mirror of
https://github.com/kennethreitz/langchain.git
synced 2026-06-05 23:00:18 +00:00
Cristóbal Carnero Liñán
e494b0a09f
#### Summary
A new approach to loading source code is implemented:
Each top-level function and class in the code is loaded into separate
documents. Then, an additional document is created with the top-level
code, but without the already loaded functions and classes.
This could improve the accuracy of QA chains over source code.
For instance, having this script:
```
class MyClass:
def __init__(self, name):
self.name = name
def greet(self):
print(f"Hello, {self.name}!")
def main():
name = input("Enter your name: ")
obj = MyClass(name)
obj.greet()
if __name__ == '__main__':
main()
```
The loader will create three documents with this content:
First document:
```
class MyClass:
def __init__(self, name):
self.name = name
def greet(self):
print(f"Hello, {self.name}!")
```
Second document:
```
def main():
name = input("Enter your name: ")
obj = MyClass(name)
obj.greet()
```
Third document:
```
# Code for: class MyClass:
# Code for: def main():
if __name__ == '__main__':
main()
```
A threshold parameter is added to control whether small scripts are
split in this way or not.
At this moment, only Python and JavaScript are supported. The
appropriate parser is determined by examining the file extension.
#### Tests
This PR adds:
- Unit tests
- Integration tests
#### Dependencies
Only one dependency was added as optional (needed for the JavaScript
parser).
#### Documentation
A notebook is added showing how the loader can be used.
#### Who can review?
@eyurtsev @hwchase17
---------
Co-authored-by: rlm <pexpresss31@gmail.com>
Example Docs
------------
The sample docs directory contains the following files:
- ``example-10k.html`` - A 10-K SEC filing in HTML format
- ``layout-parser-paper.pdf`` - A PDF copy of the layout parser paper
- ``factbook.xml``/``factbook.xsl`` - Example XML/XLS files that you
can use to test stylesheets
These documents can be used to test out the parsers in the library. In
addition, here are instructions for pulling in some sample docs that are
too big to store in the repo.
XBRL 10-K
^^^^^^^^^
You can get an example 10-K in inline XBRL format using the following
``curl``. Note, you need to have the user agent set in the header or the
SEC site will reject your request.
.. code:: bash
curl -O \
-A '${organization} ${email}'
https://www.sec.gov/Archives/edgar/data/311094/000117184321001344/0001171843-21-001344.txt
You can parse this document using the HTML parser.