Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -19,13 +19,64 @@ from agent import (
|
|
19 |
)
|
20 |
api=HfApi()
|
21 |
|
22 |
-
|
23 |
-
|
24 |
client = InferenceClient(
|
25 |
"mistralai/Mixtral-8x7B-Instruct-v0.1"
|
26 |
)
|
27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
|
|
|
|
|
|
|
|
|
29 |
|
30 |
def read_txt(txt_path):
|
31 |
text=""
|
@@ -154,13 +205,18 @@ def compress_data(c, instruct, history):
|
|
154 |
|
155 |
|
156 |
|
157 |
-
def summarize(inp,history,data=None,file=None):
|
158 |
if inp == "":
|
159 |
inp = "Process this data"
|
160 |
-
|
161 |
-
|
162 |
history = [(inp,"Working on it...")] if not history else history
|
163 |
yield "",history
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
164 |
if file:
|
165 |
try:
|
166 |
print (file)
|
|
|
19 |
)
|
20 |
api=HfApi()
|
21 |
|
|
|
|
|
22 |
client = InferenceClient(
|
23 |
"mistralai/Mixtral-8x7B-Instruct-v0.1"
|
24 |
)
|
25 |
|
26 |
+
def find_all(url):
|
27 |
+
return_list=[]
|
28 |
+
print (url)
|
29 |
+
#if action_input in query.tasks:
|
30 |
+
print (f"trying URL:: {url}")
|
31 |
+
try:
|
32 |
+
if url != "" and url != None:
|
33 |
+
out = []
|
34 |
+
source = requests.get(url)
|
35 |
+
#source = urllib.request.urlopen(url).read()
|
36 |
+
soup = bs4.BeautifulSoup(source.content,'lxml')
|
37 |
+
# title of the page
|
38 |
+
print(soup.title)
|
39 |
+
# get attributes:
|
40 |
+
print(soup.title.name)
|
41 |
+
# get values:
|
42 |
+
print(soup.title.string)
|
43 |
+
# beginning navigation:
|
44 |
+
print(soup.title.parent.name)
|
45 |
+
#rawp.append([tag.name for tag in soup.find_all()] )
|
46 |
+
print([tag.name for tag in soup.find_all()])
|
47 |
+
rawp=(f'RAW TEXT RETURNED: {soup.text}')
|
48 |
+
out.append(rawp)
|
49 |
+
q=("a","p","span","content","article")
|
50 |
+
for p in soup.find_all(q):
|
51 |
+
out.append([{q:p.string,"parent":p.parent.name,"previous":[b for b in p.previous],"first-child":[b.name for b in p.children],"content":p}])
|
52 |
+
print (f'OUT :: {out}')
|
53 |
+
'''
|
54 |
+
c=0
|
55 |
+
out = str(out)
|
56 |
+
rl = len(out)
|
57 |
+
print(f'rl:: {rl}')
|
58 |
+
#for ea in out:
|
59 |
+
for i in str(out):
|
60 |
+
if i == " " or i=="," or i=="\n":
|
61 |
+
c +=1
|
62 |
+
print (f'c:: {c}')
|
63 |
+
if rl > MAX_DATA:
|
64 |
+
print("compressing...")
|
65 |
+
rawp = compress_data(c,purpose,task,out)
|
66 |
+
print (rawp)
|
67 |
+
print (f'out:: {out}')
|
68 |
+
'''
|
69 |
+
return True, rawp
|
70 |
+
else:
|
71 |
+
return False, "Enter Valid URL"
|
72 |
+
except Exception as e:
|
73 |
+
print (e)
|
74 |
+
return False, f'Error: {e}'
|
75 |
|
76 |
+
#else:
|
77 |
+
# history = "observation: The search query I used did not return a valid response"
|
78 |
+
|
79 |
+
return "MAIN", None, history, task
|
80 |
|
81 |
def read_txt(txt_path):
|
82 |
text=""
|
|
|
205 |
|
206 |
|
207 |
|
208 |
+
def summarize(inp,history,data=None,file=None,url=None):
|
209 |
if inp == "":
|
210 |
inp = "Process this data"
|
|
|
|
|
211 |
history = [(inp,"Working on it...")] if not history else history
|
212 |
yield "",history
|
213 |
+
if url != "":
|
214 |
+
val, out = find_all(url)
|
215 |
+
if not val:
|
216 |
+
data="Error"
|
217 |
+
rawp = out
|
218 |
+
else:
|
219 |
+
rawp=out
|
220 |
if file:
|
221 |
try:
|
222 |
print (file)
|