Public/kotaemon
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

(bump:minor) Feat: Add mechanism for user-site update and auto creating releases (#56)

Browse Source 
* move flowsettings.py and launch.py to root

* update docs

* sync sub package versions

* rename launch.py to app.py and make run scripts work with installation package

* add update scripts

* auto version for root package

* rename authors and update doc dir

* Update auto-bump-and-release.yaml to trigger on push to main branch

* latest as branch instead of tag

* pin deps versions

* cache the changelogs
This commit is contained in:
ian_Cin
2024-05-15 16:34:50 +07:00
committed by GitHub
parent eb198e0ff3
commit 654501e01c
20 changed files with 596 additions and 145 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
libs/ktem/README.md
View File

@@ -1,24 +0,0 @@
# Example of MVP pipeline for _example_
## Prerequisite
To run the system out-of-the-box, please supply the following environment
variables:
```
OPENAI_API_KEY=
OPENAI_API_BASE=
OPENAI_API_VERSION=
SERPAPI_API_KEY=
COHERE_API_KEY=
OPENAI_API_KEY_EMBEDDING=
# optional
KH_APP_NAME=
```
## Run
```
gradio launch.py
```

187
libs/ktem/flowsettings.py
View File

@@ -1,187 +0,0 @@
import os
from inspect import currentframe, getframeinfo
from pathlib import Path
from decouple import config
from theflow.settings.default import * # noqa
cur_frame = currentframe()
if cur_frame is None:
raise ValueError("Cannot get the current frame.")
this_file = getframeinfo(cur_frame).filename
this_dir = Path(this_file).parent
# App can be ran from anywhere and it's not trivial to decide where to store app data.
# So let's use the same directory as the flowsetting.py file.
KH_APP_DATA_DIR = this_dir / "ktem_app_data"
KH_APP_DATA_DIR.mkdir(parents=True, exist_ok=True)
# User data directory
KH_USER_DATA_DIR = KH_APP_DATA_DIR / "user_data"
KH_USER_DATA_DIR.mkdir(parents=True, exist_ok=True)
# HF models can be big, let's store them in the app data directory so that it's easier
# for users to manage their storage.
# ref: https://huggingface.co/docs/huggingface_hub/en/guides/manage-cache
os.environ["HF_HOME"] = str(KH_APP_DATA_DIR / "huggingface")
os.environ["HF_HUB_CACHE"] = str(KH_APP_DATA_DIR / "huggingface")
COHERE_API_KEY = config("COHERE_API_KEY", default="")
KH_MODE = "dev"
KH_FEATURE_USER_MANAGEMENT = False
KH_FEATURE_USER_MANAGEMENT_ADMIN = str(
config("KH_FEATURE_USER_MANAGEMENT_ADMIN", default="admin")
)
KH_FEATURE_USER_MANAGEMENT_PASSWORD = str(
config("KH_FEATURE_USER_MANAGEMENT_PASSWORD", default="XsdMbe8zKP8KdeE@")
)
KH_ENABLE_ALEMBIC = False
KH_DATABASE = f"sqlite:///{KH_USER_DATA_DIR / 'sql.db'}"
KH_FILESTORAGE_PATH = str(KH_USER_DATA_DIR / "files")
KH_DOCSTORE = {
"__type__": "kotaemon.storages.SimpleFileDocumentStore",
"path": str(KH_USER_DATA_DIR / "docstore"),
}
KH_VECTORSTORE = {
"__type__": "kotaemon.storages.ChromaVectorStore",
"path": str(KH_USER_DATA_DIR / "vectorstore"),
}
KH_LLMS = {}
KH_EMBEDDINGS = {}
# populate options from config
if config("AZURE_OPENAI_API_KEY", default="") and config(
"AZURE_OPENAI_ENDPOINT", default=""
):
if config("AZURE_OPENAI_CHAT_DEPLOYMENT", default=""):
KH_LLMS["azure"] = {
"spec": {
"__type__": "kotaemon.llms.AzureChatOpenAI",
"temperature": 0,
"azure_endpoint": config("AZURE_OPENAI_ENDPOINT", default=""),
"api_key": config("AZURE_OPENAI_API_KEY", default=""),
"api_version": config("OPENAI_API_VERSION", default="")
or "2024-02-15-preview",
"azure_deployment": config("AZURE_OPENAI_CHAT_DEPLOYMENT", default=""),
"timeout": 20,
},
"default": False,
"accuracy": 5,
"cost": 5,
}
if config("AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT", default=""):
KH_EMBEDDINGS["azure"] = {
"spec": {
"__type__": "kotaemon.embeddings.AzureOpenAIEmbeddings",
"azure_endpoint": config("AZURE_OPENAI_ENDPOINT", default=""),
"api_key": config("AZURE_OPENAI_API_KEY", default=""),
"api_version": config("OPENAI_API_VERSION", default="")
or "2024-02-15-preview",
"azure_deployment": config(
"AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT", default=""
),
"timeout": 10,
},
"default": False,
}
if config("OPENAI_API_KEY", default=""):
KH_LLMS["openai"] = {
"spec": {
"__type__": "kotaemon.llms.ChatOpenAI",
"temperature": 0,
"base_url": config("OPENAI_API_BASE", default="")
or "https://api.openai.com/v1",
"api_key": config("OPENAI_API_KEY", default=""),
"model": config("OPENAI_CHAT_MODEL", default="") or "gpt-3.5-turbo",
"timeout": 10,
},
"default": False,
}
if len(KH_EMBEDDINGS) < 1:
KH_EMBEDDINGS["openai"] = {
"spec": {
"__type__": "kotaemon.embeddings.OpenAIEmbeddings",
"base_url": config("OPENAI_API_BASE", default="")
or "https://api.openai.com/v1",
"api_key": config("OPENAI_API_KEY", default=""),
"model": config(
"OPENAI_EMBEDDINGS_MODEL", default="text-embedding-ada-002"
)
or "text-embedding-ada-002",
"timeout": 10,
},
"default": False,
}
if config("LOCAL_MODEL", default=""):
KH_LLMS["local"] = {
"spec": {
"__type__": "kotaemon.llms.EndpointChatLLM",
"endpoint_url": "http://localhost:31415/v1/chat/completions",
},
"default": False,
"cost": 0,
}
if len(KH_EMBEDDINGS) < 1:
KH_EMBEDDINGS["local"] = {
"spec": {
"__type__": "kotaemon.embeddings.EndpointEmbeddings",
"endpoint_url": "http://localhost:31415/v1/embeddings",
},
"default": False,
"cost": 0,
}
if len(KH_EMBEDDINGS) < 1:
KH_EMBEDDINGS["local-bge-base-en-v1.5"] = {
"spec": {
"__type__": "kotaemon.embeddings.FastEmbedEmbeddings",
"model_name": "BAAI/bge-base-en-v1.5",
},
"default": True,
}
KH_REASONINGS = ["ktem.reasoning.simple.FullQAPipeline"]
KH_VLM_ENDPOINT = "{0}/openai/deployments/{1}/chat/completions?api-version={2}".format(
config("AZURE_OPENAI_ENDPOINT", default=""),
config("OPENAI_VISION_DEPLOYMENT_NAME", default="gpt-4-vision"),
config("OPENAI_API_VERSION", default=""),
)
SETTINGS_APP = {
"lang": {
"name": "Language",
"value": "en",
"choices": [("English", "en"), ("Japanese", "ja")],
"component": "dropdown",
}
}
SETTINGS_REASONING = {
"use": {
"name": "Reasoning options",
"value": None,
"choices": [],
"component": "radio",
},
"lang": {
"name": "Language",
"value": "en",
"choices": [("English", "en"), ("Japanese", "ja")],
"component": "dropdown",
},
}
KH_INDEX_TYPES = ["ktem.index.file.FileIndex"]
KH_INDICES = [
{
"name": "File",
"config": {},
"index_type": "ktem.index.file.FileIndex",
},
]

84
libs/ktem/ktem/pages/help.py
View File

@@ -1,25 +1,83 @@
from importlib.metadata import version
from pathlib import Path
import gradio as gr
import requests
from theflow.settings import settings
CHANGELOG_CACHE_DIR = Path(settings.KH_APP_DATA_DIR) / "changelogs"
def get_remote_doc(url):
try:
res = requests.get(url)
return res.text
except Exception as e:
print(f"Failed to fetch document from {url}: {e}")
return ""
def get_changelogs(version):
# try retrieve from cache
if (CHANGELOG_CACHE_DIR / f"{version}.md").exists():
with open(CHANGELOG_CACHE_DIR / f"{version}.md", "r") as fi:
return fi.read()
release_url = f"https://api.github.com/repos/Cinnamon/kotaemon/releases/{version}"
try:
res = requests.get(release_url).json()
changelogs = res.get("body", "")
# cache the changelogs
with open(CHANGELOG_CACHE_DIR / f"{version}.md", "w") as fi:
fi.write(changelogs)
return changelogs
except Exception as e:
print(f"Failed to fetch changelogs from {release_url}: {e}")
return ""
class HelpPage:
def __init__(self, app):
self._app = app
self.md_dir = Path(__file__).parent.parent / "assets" / "md"
self.doc_dir = Path(__file__).parents[4] / "docs"
self.doc_dir = Path(settings.KH_DOC_DIR)
self.remote_content_url = "https://raw.githubusercontent.com/Cinnamon/kotaemon"
with gr.Accordion("About"):
with (self.md_dir / "about.md").open(encoding="utf-8") as fi:
gr.Markdown(fi.read())
self.app_version = None
try:
# Caution: This might produce the wrong version
# https://stackoverflow.com/a/59533071
self.app_version = version(settings.KH_PACKAGE_NAME)
except Exception as e:
print(f"Failed to get app version: {e}")
with gr.Accordion("User Guide"):
about_md_dir = self.doc_dir / "about.md"
if about_md_dir.exists():
with (self.doc_dir / "about.md").open(encoding="utf-8") as fi:
about_md = fi.read()
else: # fetch from remote
about_md = get_remote_doc(
f"{self.remote_content_url}/v{self.app_version}/docs/about.md"
)
if about_md:
with gr.Accordion("About"):
gr.Markdown(about_md)
user_guide_md_dir = self.doc_dir / "usage.md"
if user_guide_md_dir.exists():
with (self.doc_dir / "usage.md").open(encoding="utf-8") as fi:
gr.Markdown(fi.read())
user_guide_md = fi.read()
else: # fetch from remote
user_guide_md = get_remote_doc(
f"{self.remote_content_url}/v{self.app_version}/docs/usage.md"
)
if user_guide_md:
with gr.Accordion("User Guide"):
gr.Markdown(user_guide_md)
with gr.Accordion("Changelogs"):
gr.Markdown(self.get_changelogs())
def get_changelogs(self):
with (self.md_dir / "changelogs.md").open(encoding="utf-8") as fi:
return fi.read()
if self.app_version:
changelogs = get_changelogs("tags/v" + self.app_version)
if changelogs:
with gr.Accordion(f"Changelogs (v{self.app_version})"):
gr.Markdown(changelogs)

5
libs/ktem/launch.py
View File

@@ -1,5 +0,0 @@
from ktem.main import App
app = App()
demo = app.make()
demo.queue().launch(favicon_path=app._favicon, inbrowser=True)

40
libs/ktem/pyproject.toml
View File

@@ -1,37 +1,41 @@
[build-system]
requires = ["setuptools >= 61.0"]
requires = ["setuptools >= 61.0", "wheel", "setuptools-git-versioning>=2.0,<3"]
build-backend = "setuptools.build_meta"
[tool.setuptools]
include-package-data = true
packages.find.exclude = ["ktem_tests*", "env*"]
packages.find.include = ["ktem*"]
packages.find.exclude = ["tests*", "env*"]
[tool.setuptools-git-versioning]
enabled = true
dev_template = "{tag}"
dirty_template = "{tag}"
tag_filter = "v?\\d+(\\.\\d+)*.*"
[project]
name = "ktem"
version = "0.2.0"
dynamic = ["version"]
requires-python = ">= 3.10"
description = "RAG-based Question and Answering Application"
dependencies = [
"click",
"platformdirs",
"pluggy",
"python-decouple",
"sqlalchemy",
"sqlmodel",
"tiktoken",
"gradio>=4.26.0",
"markdown",
"click>=8.1.7,<9",
"platformdirs>=4.2.1,<5",
"pluggy>=1.5.0,<2",
"python-decouple>=3.8,<4",
"SQLAlchemy>=2.0.29,<3",
"sqlmodel>=0.0.16,<0.1",
"tiktoken>=0.6.0<1",
"gradio>=4.26.0,<5",
"markdown>=3.6,<4",
]
readme = "README.md"
license = { text = "MIT License" }
authors = [
{ name = "john", email = "john@cinnamon.is" },
{ name = "ian", email = "ian@cinnamon.is" },
{ name = "tadashi", email = "tadashi@cinnamon.is" },
{ name = "@trducng", email = "john@cinnamon.is" },
{ name = "@lone17", email = "ian@cinnamon.is" },
{ name = "@taprosoft", email = "tadashi@cinnamon.is" },
{ name = "@cin-albert", email = "albert@cinnamon.is" },
]
classifiers = [
"Programming Language :: Python :: 3",
"License :: OSI Approved :: MIT License",
"Operating System :: OS Independent",
]