控制上下文关联里面的内容条数k的,不知道为什么写了两遍。。。
控制生成质量的参数
这些参数没有在前端显式地给出,而是写死在了模型定义里
- 模型定义,以chatglm为例:
chatglm_llm.py
py
class ChatGLMLLMChain(BaseAnswer, Chain, ABC):
max_token: int = 10000
temperature: float = 0.01
# 相关度
top_p = 0.4
# 候选词数量
top_k = 10
checkPoint: LoaderCheckPoint = None
# history = []
history_len: int = 10
参数设置心得
- score_threshold和k设太小会找不到问题对应的原文件,太大找到一堆不相关的
- chunk_size设太小不能在原文件里找到问题对应的原文,太大无法有效归纳出答案
- temperature和top_p默认值下生成的答案基本固定,但也很死板;过大的temperature导致回答的事实不稳定;过大的top_p导致回答的语言风格不稳定;调整top_k没发现结果有什么变化