文本分隔 可能存在的问题

• 粒度太大可能导致检索不精准
• 粒度太小可能导致信息不全面
• 问题的答案可能跨越两个片段

# 创建一个向量数据库对象
vector_db = MyVectorDBConnector("demo_text_split", get_embeddings)
# 向向量数据库中添加文档
vector_db.add_documents(paragraphs)

# 创建一个RAG机器人
bot = RAG_Bot(
    vector_db,
    llm_api=get_completion
)
#%%
# user_query = "llama 2有商用许可协议吗"
user_query="llama 2 chat有多少参数"
search_results = vector_db.search(user_query, 2)

for doc in search_results['documents'][0]:
    print(doc+"\n")

print("====回复====")
bot.chat(user_query)


====回复====
llama 2 chat有70B个参数。'

改进: 按一定粒度，部分重叠式的切割文本，使上下文更完整

from nltk.tokenize import sent_tokenize
import json


def split_text(paragraphs, chunk_size=300, overlap_size=100):
    '''按指定 chunk_size 和 overlap_size 交叠割文本'''
    sentences = [s.strip() for p in paragraphs for s in sent_tokenize(p)]
    chunks = []
    i = 0
    while i < len(sentences):
        chunk = sentences[i]
        overlap = ''
        prev_len = 0
        prev = i - 1
        # 向前计算重叠部分
        while prev >= 0 and len(sentences[prev])+len(overlap) <= overlap_size:
            overlap = sentences[prev] + ' ' + overlap
            prev -= 1
        chunk = overlap+chunk
        next = i + 1
        # 向后计算当前chunk
        while next < len(sentences) and len(sentences[next])+len(chunk) <= chunk_size:
            chunk = chunk + ' ' + sentences[next]
            next += 1
        chunks.append(chunk)
        i = next
    return chunks

此处 sent_tokenize 为针对英文的实现，针对中文的实现参考 chinese_utils.py

chunks = split_text(paragraphs, 300, 100)


#%%
# 创建一个向量数据库对象
vector_db = MyVectorDBConnector("demo_text_split", get_embeddings)
# 向向量数据库中添加文档
vector_db.add_documents(chunks)
# 创建一个RAG机器人
bot = RAG_Bot(
    vector_db,
    llm_api=get_completion
)
#%%
# user_query = "llama 2有商用许可协议吗"
user_query="llama 2 chat有多少参数"

search_results = vector_db.search(user_query, 2)
for doc in search_results['documents'][0]:
    print(doc+"\n")

response = bot.chat(user_query)
print("====回复====")
print(response)

====回复====
llama 2 chat有7B, 13B和70B参数。