forked from open-webui/open-webui
Timothy Jaeryang Baek
GitHub
commit
1dad423911
6 changed files with 179 additions and 62 deletions
|
|
@ -10,7 +10,7 @@ RUN npm ci
|
|||
COPY . .
|
||||
RUN npm run build
|
||||
|
||||
FROM python:3.11-bookworm as base
|
||||
FROM python:3.11-slim-bookworm as base
|
||||
|
||||
ENV ENV=prod
|
||||
|
||||
|
|
@ -28,7 +28,7 @@ WORKDIR /app/backend
|
|||
|
||||
COPY ./backend/requirements.txt ./requirements.txt
|
||||
RUN pip3 install -r requirements.txt
|
||||
RUN python -c "from sentence_transformers import SentenceTransformer; model = SentenceTransformer('all-MiniLM-L6-v2')"
|
||||
# RUN python -c "from sentence_transformers import SentenceTransformer; model = SentenceTransformer('all-MiniLM-L6-v2')"
|
||||
|
||||
COPY ./backend .
|
||||
|
||||
|
|
|
|||
|
|
@ -11,9 +11,14 @@ from fastapi import (
|
|||
from fastapi.middleware.cors import CORSMiddleware
|
||||
import os, shutil
|
||||
|
||||
from chromadb.utils import embedding_functions
|
||||
# from chromadb.utils import embedding_functions
|
||||
|
||||
from langchain_community.document_loaders import WebBaseLoader, TextLoader, PyPDFLoader
|
||||
from langchain_community.document_loaders import (
|
||||
WebBaseLoader,
|
||||
TextLoader,
|
||||
PyPDFLoader,
|
||||
CSVLoader,
|
||||
)
|
||||
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
||||
from langchain_community.vectorstores import Chroma
|
||||
from langchain.chains import RetrievalQA
|
||||
|
|
@ -23,15 +28,16 @@ from pydantic import BaseModel
|
|||
from typing import Optional
|
||||
|
||||
import uuid
|
||||
import time
|
||||
|
||||
|
||||
from utils.misc import calculate_sha256
|
||||
from utils.utils import get_current_user
|
||||
from config import UPLOAD_DIR, EMBED_MODEL, CHROMA_CLIENT, CHUNK_SIZE, CHUNK_OVERLAP
|
||||
from constants import ERROR_MESSAGES
|
||||
|
||||
EMBEDDING_FUNC = embedding_functions.SentenceTransformerEmbeddingFunction(
|
||||
model_name=EMBED_MODEL
|
||||
)
|
||||
# EMBEDDING_FUNC = embedding_functions.SentenceTransformerEmbeddingFunction(
|
||||
# model_name=EMBED_MODEL
|
||||
# )
|
||||
|
||||
app = FastAPI()
|
||||
|
||||
|
|
@ -64,9 +70,7 @@ def store_data_in_vector_db(data, collection_name) -> bool:
|
|||
metadatas = [doc.metadata for doc in docs]
|
||||
|
||||
try:
|
||||
collection = CHROMA_CLIENT.create_collection(
|
||||
name=collection_name, embedding_function=EMBEDDING_FUNC
|
||||
)
|
||||
collection = CHROMA_CLIENT.create_collection(name=collection_name)
|
||||
|
||||
collection.add(
|
||||
documents=texts, metadatas=metadatas, ids=[str(uuid.uuid1()) for _ in texts]
|
||||
|
|
@ -125,14 +129,13 @@ def store_web(form_data: StoreWebForm, user=Depends(get_current_user)):
|
|||
|
||||
@app.post("/doc")
|
||||
def store_doc(
|
||||
collection_name: str = Form(...),
|
||||
collection_name: Optional[str] = Form(None),
|
||||
file: UploadFile = File(...),
|
||||
user=Depends(get_current_user),
|
||||
):
|
||||
# "https://www.gutenberg.org/files/1727/1727-h/1727-h.htm"
|
||||
file.filename = f"{collection_name}-{file.filename}"
|
||||
|
||||
if file.content_type not in ["application/pdf", "text/plain"]:
|
||||
if file.content_type not in ["application/pdf", "text/plain", "text/csv"]:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail=ERROR_MESSAGES.FILE_NOT_SUPPORTED,
|
||||
|
|
@ -146,10 +149,17 @@ def store_doc(
|
|||
f.write(contents)
|
||||
f.close()
|
||||
|
||||
f = open(file_path, "rb")
|
||||
if collection_name == None:
|
||||
collection_name = calculate_sha256(f)[:63]
|
||||
f.close()
|
||||
|
||||
if file.content_type == "application/pdf":
|
||||
loader = PyPDFLoader(file_path)
|
||||
elif file.content_type == "text/plain":
|
||||
loader = TextLoader(file_path)
|
||||
elif file.content_type == "text/csv":
|
||||
loader = CSVLoader(file_path)
|
||||
|
||||
data = loader.load()
|
||||
result = store_data_in_vector_db(data, collection_name)
|
||||
|
|
@ -181,7 +191,7 @@ def reset_vector_db(user=Depends(get_current_user)):
|
|||
|
||||
|
||||
@app.get("/reset")
|
||||
def reset(user=Depends(get_current_user)):
|
||||
def reset(user=Depends(get_current_user)) -> bool:
|
||||
if user.role == "admin":
|
||||
folder = f"{UPLOAD_DIR}"
|
||||
for filename in os.listdir(folder):
|
||||
|
|
@ -199,7 +209,7 @@ def reset(user=Depends(get_current_user)):
|
|||
except Exception as e:
|
||||
print(e)
|
||||
|
||||
return {"status": True}
|
||||
return True
|
||||
else:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_403_FORBIDDEN,
|
||||
|
|
|
|||
|
|
@ -103,3 +103,29 @@ export const queryVectorDB = async (
|
|||
|
||||
return res;
|
||||
};
|
||||
|
||||
export const resetVectorDB = async (token: string) => {
|
||||
let error = null;
|
||||
|
||||
const res = await fetch(`${RAG_API_BASE_URL}/reset`, {
|
||||
method: 'GET',
|
||||
headers: {
|
||||
Accept: 'application/json',
|
||||
authorization: `Bearer ${token}`
|
||||
}
|
||||
})
|
||||
.then(async (res) => {
|
||||
if (!res.ok) throw await res.json();
|
||||
return res.json();
|
||||
})
|
||||
.catch((err) => {
|
||||
error = err.detail;
|
||||
return null;
|
||||
});
|
||||
|
||||
if (error) {
|
||||
throw error;
|
||||
}
|
||||
|
||||
return res;
|
||||
};
|
||||
|
|
|
|||
|
|
@ -91,6 +91,26 @@
|
|||
}
|
||||
};
|
||||
|
||||
const uploadDoc = async (file) => {
|
||||
console.log(file);
|
||||
|
||||
const doc = {
|
||||
type: 'doc',
|
||||
name: file.name,
|
||||
collection_name: '',
|
||||
upload_status: false,
|
||||
error: ''
|
||||
};
|
||||
|
||||
files = [...files, doc];
|
||||
const res = await uploadDocToVectorDB(localStorage.token, '', file);
|
||||
|
||||
if (res) {
|
||||
doc.upload_status = true;
|
||||
files = files;
|
||||
}
|
||||
};
|
||||
|
||||
onMount(() => {
|
||||
const dropZone = document.querySelector('body');
|
||||
|
||||
|
|
@ -122,21 +142,8 @@
|
|||
const file = inputFiles[0];
|
||||
if (['image/gif', 'image/jpeg', 'image/png'].includes(file['type'])) {
|
||||
reader.readAsDataURL(file);
|
||||
} else if (['application/pdf', 'text/plain'].includes(file['type'])) {
|
||||
console.log(file);
|
||||
const hash = (await calculateSHA256(file)).substring(0, 63);
|
||||
const res = await uploadDocToVectorDB(localStorage.token, hash, file);
|
||||
|
||||
if (res) {
|
||||
files = [
|
||||
...files,
|
||||
{
|
||||
type: 'doc',
|
||||
name: file.name,
|
||||
collection_name: res.collection_name
|
||||
}
|
||||
];
|
||||
}
|
||||
} else if (['application/pdf', 'text/plain', 'text/csv'].includes(file['type'])) {
|
||||
uploadDoc(file);
|
||||
} else {
|
||||
toast.error(`Unsupported File Type '${file['type']}'.`);
|
||||
}
|
||||
|
|
@ -241,22 +248,9 @@
|
|||
const file = inputFiles[0];
|
||||
if (['image/gif', 'image/jpeg', 'image/png'].includes(file['type'])) {
|
||||
reader.readAsDataURL(file);
|
||||
} else if (['application/pdf', 'text/plain'].includes(file['type'])) {
|
||||
console.log(file);
|
||||
const hash = (await calculateSHA256(file)).substring(0, 63);
|
||||
const res = await uploadDocToVectorDB(localStorage.token, hash, file);
|
||||
|
||||
if (res) {
|
||||
files = [
|
||||
...files,
|
||||
{
|
||||
type: 'doc',
|
||||
name: file.name,
|
||||
collection_name: res.collection_name
|
||||
}
|
||||
];
|
||||
} else if (['application/pdf', 'text/plain', 'text/csv'].includes(file['type'])) {
|
||||
uploadDoc(file);
|
||||
filesInputElement.value = '';
|
||||
}
|
||||
} else {
|
||||
toast.error(`Unsupported File Type '${file['type']}'.`);
|
||||
inputFiles = null;
|
||||
|
|
@ -283,6 +277,7 @@
|
|||
class="h-16 w-[15rem] flex items-center space-x-3 px-2.5 dark:bg-gray-600 rounded-xl border border-gray-200 dark:border-none"
|
||||
>
|
||||
<div class="p-2.5 bg-red-400 text-white rounded-lg">
|
||||
{#if file.upload_status}
|
||||
<svg
|
||||
xmlns="http://www.w3.org/2000/svg"
|
||||
viewBox="0 0 24 24"
|
||||
|
|
@ -298,6 +293,49 @@
|
|||
d="M12.971 1.816A5.23 5.23 0 0 1 14.25 5.25v1.875c0 .207.168.375.375.375H16.5a5.23 5.23 0 0 1 3.434 1.279 9.768 9.768 0 0 0-6.963-6.963Z"
|
||||
/>
|
||||
</svg>
|
||||
{:else}
|
||||
<svg
|
||||
class=" w-6 h-6 translate-y-[0.5px]"
|
||||
fill="currentColor"
|
||||
viewBox="0 0 24 24"
|
||||
xmlns="http://www.w3.org/2000/svg"
|
||||
><style>
|
||||
.spinner_qM83 {
|
||||
animation: spinner_8HQG 1.05s infinite;
|
||||
}
|
||||
.spinner_oXPr {
|
||||
animation-delay: 0.1s;
|
||||
}
|
||||
.spinner_ZTLf {
|
||||
animation-delay: 0.2s;
|
||||
}
|
||||
@keyframes spinner_8HQG {
|
||||
0%,
|
||||
57.14% {
|
||||
animation-timing-function: cubic-bezier(0.33, 0.66, 0.66, 1);
|
||||
transform: translate(0);
|
||||
}
|
||||
28.57% {
|
||||
animation-timing-function: cubic-bezier(0.33, 0, 0.66, 0.33);
|
||||
transform: translateY(-6px);
|
||||
}
|
||||
100% {
|
||||
transform: translate(0);
|
||||
}
|
||||
}
|
||||
</style><circle class="spinner_qM83" cx="4" cy="12" r="2.5" /><circle
|
||||
class="spinner_qM83 spinner_oXPr"
|
||||
cx="12"
|
||||
cy="12"
|
||||
r="2.5"
|
||||
/><circle
|
||||
class="spinner_qM83 spinner_ZTLf"
|
||||
cx="20"
|
||||
cy="12"
|
||||
r="2.5"
|
||||
/></svg
|
||||
>
|
||||
{/if}
|
||||
</div>
|
||||
|
||||
<div class="flex flex-col justify-center -space-y-0.5">
|
||||
|
|
|
|||
|
|
@ -31,6 +31,7 @@
|
|||
updateOpenAIKey,
|
||||
updateOpenAIUrl
|
||||
} from '$lib/apis/openai';
|
||||
import { resetVectorDB } from '$lib/apis/rag';
|
||||
|
||||
export let show = false;
|
||||
|
||||
|
|
@ -1829,6 +1830,40 @@
|
|||
<div class=" self-center text-sm font-medium">Delete All Chats</div>
|
||||
</button>
|
||||
{/if}
|
||||
|
||||
{#if $user?.role === 'admin'}
|
||||
<hr class=" dark:border-gray-700" />
|
||||
|
||||
<button
|
||||
class=" flex rounded-md py-2 px-3.5 w-full hover:bg-gray-200 dark:hover:bg-gray-800 transition"
|
||||
on:click={() => {
|
||||
const res = resetVectorDB(localStorage.token).catch((error) => {
|
||||
toast.error(error);
|
||||
return null;
|
||||
});
|
||||
|
||||
if (res) {
|
||||
toast.success('Success');
|
||||
}
|
||||
}}
|
||||
>
|
||||
<div class=" self-center mr-3">
|
||||
<svg
|
||||
xmlns="http://www.w3.org/2000/svg"
|
||||
viewBox="0 0 16 16"
|
||||
fill="currentColor"
|
||||
class="w-4 h-4"
|
||||
>
|
||||
<path
|
||||
fill-rule="evenodd"
|
||||
d="M3.5 2A1.5 1.5 0 0 0 2 3.5v9A1.5 1.5 0 0 0 3.5 14h9a1.5 1.5 0 0 0 1.5-1.5v-7A1.5 1.5 0 0 0 12.5 4H9.621a1.5 1.5 0 0 1-1.06-.44L7.439 2.44A1.5 1.5 0 0 0 6.38 2H3.5Zm6.75 7.75a.75.75 0 0 0 0-1.5h-4.5a.75.75 0 0 0 0 1.5h4.5Z"
|
||||
clip-rule="evenodd"
|
||||
/>
|
||||
</svg>
|
||||
</div>
|
||||
<div class=" self-center text-sm font-medium">Reset Vector Storage</div>
|
||||
</button>
|
||||
{/if}
|
||||
</div>
|
||||
</div>
|
||||
{:else if selectedTab === 'auth'}
|
||||
|
|
|
|||
|
|
@ -124,6 +124,14 @@
|
|||
} else if (messages.length != 0 && messages.at(-1).done != true) {
|
||||
// Response not done
|
||||
console.log('wait');
|
||||
} else if (
|
||||
files.length > 0 &&
|
||||
files.filter((file) => file.upload_status === false).length > 0
|
||||
) {
|
||||
// Upload not done
|
||||
toast.error(
|
||||
`Oops! Hold tight! Your files are still in the processing oven. We're cooking them up to perfection. Please be patient and we'll let you know once they're ready.`
|
||||
);
|
||||
} else {
|
||||
// Reset chat message textarea height
|
||||
document.getElementById('chat-textarea').style.height = '';
|
||||
|
|
|
|||
Loading…
Reference in a new issue