Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -14,22 +14,37 @@ history_max_len = 500 # 机器人记忆的最大长度
|
|
14 |
all_max_len = 2000 # 输入的最大长度
|
15 |
|
16 |
|
17 |
-
def get_text_emb(open_ai_key, text):
|
18 |
-
openai.api_key = open_ai_key
|
19 |
response = openai.Embedding.create(
|
20 |
input=text,
|
21 |
model="text-embedding-ada-002"
|
22 |
-
)
|
23 |
-
return response['data'][0]['embedding']
|
24 |
|
25 |
|
26 |
def doc_index_self(open_ai_key, doc): # 文档向量化
|
27 |
texts = doc.split('\n') # 按行切分
|
28 |
-
emb_list = []
|
29 |
-
for text in texts:
|
30 |
-
emb_list.append(get_text_emb(open_ai_key, text))
|
31 |
return texts, emb_list, gr.Textbox.update(visible=True), gr.Button.update(visible=True), gr.Markdown.update(
|
32 |
-
value="""操作说明 step 3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
|
34 |
|
35 |
def get_response_by_self(open_ai_key, msg, bot, doc_text_list, doc_embeddings): # 获取机器人回复
|
@@ -44,8 +59,8 @@ def get_response_by_self(open_ai_key, msg, bot, doc_text_list, doc_embeddings):
|
|
44 |
query_embedding = get_text_emb(open_ai_key, msg) # 获取输入的向量
|
45 |
cos_scores = [] # 用于存储相似度
|
46 |
|
47 |
-
def cos_sim(a, b):
|
48 |
-
return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))
|
49 |
|
50 |
for doc_embedding in doc_embeddings: # 遍历文档向量
|
51 |
cos_scores.append(cos_sim(query_embedding, doc_embedding)) # 计算相似度
|
@@ -111,7 +126,6 @@ def get_response_by_llama_index(open_ai_key, msg, bot, query_engine): # 获取
|
|
111 |
query_str += "机器人:" + his[1] + "\n" # 加入机器人的历史记录
|
112 |
query_str += "用户:" + msg + "\n" # 加入用户的当前输入
|
113 |
qa_template = Prompt(template) # 将模板转换成Prompt对象
|
114 |
-
query_engine = query_engine.as_query_engine(text_qa_template=qa_template) # 建立查询引擎
|
115 |
res = query_engine.query(msg) # 获取回答
|
116 |
print(res) # 显示回答
|
117 |
bot.append([msg, res]) # 加入历史记录
|
@@ -119,9 +133,9 @@ def get_response_by_llama_index(open_ai_key, msg, bot, query_engine): # 获取
|
|
119 |
|
120 |
|
121 |
def get_response(open_ai_key, msg, bot, doc_text_list, doc_embeddings, query_engine, index_type): # 获取机器人回复
|
122 |
-
if index_type == 1:
|
123 |
return get_response_by_self(open_ai_key, msg, bot, doc_text_list, doc_embeddings)
|
124 |
-
else:
|
125 |
return get_response_by_llama_index(open_ai_key, msg, bot, query_engine)
|
126 |
|
127 |
|
@@ -166,21 +180,6 @@ def up_file(files): # 上传文件
|
|
166 |
value="操作说明 step 2:确认PDF解析结果(可修正),点击“建立索引”,随后进行对话")
|
167 |
|
168 |
|
169 |
-
def doc_index_llama(open_ai_key, txt): # 建立索引
|
170 |
-
# 根据时间戳新建目录,保存txt文件
|
171 |
-
path = str(time.time())
|
172 |
-
import os
|
173 |
-
os.mkdir(path)
|
174 |
-
with open(path + '/doc.txt', mode='w', encoding='utf-8') as f:
|
175 |
-
f.write(txt)
|
176 |
-
openai.api_key = open_ai_key # 设置OpenAI API Key
|
177 |
-
documents = SimpleDirectoryReader(path).load_data() # 读取文档
|
178 |
-
index = GPTVectorStoreIndex.from_documents(documents) # 建立索引
|
179 |
-
query_engine = index.as_query_engine() # 建立查询引擎
|
180 |
-
return query_engine, gr.Textbox.update(visible=True), gr.Button.update(visible=True), gr.Markdown.update(
|
181 |
-
value="""操作说明 step 3:PDF解析提交成功! 🙋 可以开始对话啦~"""), gr.Chatbot.update(visible=True), 0
|
182 |
-
|
183 |
-
|
184 |
with gr.Blocks() as demo:
|
185 |
with gr.Row():
|
186 |
with gr.Column():
|
|
|
14 |
all_max_len = 2000 # 输入的最大长度
|
15 |
|
16 |
|
17 |
+
def get_text_emb(open_ai_key, text): # 文本向量化
|
18 |
+
openai.api_key = open_ai_key # 设置openai的key
|
19 |
response = openai.Embedding.create(
|
20 |
input=text,
|
21 |
model="text-embedding-ada-002"
|
22 |
+
) # 调用openai的api
|
23 |
+
return response['data'][0]['embedding'] # 返回向量
|
24 |
|
25 |
|
26 |
def doc_index_self(open_ai_key, doc): # 文档向量化
|
27 |
texts = doc.split('\n') # 按行切分
|
28 |
+
emb_list = [] # 用于存储向量
|
29 |
+
for text in texts: # 遍历每一行
|
30 |
+
emb_list.append(get_text_emb(open_ai_key, text)) # 获取向量
|
31 |
return texts, emb_list, gr.Textbox.update(visible=True), gr.Button.update(visible=True), gr.Markdown.update(
|
32 |
+
value="""操作说明 step 3:建立索引(by self)成功! 🙋 可以开始对话啦~"""), gr.Chatbot.update(visible=True), 1
|
33 |
+
|
34 |
+
|
35 |
+
def doc_index_llama(open_ai_key, txt): # 建立索引
|
36 |
+
# 根据时间戳新建目录,保存txt文件
|
37 |
+
path = str(time.time())
|
38 |
+
import os
|
39 |
+
os.mkdir(path)
|
40 |
+
with open(path + '/doc.txt', mode='w', encoding='utf-8') as f:
|
41 |
+
f.write(txt)
|
42 |
+
openai.api_key = open_ai_key # 设置OpenAI API Key
|
43 |
+
documents = SimpleDirectoryReader(path).load_data() # 读取文档
|
44 |
+
index = GPTVectorStoreIndex.from_documents(documents) # 建立索引
|
45 |
+
query_engine = index.as_query_engine() # 建立查询引擎
|
46 |
+
return query_engine, gr.Textbox.update(visible=True), gr.Button.update(visible=True), gr.Markdown.update(
|
47 |
+
value="""操作说明 step 3:建立索引(by llama_index)成功! 🙋 可以开始对话啦~"""), gr.Chatbot.update(visible=True), 0
|
48 |
|
49 |
|
50 |
def get_response_by_self(open_ai_key, msg, bot, doc_text_list, doc_embeddings): # 获取机器人回复
|
|
|
59 |
query_embedding = get_text_emb(open_ai_key, msg) # 获取输入的向量
|
60 |
cos_scores = [] # 用于存储相似度
|
61 |
|
62 |
+
def cos_sim(a, b): # 计算余弦相似度
|
63 |
+
return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b)) # 返回相似度
|
64 |
|
65 |
for doc_embedding in doc_embeddings: # 遍历文档向量
|
66 |
cos_scores.append(cos_sim(query_embedding, doc_embedding)) # 计算相似度
|
|
|
126 |
query_str += "机器人:" + his[1] + "\n" # 加入机器人的历史记录
|
127 |
query_str += "用户:" + msg + "\n" # 加入用户的当前输入
|
128 |
qa_template = Prompt(template) # 将模板转换成Prompt对象
|
|
|
129 |
res = query_engine.query(msg) # 获取回答
|
130 |
print(res) # 显示回答
|
131 |
bot.append([msg, res]) # 加入历史记录
|
|
|
133 |
|
134 |
|
135 |
def get_response(open_ai_key, msg, bot, doc_text_list, doc_embeddings, query_engine, index_type): # 获取机器人回复
|
136 |
+
if index_type == 1: # 如果是使用自己的索引
|
137 |
return get_response_by_self(open_ai_key, msg, bot, doc_text_list, doc_embeddings)
|
138 |
+
else: # 如果是使用llama_index索引
|
139 |
return get_response_by_llama_index(open_ai_key, msg, bot, query_engine)
|
140 |
|
141 |
|
|
|
180 |
value="操作说明 step 2:确认PDF解析结果(可修正),点击“建立索引”,随后进行对话")
|
181 |
|
182 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
183 |
with gr.Blocks() as demo:
|
184 |
with gr.Row():
|
185 |
with gr.Column():
|