issues
search
jamesturk
/
scrapeghost
👻 Experimental library for scraping websites using OpenAI's GPT API.
https://jamesturk.github.io/scrapeghost/
Other
1.43k
stars
87
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Add more OpenAI models
#61
DieterHolvoet
opened
1 month ago
0
Add support for gpt-4o-mini
#60
DieterHolvoet
opened
1 month ago
2
Autoscraper memoization?
#59
walking-octopus
opened
9 months ago
0
2023-11-06 updates
#58
jamesturk
closed
9 months ago
0
Not all chunk sizes are limited by the auto_split_length parameter
#57
gfranxman
closed
9 months ago
1
JavaScript Enabling
#56
d-pizhuk
closed
1 year ago
1
Add support for Azure, OpenAI, Palm, Anthropic, Cohere Models - using litellm
#55
ishaan-jaff
closed
11 months ago
4
explore using new functions-mode in GPT
#53
jamesturk
closed
9 months ago
0
pagination
#52
daonsh
closed
1 year ago
1
Optionally use puppeteer chromium and/or beautiful soup?
#51
turian
closed
1 year ago
2
breaking change: adjust how models are selected
#50
jamesturk
opened
1 year ago
0
Better Automatic Token Reduction
#49
jamesturk
opened
1 year ago
1
add non-JSON output option
#48
jamesturk
closed
9 months ago
0
pagination restore
#47
jamesturk
closed
1 year ago
0
adding header parameter to src/scrapeghost/scrapers.py
#46
ltngonnguyen
closed
1 year ago
1
scrapeghost.errors.TooManyTokens even though I am using auto_split_length
#45
Abio16
closed
1 year ago
1
Example error
#44
enflo
closed
1 year ago
1
Extending the project for older python versions
#43
enflo
closed
1 year ago
1
Preprocessing
#38
brasfb
closed
1 year ago
1
Issue with release_date formatting in tutorial
#37
christianboyle
closed
1 year ago
2
Functionality to JUST update existing CSS / XPath Selectors
#36
srhinos
closed
1 year ago
1
Disable HallucinationChecker
#35
kjenney
closed
1 year ago
3
added an optional verify parameter for requests
#34
smyja
closed
1 year ago
1
SSL verification check
#33
smyja
closed
1 year ago
0
Use guardrails for validation.
#32
smyja
closed
1 year ago
0
HallucinationChecker error
#31
ryandorward
closed
1 year ago
2
Discussion: Relicensing
#30
jamesturk
closed
3 months ago
6
Example Data/Case Studies Needed!
#29
jamesturk
closed
1 year ago
0
selenium intergration?
#28
barshag
closed
1 year ago
2
change log configuration for examples
#27
jamesturk
closed
1 year ago
0
restore PaginatedSchemaScraper
#26
jamesturk
closed
1 year ago
7
Hallucination checker improvements
#25
jamesturk
closed
1 year ago
0
pydantic improvements
#24
jamesturk
closed
1 year ago
0
Hallucination check postprocessor
#23
jamesturk
closed
1 year ago
0
help improve tests
#22
jamesturk
opened
1 year ago
0
more examples
#21
jamesturk
closed
1 year ago
0
pydantic validation
#20
jamesturk
closed
1 year ago
0
mypy
#19
jamesturk
closed
1 year ago
0
Make API backend pluggable to allow for non-OpenAI models
#18
jamesturk
opened
1 year ago
12
More Docs
#17
jamesturk
closed
1 year ago
1
meta
#16
jamesturk
closed
1 year ago
0
support other filetypes?
#15
jamesturk
opened
1 year ago
2
`Response` class
#14
jamesturk
closed
1 year ago
0
Add ability to provide few-shot examples
#13
patrickstorm
closed
1 year ago
2
0.3.0
#12
jamesturk
closed
1 year ago
0
add `stats` method
#11
jamesturk
closed
1 year ago
0
request->response extensibility
#10
jamesturk
closed
1 year ago
0
max_cost parameter(s)
#9
jamesturk
closed
1 year ago
0
tiktoken support
#8
jamesturk
closed
1 year ago
0
Hybrid Mode: ask scrapeghost to write selectors
#7
jamesturk
opened
1 year ago
1
Next