mirror of https://github.com/arc53/DocsGPT
Merge branch 'main' of github.com:ajaythapliyal/DocsGPT into ui-cleanup
commit
2461f5c1f6
@ -0,0 +1,13 @@
|
|||||||
|
from flask import jsonify
|
||||||
|
from werkzeug.http import HTTP_STATUS_CODES
|
||||||
|
|
||||||
|
def response_error(code_status,message=None):
|
||||||
|
payload = {'error':HTTP_STATUS_CODES.get(code_status,"something went wrong")}
|
||||||
|
if message:
|
||||||
|
payload['message'] = message
|
||||||
|
response = jsonify(payload)
|
||||||
|
response.status_code = code_status
|
||||||
|
return response
|
||||||
|
|
||||||
|
def bad_request(status_code=400,message=''):
|
||||||
|
return response_error(code_status=status_code,message=message)
|
@ -1,55 +1,73 @@
|
|||||||
var el = document.getElementById('message-form');
|
var form = document.getElementById('message-form');
|
||||||
if (el) {
|
var errorModal = document.getElementById('error-alert')
|
||||||
el.addEventListener("submit", function (event) {
|
document.getElementById('close').addEventListener('click',()=>{
|
||||||
console.log("submitting")
|
errorModal.classList.toggle('hidden')
|
||||||
event.preventDefault()
|
})
|
||||||
var message = document.getElementById("message-input").value;
|
|
||||||
msg_html = '<div class="bg-blue-500 text-white p-2 rounded-lg mb-2 self-end"><p class="text-sm">'
|
|
||||||
msg_html += message
|
function submitForm(event){
|
||||||
msg_html += '</p></div>'
|
event.preventDefault()
|
||||||
document.getElementById("messages").innerHTML += msg_html;
|
var message = document.getElementById("message-input").value;
|
||||||
let chatWindow = document.getElementById("messages-container");
|
console.log(message.length)
|
||||||
chatWindow.scrollTop = chatWindow.scrollHeight;
|
if(message.length === 0){
|
||||||
document.getElementById("message-input").value = "";
|
return
|
||||||
document.getElementById("button-submit").innerHTML = '<i class="fa fa-circle-o-notch fa-spin"></i> Thinking...';
|
}
|
||||||
document.getElementById("button-submit").disabled = true;
|
msg_html = '<div class="bg-blue-500 text-white p-2 rounded-lg mb-2 self-end"><p class="text-sm">'
|
||||||
if (localStorage.getItem('activeDocs') == null) {
|
msg_html += message
|
||||||
localStorage.setItem('activeDocs', 'default')
|
msg_html += '</p></div>'
|
||||||
}
|
document.getElementById("messages").innerHTML += msg_html;
|
||||||
|
let chatWindow = document.getElementById("messages-container");
|
||||||
fetch('/api/answer', {
|
chatWindow.scrollTop = chatWindow.scrollHeight;
|
||||||
method: 'POST',
|
document.getElementById("message-input").value = "";
|
||||||
headers: {
|
document.getElementById("button-submit").innerHTML = '<i class="fa fa-circle-o-notch fa-spin"></i> Thinking...';
|
||||||
'Content-Type': 'application/json',
|
document.getElementById("button-submit").disabled = true;
|
||||||
},
|
if (localStorage.getItem('activeDocs') == null) {
|
||||||
|
localStorage.setItem('activeDocs', 'default')
|
||||||
body: JSON.stringify({question: message,
|
}
|
||||||
api_key: localStorage.getItem('apiKey'),
|
|
||||||
embeddings_key: localStorage.getItem('apiKey'),
|
|
||||||
history: localStorage.getItem('chatHistory'),
|
fetch('/api/answer', {
|
||||||
active_docs: localStorage.getItem('activeDocs')}),
|
method: 'POST',
|
||||||
|
headers: {
|
||||||
|
'Content-Type': 'application/json',
|
||||||
|
},
|
||||||
|
|
||||||
|
body: JSON.stringify({question: message,
|
||||||
|
api_key: localStorage.getItem('apiKey'),
|
||||||
|
embeddings_key: localStorage.getItem('apiKey'),
|
||||||
|
history: localStorage.getItem('chatHistory'),
|
||||||
|
active_docs: localStorage.getItem('activeDocs')}),
|
||||||
|
}).then((response)=> response.json())
|
||||||
|
.then(data => {
|
||||||
|
console.log('Success:', data);
|
||||||
|
if(data.error){
|
||||||
|
document.getElementById('text-error').textContent = `Error : ${JSON.stringify(data.message)}`
|
||||||
|
errorModal.classList.toggle('hidden')
|
||||||
|
}
|
||||||
|
if(data.answer){
|
||||||
|
msg_html = '<div class="bg-indigo-500 text-white p-2 rounded-lg mb-2 self-start"><code class="text-sm">'
|
||||||
|
msg_html += data.answer
|
||||||
|
msg_html += '</code></div>'
|
||||||
|
document.getElementById("messages").innerHTML += msg_html;
|
||||||
|
let chatWindow = document.getElementById("messages-container");
|
||||||
|
chatWindow.scrollTop = chatWindow.scrollHeight;
|
||||||
|
}
|
||||||
|
document.getElementById("button-submit").innerHTML = 'Send';
|
||||||
|
document.getElementById("button-submit").disabled = false;
|
||||||
|
let chatHistory = [message, data.answer || ''];
|
||||||
|
localStorage.setItem('chatHistory', JSON.stringify(chatHistory));
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
})
|
})
|
||||||
.then(response => response.json())
|
.catch((error) => {
|
||||||
.then(data => {
|
console.error('Error:', error);
|
||||||
console.log('Success:', data);
|
// console.log(error);
|
||||||
msg_html = '<div class="bg-indigo-500 text-white p-2 rounded-lg mb-2 self-start"><code class="text-sm">'
|
// document.getElementById("button-submit").innerHTML = 'Send';
|
||||||
msg_html += data.answer
|
// document.getElementById("button-submit").disabled = false;
|
||||||
msg_html += '</code></div>'
|
|
||||||
document.getElementById("messages").innerHTML += msg_html;
|
});
|
||||||
let chatWindow = document.getElementById("messages-container");
|
|
||||||
chatWindow.scrollTop = chatWindow.scrollHeight;
|
|
||||||
document.getElementById("button-submit").innerHTML = 'Send';
|
|
||||||
document.getElementById("button-submit").disabled = false;
|
|
||||||
let chatHistory = [message, data.answer];
|
|
||||||
localStorage.setItem('chatHistory', JSON.stringify(chatHistory));
|
|
||||||
})
|
|
||||||
.catch((error) => {
|
|
||||||
console.error('Error:', error);
|
|
||||||
console.log(error);
|
|
||||||
document.getElementById("button-submit").innerHTML = 'Send';
|
|
||||||
document.getElementById("button-submit").disabled = false;
|
|
||||||
});
|
|
||||||
|
|
||||||
|
|
||||||
});
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
window.addEventListener('submit',submitForm)
|
||||||
|
@ -0,0 +1,126 @@
|
|||||||
|
from pathlib import Path
|
||||||
|
from langchain.text_splitter import CharacterTextSplitter
|
||||||
|
import faiss
|
||||||
|
from langchain.vectorstores import FAISS
|
||||||
|
from langchain.embeddings import OpenAIEmbeddings
|
||||||
|
from langchain.llms import OpenAI
|
||||||
|
from langchain.prompts import PromptTemplate
|
||||||
|
import pickle
|
||||||
|
import dotenv
|
||||||
|
import tiktoken
|
||||||
|
import sys
|
||||||
|
from argparse import ArgumentParser
|
||||||
|
import ast
|
||||||
|
|
||||||
|
dotenv.load_dotenv()
|
||||||
|
|
||||||
|
|
||||||
|
ps = list(Path("inputs").glob("**/*.py"))
|
||||||
|
data = []
|
||||||
|
sources = []
|
||||||
|
for p in ps:
|
||||||
|
with open(p) as f:
|
||||||
|
data.append(f.read())
|
||||||
|
sources.append(p)
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
# with open('inputs/client.py', 'r') as f:
|
||||||
|
# tree = ast.parse(f.read())
|
||||||
|
|
||||||
|
# print(tree)
|
||||||
|
|
||||||
|
|
||||||
|
def get_functions_in_class(node):
|
||||||
|
functions = []
|
||||||
|
functions_code = []
|
||||||
|
for child in node.body:
|
||||||
|
if isinstance(child, ast.FunctionDef):
|
||||||
|
functions.append(child.name)
|
||||||
|
functions_code.append(ast.unparse(child))
|
||||||
|
|
||||||
|
return functions, functions_code
|
||||||
|
|
||||||
|
|
||||||
|
def get_classes_and_functions(source_code):
|
||||||
|
tree = ast.parse(source_code)
|
||||||
|
classes = {}
|
||||||
|
for node in tree.body:
|
||||||
|
if isinstance(node, ast.ClassDef):
|
||||||
|
class_name = node.name
|
||||||
|
function_name, function = get_functions_in_class(node)
|
||||||
|
# join function name and function code
|
||||||
|
functions = dict(zip(function_name, function))
|
||||||
|
classes[class_name] = functions
|
||||||
|
return classes
|
||||||
|
|
||||||
|
|
||||||
|
structure_dict = {}
|
||||||
|
c1 = 0
|
||||||
|
for code in data:
|
||||||
|
classes = get_classes_and_functions(ast.parse(code))
|
||||||
|
source = str(sources[c1])
|
||||||
|
structure_dict[source] = classes
|
||||||
|
c1 += 1
|
||||||
|
|
||||||
|
# save the structure dict as json
|
||||||
|
import json
|
||||||
|
with open('structure_dict.json', 'w') as f:
|
||||||
|
json.dump(structure_dict, f)
|
||||||
|
|
||||||
|
|
||||||
|
# llm = OpenAI(temperature=0)
|
||||||
|
# prompt = PromptTemplate(
|
||||||
|
# input_variables=["code"],
|
||||||
|
# template="Code: {code}, Documentation: ",
|
||||||
|
# )
|
||||||
|
#
|
||||||
|
# print(prompt.format(code="print('hello world')"))
|
||||||
|
# print(llm(prompt.format(code="print('hello world')")))
|
||||||
|
|
||||||
|
|
||||||
|
if not Path("outputs").exists():
|
||||||
|
Path("outputs").mkdir()
|
||||||
|
|
||||||
|
c1 = len(structure_dict)
|
||||||
|
c2 = 0
|
||||||
|
for source, classes in structure_dict.items():
|
||||||
|
c2 += 1
|
||||||
|
print(f"Processing file {c2}/{c1}")
|
||||||
|
f1 = len(classes)
|
||||||
|
f2 = 0
|
||||||
|
for class_name, functions in classes.items():
|
||||||
|
f2 += 1
|
||||||
|
print(f"Processing class {f2}/{f1}")
|
||||||
|
source_w = source.replace("inputs/", "")
|
||||||
|
source_w = source_w.replace(".py", ".txt")
|
||||||
|
if not Path(f"outputs/{source_w}").exists():
|
||||||
|
with open(f"outputs/{source_w}", "w") as f:
|
||||||
|
f.write(f"Class: {class_name}")
|
||||||
|
else:
|
||||||
|
with open(f"outputs/{source_w}", "a") as f:
|
||||||
|
f.write(f"\n\nClass: {class_name}")
|
||||||
|
# append class name to the front
|
||||||
|
for function in functions:
|
||||||
|
b1 = len(functions)
|
||||||
|
b2 = 0
|
||||||
|
print(f"Processing function {b2}/{b1}")
|
||||||
|
b2 += 1
|
||||||
|
prompt = PromptTemplate(
|
||||||
|
input_variables=["code"],
|
||||||
|
template="Code: \n{code}, \nDocumentation: ",
|
||||||
|
)
|
||||||
|
llm = OpenAI(temperature=0)
|
||||||
|
response = llm(prompt.format(code=functions[function]))
|
||||||
|
|
||||||
|
if not Path(f"outputs/{source_w}").exists():
|
||||||
|
with open(f"outputs/{source_w}", "w") as f:
|
||||||
|
f.write(f"Function: {functions[function]}, \nDocumentation: {response}")
|
||||||
|
else:
|
||||||
|
with open(f"outputs/{source_w}", "a") as f:
|
||||||
|
f.write(f"\n\nFunction: {functions[function]}, \nDocumentation: {response}")
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
@ -0,0 +1,167 @@
|
|||||||
|
# Function name: get_functions_in_class
|
||||||
|
|
||||||
|
Function:
|
||||||
|
```
|
||||||
|
def get_functions_in_class(source_code, class_name):
|
||||||
|
tree = ast.parse(source_code)
|
||||||
|
functions = []
|
||||||
|
for node in tree.body:
|
||||||
|
if isinstance(node, ast.ClassDef):
|
||||||
|
if node.name == class_name:
|
||||||
|
for function in node.body:
|
||||||
|
if isinstance(function, ast.FunctionDef):
|
||||||
|
functions.append(function.name)
|
||||||
|
return functions
|
||||||
|
```,
|
||||||
|
Documentation:
|
||||||
|
|
||||||
|
|
||||||
|
get_functions_in_class(source_code, class_name)
|
||||||
|
|
||||||
|
Inputs:
|
||||||
|
source_code (str): The source code of the program.
|
||||||
|
class_name (str): The name of the class.
|
||||||
|
|
||||||
|
Outputs:
|
||||||
|
functions (list): A list of the functions in the class.
|
||||||
|
|
||||||
|
Description:
|
||||||
|
This function takes in a source code and a class name and returns a list of the functions in the class. It uses the ast module to parse the source code and find the class definition. It then iterates through the body of the class and checks if each node is a function definition. If it is, it adds the name of the function to the list of functions.
|
||||||
|
|
||||||
|
# Function name: process_functions
|
||||||
|
|
||||||
|
Function:
|
||||||
|
```
|
||||||
|
def process_functions(functions_dict):
|
||||||
|
c1 = len(functions_dict)
|
||||||
|
c2 = 0
|
||||||
|
for (source, functions) in functions_dict.items():
|
||||||
|
c2 += 1
|
||||||
|
print(f'Processing file {c2}/{c1}')
|
||||||
|
f1 = len(functions)
|
||||||
|
f2 = 0
|
||||||
|
source_w = source.replace('inputs/', '')
|
||||||
|
source_w = source_w.replace('.py', '.md')
|
||||||
|
create_subfolder(source_w)
|
||||||
|
for (name, function) in functions.items():
|
||||||
|
f2 += 1
|
||||||
|
print(f'Processing function {f2}/{f1}')
|
||||||
|
response = generate_response(function)
|
||||||
|
write_output_file(source_w, name, function, response)
|
||||||
|
```,
|
||||||
|
Documentation:
|
||||||
|
|
||||||
|
|
||||||
|
This function takes in a dictionary of functions and processes them. It takes the source file and the functions from the dictionary and creates a subfolder for the source file. It then generates a response for each function and writes the output file. The output file contains the function, the response, and the source file.
|
||||||
|
|
||||||
|
# Function name: get_functions_in_class
|
||||||
|
|
||||||
|
Function:
|
||||||
|
```
|
||||||
|
def get_functions_in_class(source_code, class_name):
|
||||||
|
tree = ast.parse(source_code)
|
||||||
|
functions = []
|
||||||
|
for node in tree.body:
|
||||||
|
if isinstance(node, ast.ClassDef):
|
||||||
|
if node.name == class_name:
|
||||||
|
for function in node.body:
|
||||||
|
if isinstance(function, ast.FunctionDef):
|
||||||
|
functions.append(function.name)
|
||||||
|
return functions
|
||||||
|
```,
|
||||||
|
Documentation:
|
||||||
|
|
||||||
|
|
||||||
|
get_functions_in_class(source_code, class_name)
|
||||||
|
|
||||||
|
Inputs:
|
||||||
|
source_code (str): The source code of the program.
|
||||||
|
class_name (str): The name of the class.
|
||||||
|
|
||||||
|
Outputs:
|
||||||
|
functions (list): A list of the functions in the class.
|
||||||
|
|
||||||
|
Description:
|
||||||
|
This function takes in a source code and a class name and returns a list of the functions in the class. It uses the ast module to parse the source code and find the class definition. It then iterates through the body of the class and checks if each node is a function definition. If it is, it adds the name of the function to the list of functions.
|
||||||
|
|
||||||
|
# Function name: process_functions
|
||||||
|
|
||||||
|
Function:
|
||||||
|
```
|
||||||
|
def process_functions(functions_dict):
|
||||||
|
c1 = len(functions_dict)
|
||||||
|
c2 = 0
|
||||||
|
for (source, functions) in functions_dict.items():
|
||||||
|
c2 += 1
|
||||||
|
print(f'Processing file {c2}/{c1}')
|
||||||
|
f1 = len(functions)
|
||||||
|
f2 = 0
|
||||||
|
source_w = source.replace('inputs/', '')
|
||||||
|
source_w = source_w.replace('.py', '.md')
|
||||||
|
create_subfolder(source_w)
|
||||||
|
for (name, function) in functions.items():
|
||||||
|
f2 += 1
|
||||||
|
print(f'Processing function {f2}/{f1}')
|
||||||
|
response = generate_response(function)
|
||||||
|
write_output_file(source_w, name, function, response)
|
||||||
|
```,
|
||||||
|
Documentation:
|
||||||
|
|
||||||
|
|
||||||
|
This function takes in a dictionary of functions and processes them. It takes the source file and the functions from the dictionary and creates a subfolder for the source file. It then generates a response for each function and writes the output file for each function.
|
||||||
|
|
||||||
|
# Function name: get_functions_in_class
|
||||||
|
|
||||||
|
Function:
|
||||||
|
```
|
||||||
|
def get_functions_in_class(source_code, class_name):
|
||||||
|
tree = ast.parse(source_code)
|
||||||
|
functions = []
|
||||||
|
for node in tree.body:
|
||||||
|
if isinstance(node, ast.ClassDef):
|
||||||
|
if node.name == class_name:
|
||||||
|
for function in node.body:
|
||||||
|
if isinstance(function, ast.FunctionDef):
|
||||||
|
functions.append(function.name)
|
||||||
|
return functions
|
||||||
|
```,
|
||||||
|
Documentation:
|
||||||
|
|
||||||
|
|
||||||
|
get_functions_in_class(source_code, class_name)
|
||||||
|
|
||||||
|
Inputs:
|
||||||
|
source_code (str): The source code of the program.
|
||||||
|
class_name (str): The name of the class.
|
||||||
|
|
||||||
|
Outputs:
|
||||||
|
functions (list): A list of the functions in the class.
|
||||||
|
|
||||||
|
Description:
|
||||||
|
This function takes in a source code and a class name and returns a list of the functions in the class. It uses the ast module to parse the source code and find the class definition. It then iterates through the body of the class and checks if each node is a function definition. If it is, it adds the name of the function to the list of functions.
|
||||||
|
|
||||||
|
# Function name: process_functions
|
||||||
|
|
||||||
|
Function:
|
||||||
|
```
|
||||||
|
def process_functions(functions_dict):
|
||||||
|
c1 = len(functions_dict)
|
||||||
|
c2 = 0
|
||||||
|
for (source, functions) in functions_dict.items():
|
||||||
|
c2 += 1
|
||||||
|
print(f'Processing file {c2}/{c1}')
|
||||||
|
f1 = len(functions)
|
||||||
|
f2 = 0
|
||||||
|
source_w = source.replace('inputs/', '')
|
||||||
|
source_w = source_w.replace('.py', '.md')
|
||||||
|
create_subfolder(source_w)
|
||||||
|
for (name, function) in functions.items():
|
||||||
|
f2 += 1
|
||||||
|
print(f'Processing function {f2}/{f1}')
|
||||||
|
response = generate_response(function)
|
||||||
|
write_output_file(source_w, name, function, response)
|
||||||
|
```,
|
||||||
|
Documentation:
|
||||||
|
|
||||||
|
|
||||||
|
This function takes in a dictionary of functions and processes them. It takes the source file and the functions from the dictionary and creates a subfolder for the source file. It then generates a response for each function and writes the output file for each function.
|
@ -0,0 +1,82 @@
|
|||||||
|
"""HTML parser.
|
||||||
|
|
||||||
|
Contains parser for html files.
|
||||||
|
|
||||||
|
"""
|
||||||
|
import re
|
||||||
|
from pathlib import Path
|
||||||
|
from typing import Dict, Union
|
||||||
|
|
||||||
|
from parser.file.base_parser import BaseParser
|
||||||
|
|
||||||
|
class HTMLParser(BaseParser):
|
||||||
|
"""HTML parser."""
|
||||||
|
|
||||||
|
def _init_parser(self) -> Dict:
|
||||||
|
"""Init parser."""
|
||||||
|
return {}
|
||||||
|
|
||||||
|
def parse_file(self, file: Path, errors: str = "ignore") -> Union[str, list[str]]:
|
||||||
|
"""Parse file.
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
Union[str, List[str]]: a string or a List of strings.
|
||||||
|
"""
|
||||||
|
try:
|
||||||
|
import unstructured
|
||||||
|
except ImportError:
|
||||||
|
raise ValueError("unstructured package is required to parse HTML files.")
|
||||||
|
from unstructured.partition.html import partition_html
|
||||||
|
from unstructured.staging.base import convert_to_isd
|
||||||
|
from unstructured.cleaners.core import clean
|
||||||
|
|
||||||
|
# Using the unstructured library to convert the html to isd format
|
||||||
|
# isd sample : isd = [
|
||||||
|
# {"text": "My Title", "type": "Title"},
|
||||||
|
# {"text": "My Narrative", "type": "NarrativeText"}
|
||||||
|
# ]
|
||||||
|
with open(file, "r", encoding="utf-8") as fp:
|
||||||
|
elements = partition_html(file=fp)
|
||||||
|
isd = convert_to_isd(elements)
|
||||||
|
|
||||||
|
# Removing non ascii charactwers from isd_el['text']
|
||||||
|
for isd_el in isd:
|
||||||
|
isd_el['text'] = isd_el['text'].encode("ascii", "ignore").decode()
|
||||||
|
|
||||||
|
# Removing all the \n characters from isd_el['text'] using regex and replace with single space
|
||||||
|
# Removing all the extra spaces from isd_el['text'] using regex and replace with single space
|
||||||
|
for isd_el in isd:
|
||||||
|
isd_el['text'] = re.sub(r'\n', ' ', isd_el['text'], flags=re.MULTILINE|re.DOTALL)
|
||||||
|
isd_el['text'] = re.sub(r"\s{2,}"," ", isd_el['text'], flags=re.MULTILINE|re.DOTALL)
|
||||||
|
|
||||||
|
# more cleaning: extra_whitespaces, dashes, bullets, trailing_punctuation
|
||||||
|
for isd_el in isd:
|
||||||
|
clean(isd_el['text'], extra_whitespace=True, dashes=True, bullets=True, trailing_punctuation=True )
|
||||||
|
|
||||||
|
# Creating a list of all the indexes of isd_el['type'] = 'Title'
|
||||||
|
title_indexes = [i for i,isd_el in enumerate(isd) if isd_el['type'] == 'Title']
|
||||||
|
|
||||||
|
# Creating 'Chunks' - List of lists of strings
|
||||||
|
# each list starting with with isd_el['type'] = 'Title' and all the data till the next 'Title'
|
||||||
|
# Each Chunk can be thought of as an individual set of data, which can be sent to the model
|
||||||
|
# Where Each Title is grouped together with the data under it
|
||||||
|
|
||||||
|
Chunks = [[]]
|
||||||
|
final_chunks = list(list())
|
||||||
|
|
||||||
|
for i,isd_el in enumerate(isd):
|
||||||
|
if i in title_indexes:
|
||||||
|
Chunks.append([])
|
||||||
|
Chunks[-1].append(isd_el['text'])
|
||||||
|
|
||||||
|
# Removing all the chunks with sum of lenth of all the strings in the chunk < 25 #TODO: This value can be an user defined variable
|
||||||
|
for chunk in Chunks:
|
||||||
|
# sum of lenth of all the strings in the chunk
|
||||||
|
sum = 0
|
||||||
|
sum += len(str(chunk))
|
||||||
|
if sum < 25:
|
||||||
|
Chunks.remove(chunk)
|
||||||
|
else :
|
||||||
|
# appending all the approved chunks to final_chunks as a single string
|
||||||
|
final_chunks.append(" ".join([str(item) for item in chunk]))
|
||||||
|
return final_chunks
|
@ -0,0 +1,155 @@
|
|||||||
|
from pathlib import Path
|
||||||
|
from langchain.llms import OpenAI
|
||||||
|
from langchain.prompts import PromptTemplate
|
||||||
|
import dotenv
|
||||||
|
import ast
|
||||||
|
import typer
|
||||||
|
import tiktoken
|
||||||
|
|
||||||
|
dotenv.load_dotenv()
|
||||||
|
|
||||||
|
def get_functions(source_code):
|
||||||
|
tree = ast.parse(source_code)
|
||||||
|
functions = {}
|
||||||
|
for node in tree.body:
|
||||||
|
if isinstance(node, ast.FunctionDef):
|
||||||
|
functions[node.name] = ast.unparse(node)
|
||||||
|
|
||||||
|
return functions
|
||||||
|
|
||||||
|
def get_functions_names(node):
|
||||||
|
functions = []
|
||||||
|
for child in node.body:
|
||||||
|
if isinstance(child, ast.FunctionDef):
|
||||||
|
functions.append(child.name)
|
||||||
|
return functions
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
def get_classes(source_code):
|
||||||
|
tree = ast.parse(source_code)
|
||||||
|
classes = {}
|
||||||
|
for node in tree.body:
|
||||||
|
if isinstance(node, ast.ClassDef):
|
||||||
|
classes[node.name] = get_functions_names(node)
|
||||||
|
return classes
|
||||||
|
|
||||||
|
def get_functions_in_class(source_code, class_name):
|
||||||
|
tree = ast.parse(source_code)
|
||||||
|
functions = []
|
||||||
|
for node in tree.body:
|
||||||
|
if isinstance(node, ast.ClassDef):
|
||||||
|
if node.name == class_name:
|
||||||
|
for function in node.body:
|
||||||
|
if isinstance(function, ast.FunctionDef):
|
||||||
|
functions.append(function.name)
|
||||||
|
return functions
|
||||||
|
|
||||||
|
|
||||||
|
def parse_functions(functions_dict):
|
||||||
|
c1 = len(functions_dict)
|
||||||
|
c2 = 0
|
||||||
|
for source, functions in functions_dict.items():
|
||||||
|
c2 += 1
|
||||||
|
print(f"Processing file {c2}/{c1}")
|
||||||
|
f1 = len(functions)
|
||||||
|
f2 = 0
|
||||||
|
source_w = source.replace("inputs/", "")
|
||||||
|
source_w = source_w.replace(".py", ".md")
|
||||||
|
# this is how we check subfolders
|
||||||
|
if "/" in source_w:
|
||||||
|
subfolders = source_w.split("/")
|
||||||
|
subfolders = subfolders[:-1]
|
||||||
|
subfolders = "/".join(subfolders)
|
||||||
|
if not Path(f"outputs/{subfolders}").exists():
|
||||||
|
Path(f"outputs/{subfolders}").mkdir(parents=True)
|
||||||
|
|
||||||
|
for name, function in functions.items():
|
||||||
|
f2 += 1
|
||||||
|
print(f"Processing function {f2}/{f1}")
|
||||||
|
prompt = PromptTemplate(
|
||||||
|
input_variables=["code"],
|
||||||
|
template="Code: \n{code}, \nDocumentation: ",
|
||||||
|
)
|
||||||
|
llm = OpenAI(temperature=0)
|
||||||
|
response = llm(prompt.format(code=function))
|
||||||
|
|
||||||
|
if not Path(f"outputs/{source_w}").exists():
|
||||||
|
with open(f"outputs/{source_w}", "w") as f:
|
||||||
|
f.write(f"# Function name: {name} \n\nFunction: \n```\n{function}\n```, \nDocumentation: \n{response}")
|
||||||
|
else:
|
||||||
|
with open(f"outputs/{source_w}", "a") as f:
|
||||||
|
f.write(f"\n\n# Function name: {name} \n\nFunction: \n```\n{function}\n```, \nDocumentation: \n{response}")
|
||||||
|
|
||||||
|
|
||||||
|
def parse_classes(classes_dict):
|
||||||
|
c1 = len(classes_dict)
|
||||||
|
c2 = 0
|
||||||
|
for source, classes in classes_dict.items():
|
||||||
|
c2 += 1
|
||||||
|
print(f"Processing file {c2}/{c1}")
|
||||||
|
f1 = len(classes)
|
||||||
|
f2 = 0
|
||||||
|
source_w = source.replace("inputs/", "")
|
||||||
|
source_w = source_w.replace(".py", ".md")
|
||||||
|
|
||||||
|
if "/" in source_w:
|
||||||
|
subfolders = source_w.split("/")
|
||||||
|
subfolders = subfolders[:-1]
|
||||||
|
subfolders = "/".join(subfolders)
|
||||||
|
if not Path(f"outputs/{subfolders}").exists():
|
||||||
|
Path(f"outputs/{subfolders}").mkdir(parents=True)
|
||||||
|
|
||||||
|
for name, function_names in classes.items():
|
||||||
|
print(f"Processing Class {f2}/{f1}")
|
||||||
|
f2 += 1
|
||||||
|
prompt = PromptTemplate(
|
||||||
|
input_variables=["class_name", "functions_names"],
|
||||||
|
template="Class name: {class_name} \nFunctions: {functions_names}, \nDocumentation: ",
|
||||||
|
)
|
||||||
|
llm = OpenAI(temperature=0)
|
||||||
|
response = llm(prompt.format(class_name=name, functions_names=function_names))
|
||||||
|
|
||||||
|
if not Path(f"outputs/{source_w}").exists():
|
||||||
|
with open(f"outputs/{source_w}", "w") as f:
|
||||||
|
f.write(f"# Class name: {name} \n\nFunctions: \n{function_names}, \nDocumentation: \n{response}")
|
||||||
|
else:
|
||||||
|
with open(f"outputs/{source_w}", "a") as f:
|
||||||
|
f.write(f"\n\n# Class name: {name} \n\nFunctions: \n{function_names}, \nDocumentation: \n{response}")
|
||||||
|
|
||||||
|
|
||||||
|
#User permission
|
||||||
|
def transform_to_docs(functions_dict, classes_dict):
|
||||||
|
# Function to ask user permission to call the OpenAI api and spend their OpenAI funds.
|
||||||
|
# Here we convert dicts to a string and calculate the number of OpenAI tokens the string represents.
|
||||||
|
docs_content = ""
|
||||||
|
for key, value in functions_dict.items():
|
||||||
|
docs_content += str(key) + str(value)
|
||||||
|
for key, value in classes_dict.items():
|
||||||
|
docs_content += str(key) + str(value)
|
||||||
|
|
||||||
|
encoding = tiktoken.get_encoding("cl100k_base")
|
||||||
|
num_tokens = len(encoding.encode(docs_content))
|
||||||
|
total_price = ((num_tokens / 1000) * 0.02)
|
||||||
|
|
||||||
|
# Here we print the number of tokens and the approx user cost with some visually appealing formatting.
|
||||||
|
print(f"Number of Tokens = {format(num_tokens, ',d')}")
|
||||||
|
print(f"Approx Cost = ${format(total_price, ',.2f')}")
|
||||||
|
#Here we check for user permission before calling the API.
|
||||||
|
user_input = input("Price Okay? (Y/N) \n").lower()
|
||||||
|
if user_input == "y":
|
||||||
|
if not Path("outputs").exists():
|
||||||
|
Path("outputs").mkdir()
|
||||||
|
parse_functions(functions_dict)
|
||||||
|
print("Functions done!")
|
||||||
|
parse_classes(classes_dict)
|
||||||
|
print("All done!")
|
||||||
|
elif user_input == "":
|
||||||
|
if not Path("outputs").exists():
|
||||||
|
Path("outputs").mkdir()
|
||||||
|
parse_functions(functions_dict)
|
||||||
|
print("Functions done!")
|
||||||
|
parse_classes(classes_dict)
|
||||||
|
print("All done!")
|
||||||
|
else:
|
||||||
|
print("The API was not called. No money was spent.")
|
Loading…
Reference in New Issue