senaduka/old-svevijesti
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Removing previous f.

Browse Source
This commit is contained in:
Amir Sabani
2024-01-06 08:26:31 +01:00
parent d4e99c7c5f
commit 96a2d88895
1 changed files with 0 additions and 112 deletions
Download Patch File Download Diff File Expand all files Collapse all files

112
pyth/scrapingsingle.py
View File

@@ -155,115 +155,3 @@ if __name__ == '__main__':
print(f"Error in completion: {e}") print(f"Error in completion: {e}")
continue continue
def comb_similar():
print("Checking similar")
similar_article = get_similar()
grouped_data = {}
for sa in similar_article:
if similar_article:
first_t = get_specific_data(sa[0])
second_t = get_specific_data(sa[1])
link_f = first_t[0][2]
link_s = second_t[0][2]
f_text = first_t[0][1]
s_text = second_t[0][1]
f_title = first_t[0][0]
s_title = second_t[0][0]
if f_title in grouped_data:
grouped_data[f_title].append((f_text, link_f))
else:
grouped_data[f_title] = [(f_text, link_f)]
if s_title in grouped_data:
grouped_data[s_title].append((s_text, link_s))
else:
grouped_data[s_title] = [(s_text, link_s)]
for title, tuples in grouped_data.items():
if len(tuples) == 3:
text1, link1 = tuples[0]
text2, link2 = tuples[1]
text3, link3 = tuples[2]
t1check = num_tokens_from_string(text1)
t2check = num_tokens_from_string(text2)
t3check = num_tokens_from_string(text3)
slice_if_more = t1check,t2check,t3check
if slice_if_more < 2000:
combined_text = f"{text1}{text2}{text3}"
combined_text = slice_text_at_2k_tokens(combined_text)
user_message = rf"Here is text {combined_text}, combined from 3 sources, filter text, and make news content, return as JSON only with 'content' field"
if link1 != link2 and link1 != link3 and link2 != link3:
link = f"{link1} {link2} {link3}"
else:
link = link1
else:
user_message = rf"Here are 3 texts {text1} {text2} and {text3}, combine the following texts into a cohesive news remove any non-news related to both texts and provide the cleaned data as a JSON only with 'content' field."
if link1 != link2 and link1 != link3 and link2 != link3:
link = f"{link1} {link2} {link3}"
else:
link = link1
else:
ftcheck = num_tokens_from_string(f_text)
stcheck = num_tokens_from_string(s_text)
fscomb = ftcheck + stcheck
if fscomb <2000:
combined_text = f"{f_text}{s_text}"
user_message = rf"Here is text {combined_text}, combined from 2 sources, filter text, and make news content, return as JSON only with 'content' field"
if link_f != link_s:
link = f"{link_f} {link_s}"
else:
link = link_f
else:
user_message = rf"Here are 2 texts {f_text} and {s_text}, combine the following texts into a cohesive news remove any non-news related to both texts and provide the cleaned data as a JSON only with 'content' field."
if link_f != link_s:
link = f"{link_f} {link_s}"
else:
link = link_f
try:
completion = client.chat.completions.create(
model="gpt-3.5-turbo",
messages=[
{"role": "system", "content": "Data analytic, Journalist and News reporter"},
{"role": "user", "content": user_message}
]
)
generated_text = completion.choices[0].message.content
if similar_article:
if f_title == s_title:
print(f_title)
modify_similar_data(first_t,"SOURCE")
similar_article.remove(sa)
print("Modified")
else:
print(f"First: {f_title}")
print(f"Second: {s_title}")
modify_similar_data(first_t,"SOURCE")
modify_similar_data(second_t,"SOURCE")
similar_article.remove(sa)
print("Modified")
else:
print("Similar list is empty")
response_data = json.loads(generated_text)
title = f_title
text = response_data["content"]
vector = embeddings.embed_query(generated_text)
if not is_similar_data(title, text, link, vector, threshold=0.98):
similar_d = "NO"
insert_data(title, text, link, vector, similar_d)
except Exception as e:
print(f"Error in completion: {e}")
continue