LLM/DocsGPT
1
0
Fork 0
mirror of https://github.com/arc53/DocsGPT.git synced 2025-11-29 08:33:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Proper PEP8 formatting

Browse Source
This commit is contained in:
Anton Larin
2023-05-12 12:02:25 +02:00
parent 7f56f57778
commit 168648e789
14 changed files with 139 additions and 123 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
application/app.py
View File

@@ -90,10 +90,12 @@ mongo = MongoClient(app.config['MONGO_URI'])
db = mongo["docsgpt"]
vectors_collection = db["vectors"]
async def async_generate(chain, question, chat_history):
result = await chain.arun({"question": question, "chat_history": chat_history})
return result
def run_async_chain(chain, question, chat_history):
loop = asyncio.new_event_loop()
asyncio.set_event_loop(loop)
@@ -105,6 +107,7 @@ def run_async_chain(chain, question, chat_history):
result["answer"] = answer
return result
@celery.task(bind=True)
def ingest(self, directory, formats, name_job, filename, user):
resp = ingest_worker(self, directory, formats, name_job, filename, user)

10
scripts/code_docs_gen.py
View File

@@ -11,10 +11,10 @@ import tiktoken
import sys
from argparse import ArgumentParser
import ast
import json
dotenv.load_dotenv()
ps = list(Path("inputs").glob("**/*.py"))
data = []
sources = []
@@ -24,7 +24,6 @@ for p in ps:
sources.append(p)
# with open('inputs/client.py', 'r') as f:
# tree = ast.parse(f.read())
@@ -64,11 +63,9 @@ for code in data:
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"],
@@ -119,8 +116,3 @@ for source, classes in structure_dict.items():
else:
with open(f"outputs/{source_w}", "a") as f:
f.write(f"\n\nFunction: {functions[function]}, \nDocumentation: {response}")

14
scripts/ingest.py
View File

@@ -16,7 +16,6 @@ from parser.js2doc import extract_functions_and_classes as extract_js
from parser.java2doc import extract_functions_and_classes as extract_java
from parser.token_func import group_split
dotenv.load_dotenv()
app = typer.Typer(add_completion=False)
@@ -41,12 +40,12 @@ def ingest(yes: bool = typer.Option(False, "-y", "--yes", prompt=False,
help="""List of required extensions (list with .)
Currently supported: .rst, .md, .pdf, .docx, .csv, .epub, .html, .mdx"""),
exclude: Optional[bool] = typer.Option(True, help="Whether to exclude hidden files (dotfiles)."),
sample: Optional[bool] = typer.Option(False, help="Whether to output sample of the first 5 split documents."),
sample: Optional[bool] = typer.Option(False,
help="Whether to output sample of the first 5 split documents."),
token_check: Optional[bool] = typer.Option(True, help="Whether to group small documents and split large."),
min_tokens: Optional[int] = typer.Option(150, help="Minimum number of tokens to not group."),
max_tokens: Optional[int] = typer.Option(2000, help="Maximum number of tokens to not split."),
):
"""
Creates index from specified location or files.
By default /inputs folder is used, .rst and .md are parsed.
@@ -59,7 +58,8 @@ def ingest(yes: bool = typer.Option(False, "-y", "--yes", prompt=False,
# Here we split the documents, as needed, into smaller chunks.
# We do this due to the context limits of the LLMs.
raw_docs = group_split(documents=raw_docs, min_tokens=min_tokens, max_tokens=max_tokens, token_check=token_check)
raw_docs = group_split(documents=raw_docs, min_tokens=min_tokens, max_tokens=max_tokens,
token_check=token_check)
# Old method
# text_splitter = RecursiveCharacterTextSplitter()
# docs = text_splitter.split_documents(raw_docs)
@@ -71,7 +71,6 @@ def ingest(yes: bool = typer.Option(False, "-y", "--yes", prompt=False,
docs = [Document.to_langchain_format(raw_doc) for raw_doc in raw_docs]
# Here we check for command line arguments for bot calls.
# If no argument exists or the yes is not True, then the
# user permission is requested to call the API.
@@ -103,7 +102,6 @@ def convert(dir: Optional[str] = typer.Option("inputs",
formats: Optional[str] = typer.Option("py",
help="""Required language.
py, js, java supported for now""")):
"""
Creates documentation linked to original functions from specified location.
By default /inputs folder is used, .py is parsed.
@@ -117,7 +115,7 @@ def convert(dir: Optional[str] = typer.Option("inputs",
else:
raise Exception("Sorry, language not supported yet")
transform_to_docs(functions_dict, classes_dict, formats, dir)
if __name__ == "__main__":
app()

1
scripts/parser/file/html_parser.py
View File

@@ -9,6 +9,7 @@ from typing import Dict, Union
from parser.file.base_parser import BaseParser
class HTMLParser(BaseParser):
"""HTML parser."""

5
scripts/parser/file/markdown_parser.py
View File

@@ -35,8 +35,8 @@ class MarkdownParser(BaseParser):
self._max_tokens = max_tokens
# self._remove_tables = remove_tables
def tups_chunk_append(self, tups: List[Tuple[Optional[str], str]], current_header: Optional[str], current_text: str):
def tups_chunk_append(self, tups: List[Tuple[Optional[str], str]], current_header: Optional[str],
current_text: str):
"""Append to tups chunk."""
num_tokens = len(tiktoken.get_encoding("cl100k_base").encode(current_text))
if num_tokens > self._max_tokens:
@@ -46,6 +46,7 @@ class MarkdownParser(BaseParser):
else:
tups.append((current_header, current_text))
return tups
def markdown_to_tups(self, markdown_text: str) -> List[Tuple[Optional[str], str]]:
"""Convert a markdown file to a dictionary.

5
scripts/parser/file/rst_parser.py
View File

@@ -10,6 +10,7 @@ from typing import Any, Dict, List, Optional, Tuple, Union, cast
from parser.file.base_parser import BaseParser
import tiktoken
class RstParser(BaseParser):
"""reStructuredText parser.
@@ -41,7 +42,6 @@ class RstParser(BaseParser):
self._remove_whitespaces_excess = remove_whitespaces_excess
self._remove_characters_excess = remove_characters_excess
def rst_to_tups(self, rst_text: str) -> List[Tuple[Optional[str], str]]:
"""Convert a reStructuredText file to a dictionary.
@@ -56,7 +56,8 @@ class RstParser(BaseParser):
for i, line in enumerate(lines):
header_match = re.match(r"^[^\S\n]*[-=]+[^\S\n]*$", line)
if header_match and i > 0 and (len(lines[i - 1].strip()) == len(header_match.group().strip()) or lines[i - 2] == lines[i - 2]):
if header_match and i > 0 and (
len(lines[i - 1].strip()) == len(header_match.group().strip()) or lines[i - 2] == lines[i - 2]):
if current_header is not None:
if current_text == "" or None:
continue

4
scripts/parser/java2doc.py
View File

@@ -1,6 +1,7 @@
import os
import javalang
def find_files(directory):
files_list = []
for root, dirs, files in os.walk(directory):
@@ -9,6 +10,7 @@ def find_files(directory):
files_list.append(os.path.join(root, file))
return files_list
def extract_functions(file_path):
with open(file_path, "r") as file:
java_code = file.read()
@@ -28,6 +30,7 @@ def extract_functions(file_path):
methods[method_name] = method_source_code
return methods
def extract_classes(file_path):
with open(file_path, 'r') as file:
source_code = file.read()
@@ -47,6 +50,7 @@ def extract_classes(file_path):
classes[class_name] = class_string
return classes
def extract_functions_and_classes(directory):
files = find_files(directory)
functions_dict = {}

3
scripts/parser/js2doc.py
View File

@@ -11,6 +11,7 @@ def find_files(directory):
files_list.append(os.path.join(root, file))
return files_list
def extract_functions(file_path):
with open(file_path, 'r') as file:
source_code = file.read()
@@ -38,6 +39,7 @@ def extract_functions(file_path):
functions[func_name] = escodegen.generate(declaration.init)
return functions
def extract_classes(file_path):
with open(file_path, 'r') as file:
source_code = file.read()
@@ -53,6 +55,7 @@ def extract_classes(file_path):
classes[class_name] = ", ".join(function_names)
return classes
def extract_functions_and_classes(directory):
files = find_files(directory)
functions_dict = {}

8
scripts/parser/open_ai_func.py
View File

@@ -12,7 +12,6 @@ from langchain.embeddings import OpenAIEmbeddings
from retry import retry
def num_tokens_from_string(string: str, encoding_name: str) -> int:
# Function to convert string to tokens and estimate user cost.
encoding = tiktoken.get_encoding(encoding_name)
@@ -20,11 +19,13 @@ def num_tokens_from_string(string: str, encoding_name: str) -> int:
total_price = ((num_tokens / 1000) * 0.0004)
return num_tokens, total_price
@retry(tries=10, delay=60)
def store_add_texts_with_retry(store, i):
store.add_texts([i.page_content], metadatas=[i.metadata])
# store_pine.add_texts([i.page_content], metadatas=[i.metadata])
def call_openai_api(docs, folder_name):
# Function to create a vector store from the documents and save it to disk.
@@ -51,7 +52,8 @@ def call_openai_api(docs, folder_name):
# model_name = "sentence-transformers/all-mpnet-base-v2"
# hf = HuggingFaceEmbeddings(model_name=model_name)
# store = FAISS.from_documents(docs_test, hf)
for i in tqdm(docs, desc="Embedding 🦖", unit="docs", total=len(docs), bar_format='{l_bar}{bar}| Time Left: {remaining}'):
for i in tqdm(docs, desc="Embedding 🦖", unit="docs", total=len(docs),
bar_format='{l_bar}{bar}| Time Left: {remaining}'):
try:
store_add_texts_with_retry(store, i)
except Exception as e:
@@ -64,6 +66,7 @@ def call_openai_api(docs, folder_name):
c1 += 1
store.save_local(f"outputs/{folder_name}")
def get_user_permission(docs, folder_name):
# Function to ask user permission to call the OpenAI api and spend their OpenAI funds.
# Here we convert the docs list to a string and calculate the number of OpenAI tokens the string represents.
@@ -72,7 +75,6 @@ def get_user_permission(docs, folder_name):
for doc in docs:
docs_content += doc.page_content
tokens, total_price = num_tokens_from_string(string=docs_content, encoding_name="cl100k_base")
# Here we print the number of tokens and the approx user cost with some visually appealing formatting.
print(f"Number of Tokens = {format(tokens, ',d')}")

9
scripts/parser/py2doc.py
View File

@@ -5,6 +5,7 @@ from pathlib import Path
from langchain.llms import OpenAI
from langchain.prompts import PromptTemplate
def find_files(directory):
files_list = []
for root, dirs, files in os.walk(directory):
@@ -13,6 +14,7 @@ def find_files(directory):
files_list.append(os.path.join(root, file))
return files_list
def extract_functions(file_path):
with open(file_path, 'r') as file:
source_code = file.read()
@@ -25,6 +27,7 @@ def extract_functions(file_path):
functions[func_name] = func_def
return functions
def extract_classes(file_path):
with open(file_path, 'r') as file:
source_code = file.read()
@@ -40,6 +43,7 @@ def extract_classes(file_path):
classes[class_name] = ", ".join(function_names)
return classes
def extract_functions_and_classes(directory):
files = find_files(directory)
functions_dict = {}
@@ -53,6 +57,7 @@ def extract_functions_and_classes(directory):
classes_dict[file] = classes
return functions_dict, classes_dict
def parse_functions(functions_dict, formats, dir):
c1 = len(functions_dict)
for i, (source, functions) in enumerate(functions_dict.items(), start=1):
@@ -70,7 +75,8 @@ def parse_functions(functions_dict, formats, dir):
response = llm(prompt.format(code=function))
mode = "a" if Path(f"outputs/{source_w}").exists() else "w"
with open(f"outputs/{source_w}", mode) as f:
f.write(f"\n\n# Function name: {name} \n\nFunction: \n```\n{function}\n```, \nDocumentation: \n{response}")
f.write(
f"\n\n# Function name: {name} \n\nFunction: \n```\n{function}\n```, \nDocumentation: \n{response}")
def parse_classes(classes_dict, formats, dir):
@@ -92,6 +98,7 @@ def parse_classes(classes_dict, formats, dir):
with open(f"outputs/{source_w}", "a" if Path(f"outputs/{source_w}").exists() else "w") as f:
f.write(f"\n\n# Class name: {name} \n\nFunctions: \n{function_names}, \nDocumentation: \n{response}")
def transform_to_docs(functions_dict, classes_dict, formats, dir):
docs_content = ''.join([str(key) + str(value) for key, value in functions_dict.items()])
docs_content += ''.join([str(key) + str(value) for key, value in classes_dict.items()])

6
scripts/parser/token_func.py
View File

@@ -13,6 +13,7 @@ def separate_header_and_body(text):
body = text[len(header):]
return header, body
def group_documents(documents: List[Document], min_tokens: int, max_tokens: int) -> List[Document]:
docs = []
current_group = None
@@ -23,7 +24,8 @@ def group_documents(documents: List[Document], min_tokens: int, max_tokens: int)
if current_group is None:
current_group = Document(text=doc.text, doc_id=doc.doc_id, embedding=doc.embedding,
extra_info=doc.extra_info)
elif len(tiktoken.get_encoding("cl100k_base").encode(current_group.text)) + doc_len < max_tokens and doc_len >= min_tokens:
elif len(tiktoken.get_encoding("cl100k_base").encode(
current_group.text)) + doc_len < max_tokens and doc_len >= min_tokens:
current_group.text += " " + doc.text
else:
docs.append(current_group)
@@ -35,6 +37,7 @@ def group_documents(documents: List[Document], min_tokens: int, max_tokens: int)
return docs
def split_documents(documents: List[Document], max_tokens: int) -> List[Document]:
docs = []
for doc in documents:
@@ -54,6 +57,7 @@ def split_documents(documents: List[Document], max_tokens: int) -> List[Document
docs.append(new_doc)
return docs
def group_split(documents: List[Document], max_tokens: int = 2000, min_tokens: int = 150, token_check: bool = True):
if token_check == False:
return documents