{{inviter}} has invited you to join their team (ID: {{tenant_id}}).
+If you did not request this, please ignore this email.
+"""
+
+# Password reset code template
+RESET_CODE_EMAIL_TMPL = """
+This code will expire in {{ ttl_min }} minutes.
+"""
+
+# Template registry
+EMAIL_TEMPLATES = {
+ "invite": INVITE_EMAIL_TMPL,
+ "reset_code": RESET_CODE_EMAIL_TMPL,
+}
diff --git a/api/utils/file_utils.py b/api/utils/file_utils.py
index 63e96fb..9815f0d 100644
--- a/api/utils/file_utils.py
+++ b/api/utils/file_utils.py
@@ -13,7 +13,12 @@
# See the License for the specific language governing permissions and
# limitations under the License.
#
+
+
+# Standard library imports
import base64
+import hashlib
+import io
import json
import os
import re
@@ -22,13 +27,20 @@ import subprocess
import sys
import tempfile
import threading
+import zipfile
from io import BytesIO
+# Typing
+from typing import List, Union, Tuple
+
+# Third-party imports
+import olefile
import pdfplumber
from cachetools import LRUCache, cached
from PIL import Image
from ruamel.yaml import YAML
+# Local imports
from api.constants import IMG_BASE64_PREFIX
from api.db import FileType
@@ -161,7 +173,7 @@ def filename_type(filename):
if re.match(r".*\.(wav|flac|ape|alac|wavpack|wv|mp3|aac|ogg|vorbis|opus)$", filename):
return FileType.AURAL.value
- if re.match(r".*\.(jpg|jpeg|png|tif|gif|pcx|tga|exif|fpx|svg|psd|cdr|pcd|dxf|ufo|eps|ai|raw|WMF|webp|avif|apng|icon|ico|mpg|mpeg|avi|rm|rmvb|mov|wmv|asf|dat|asx|wvx|mpe|mpa|mp4)$", filename):
+ if re.match(r".*\.(jpg|jpeg|png|tif|gif|pcx|tga|exif|fpx|svg|psd|cdr|pcd|dxf|ufo|eps|ai|raw|WMF|webp|avif|apng|icon|ico|mpg|mpeg|avi|rm|rmvb|mov|wmv|asf|dat|asx|wvx|mpe|mpa|mp4|avi|mkv)$", filename):
return FileType.VISUAL.value
return FileType.OTHER.value
@@ -284,3 +296,125 @@ def read_potential_broken_pdf(blob):
return repaired
return blob
+
+
+
+def _is_zip(h: bytes) -> bool:
+ return h.startswith(b"PK\x03\x04") or h.startswith(b"PK\x05\x06") or h.startswith(b"PK\x07\x08")
+
+def _is_pdf(h: bytes) -> bool:
+ return h.startswith(b"%PDF-")
+
+def _is_ole(h: bytes) -> bool:
+ return h.startswith(b"\xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1")
+
+def _sha10(b: bytes) -> str:
+ return hashlib.sha256(b).hexdigest()[:10]
+
+def _guess_ext(b: bytes) -> str:
+ h = b[:8]
+ if _is_zip(h):
+ try:
+ with zipfile.ZipFile(io.BytesIO(b), "r") as z:
+ names = [n.lower() for n in z.namelist()]
+ if any(n.startswith("word/") for n in names):
+ return ".docx"
+ if any(n.startswith("ppt/") for n in names):
+ return ".pptx"
+ if any(n.startswith("xl/") for n in names):
+ return ".xlsx"
+ except Exception:
+ pass
+ return ".zip"
+ if _is_pdf(h):
+ return ".pdf"
+ if _is_ole(h):
+ return ".doc"
+ return ".bin"
+
+# Try to extract the real embedded payload from OLE's Ole10Native
+def _extract_ole10native_payload(data: bytes) -> bytes:
+ try:
+ pos = 0
+ if len(data) < 4:
+ return data
+ _ = int.from_bytes(data[pos:pos+4], "little")
+ pos += 4
+ # filename/src/tmp (NUL-terminated ANSI)
+ for _ in range(3):
+ z = data.index(b"\x00", pos)
+ pos = z + 1
+ # skip unknown 4 bytes
+ pos += 4
+ if pos + 4 > len(data):
+ return data
+ size = int.from_bytes(data[pos:pos+4], "little")
+ pos += 4
+ if pos + size <= len(data):
+ return data[pos:pos+size]
+ except Exception:
+ pass
+ return data
+
+def extract_embed_file(target: Union[bytes, bytearray]) -> List[Tuple[str, bytes]]:
+ """
+ Only extract the 'first layer' of embedding, returning raw (filename, bytes).
+ """
+ top = bytes(target)
+ head = top[:8]
+ out: List[Tuple[str, bytes]] = []
+ seen = set()
+
+ def push(b: bytes, name_hint: str = ""):
+ h10 = _sha10(b)
+ if h10 in seen:
+ return
+ seen.add(h10)
+ ext = _guess_ext(b)
+ # If name_hint has an extension use its basename; else fallback to guessed ext
+ if "." in name_hint:
+ fname = name_hint.split("/")[-1]
+ else:
+ fname = f"{h10}{ext}"
+ out.append((fname, b))
+
+ # OOXML/ZIP container (docx/xlsx/pptx)
+ if _is_zip(head):
+ try:
+ with zipfile.ZipFile(io.BytesIO(top), "r") as z:
+ embed_dirs = (
+ "word/embeddings/", "word/objects/", "word/activex/",
+ "xl/embeddings/", "ppt/embeddings/"
+ )
+ for name in z.namelist():
+ low = name.lower()
+ if any(low.startswith(d) for d in embed_dirs):
+ try:
+ b = z.read(name)
+ push(b, name)
+ except Exception:
+ pass
+ except Exception:
+ pass
+ return out
+
+ # OLE container (doc/ppt/xls)
+ if _is_ole(head):
+ try:
+ with olefile.OleFileIO(io.BytesIO(top)) as ole:
+ for entry in ole.listdir():
+ p = "/".join(entry)
+ try:
+ data = ole.openstream(entry).read()
+ except Exception:
+ continue
+ if not data:
+ continue
+ if "Ole10Native" in p or "ole10native" in p.lower():
+ data = _extract_ole10native_payload(data)
+ push(data, p)
+ except Exception:
+ pass
+ return out
+
+ return out
\ No newline at end of file
diff --git a/api/utils/health_utils.py b/api/utils/health_utils.py
index 1396d75..3a97fc5 100644
--- a/api/utils/health_utils.py
+++ b/api/utils/health_utils.py
@@ -74,12 +74,12 @@ def get_es_cluster_stats() -> dict:
raise Exception("Elasticsearch is not in use.")
try:
return {
- "alive": True,
+ "status": "alive",
"message": ESConnection().get_cluster_stats()
}
except Exception as e:
return {
- "alive": False,
+ "status": "timeout",
"message": f"error: {str(e)}",
}
@@ -90,12 +90,12 @@ def get_infinity_status():
raise Exception("Infinity is not in use.")
try:
return {
- "alive": True,
+ "status": "alive",
"message": InfinityConnection().health()
}
except Exception as e:
return {
- "alive": False,
+ "status": "timeout",
"message": f"error: {str(e)}",
}
@@ -107,12 +107,12 @@ def get_mysql_status():
headers = ['id', 'user', 'host', 'db', 'command', 'time', 'state', 'info']
cursor.close()
return {
- "alive": True,
+ "status": "alive",
"message": [dict(zip(headers, r)) for r in res_rows]
}
except Exception as e:
return {
- "alive": False,
+ "status": "timeout",
"message": f"error: {str(e)}",
}
@@ -122,12 +122,12 @@ def check_minio_alive():
try:
response = requests.get(f'http://{rag_settings.MINIO["host"]}/minio/health/live')
if response.status_code == 200:
- return {'alive': True, "message": f"Confirm elapsed: {(timer() - start_time) * 1000.0:.1f} ms."}
+ return {"status": "alive", "message": f"Confirm elapsed: {(timer() - start_time) * 1000.0:.1f} ms."}
else:
- return {'alive': False, "message": f"Confirm elapsed: {(timer() - start_time) * 1000.0:.1f} ms."}
+ return {"status": "timeout", "message": f"Confirm elapsed: {(timer() - start_time) * 1000.0:.1f} ms."}
except Exception as e:
return {
- "alive": False,
+ "status": "timeout",
"message": f"error: {str(e)}",
}
@@ -135,12 +135,12 @@ def check_minio_alive():
def get_redis_info():
try:
return {
- "alive": True,
+ "status": "alive",
"message": REDIS_CONN.info()
}
except Exception as e:
return {
- "alive": False,
+ "status": "timeout",
"message": f"error: {str(e)}",
}
@@ -150,12 +150,12 @@ def check_ragflow_server_alive():
try:
response = requests.get(f'http://{settings.HOST_IP}:{settings.HOST_PORT}/v1/system/ping')
if response.status_code == 200:
- return {'alive': True, "message": f"Confirm elapsed: {(timer() - start_time) * 1000.0:.1f} ms."}
+ return {"status": "alive", "message": f"Confirm elapsed: {(timer() - start_time) * 1000.0:.1f} ms."}
else:
- return {'alive': False, "message": f"Confirm elapsed: {(timer() - start_time) * 1000.0:.1f} ms."}
+ return {"status": "timeout", "message": f"Confirm elapsed: {(timer() - start_time) * 1000.0:.1f} ms."}
except Exception as e:
return {
- "alive": False,
+ "status": "timeout",
"message": f"error: {str(e)}",
}
@@ -192,9 +192,7 @@ def run_health_checks() -> tuple[dict, bool]:
except Exception:
result["storage"] = "nok"
-
- all_ok = (result.get("db") == "ok") and (result.get("redis") == "ok") and (result.get("doc_engine") == "ok") and (result.get("storage") == "ok")
+ all_ok = (result.get("db") == "ok") and (result.get("redis") == "ok") and (result.get("doc_engine") == "ok") and (
+ result.get("storage") == "ok")
result["status"] = "ok" if all_ok else "nok"
return result, all_ok
-
-
diff --git a/api/utils/web_utils.py b/api/utils/web_utils.py
index 55ce561..e0e47f4 100644
--- a/api/utils/web_utils.py
+++ b/api/utils/web_utils.py
@@ -24,6 +24,7 @@ from urllib.parse import urlparse
from api.apps import smtp_mail_server
from flask_mail import Message
from flask import render_template_string
+from api.utils.email_templates import EMAIL_TEMPLATES
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.chrome.options import Options
@@ -34,6 +35,12 @@ from selenium.webdriver.support.ui import WebDriverWait
from webdriver_manager.chrome import ChromeDriverManager
+OTP_LENGTH = 8
+OTP_TTL_SECONDS = 5 * 60
+ATTEMPT_LIMIT = 5
+ATTEMPT_LOCK_SECONDS = 30 * 60
+RESEND_COOLDOWN_SECONDS = 60
+
CONTENT_TYPE_MAP = {
# Office
@@ -178,24 +185,49 @@ def get_float(req: dict, key: str, default: float | int = 10.0) -> float:
return default
-INVITE_EMAIL_TMPL = """
-{{inviter}} has invited you to join their team (ID: {{tenant_id}}).
-If you did not request this, please ignore this email.
-"""
+def send_email_html(subject: str, to_email: str, template_key: str, **context):
+ """Generic HTML email sender using shared templates.
+ template_key must exist in EMAIL_TEMPLATES.
+ """
+ from api.apps import app
+ tmpl = EMAIL_TEMPLATES.get(template_key)
+ if not tmpl:
+ raise ValueError(f"Unknown email template: {template_key}")
+ with app.app_context():
+ msg = Message(subject=subject, recipients=[to_email])
+ msg.html = render_template_string(tmpl, **context)
+ smtp_mail_server.send(msg)
+
def send_invite_email(to_email, invite_url, tenant_id, inviter):
- from api.apps import app
- with app.app_context():
- msg = Message(subject="RAGFlow Invitation",
- recipients=[to_email])
- msg.html = render_template_string(
- INVITE_EMAIL_TMPL,
- email=to_email,
- invite_url=invite_url,
- tenant_id=tenant_id,
- inviter=inviter,
- )
- smtp_mail_server.send(msg)
+ # Reuse the generic HTML sender with 'invite' template
+ send_email_html(
+ subject="RAGFlow Invitation",
+ to_email=to_email,
+ template_key="invite",
+ email=to_email,
+ invite_url=invite_url,
+ tenant_id=tenant_id,
+ inviter=inviter,
+ )
+
+
+def otp_keys(email: str):
+ email = (email or "").strip().lower()
+ return (
+ f"otp:{email}",
+ f"otp_attempts:{email}",
+ f"otp_last_sent:{email}",
+ f"otp_lock:{email}",
+ )
+
+
+def hash_code(code: str, salt: bytes) -> str:
+ import hashlib
+ import hmac
+ return hmac.new(salt, (code or "").encode("utf-8"), hashlib.sha256).hexdigest()
+
+
+def captcha_key(email: str) -> str:
+ return f"captcha:{email}"
+
diff --git a/chat_demo/index.html b/chat_demo/index.html
new file mode 100644
index 0000000..114b136
--- /dev/null
+++ b/chat_demo/index.html
@@ -0,0 +1,19 @@
+
+
🚀 Floating Chat Widget Demo
+
+
+ Welcome to our demo page! This page simulates a real website with content.
+ Look for the floating chat button in the bottom-right corner - just like Intercom!
+
+
+
+
🎯 Widget Features
+
+ - Floating button that stays visible while scrolling
+ - Click to open/close the chat window
+ - Minimize button to collapse the chat
+ - Professional Intercom-style design
+ - Unread message indicator (red badge)
+ - Transparent background integration
+ - Responsive design for all screen sizes
+
+
+
+
+ The chat widget is completely separate from your website's content and won't
+ interfere with your existing layout or functionality. It's designed to be
+ lightweight and performant.
+
+
+
+ Try scrolling this page - notice how the chat button stays in position.
+ Click it to start a conversation with our AI assistant!
+
+
+
+
🔧 Implementation
+
+ - Simple iframe embed - just copy and paste
+ - No JavaScript dependencies required
+ - Works on any website or platform
+ - Customizable appearance and behavior
+ - Secure and privacy-focused
+
+
+
+
+ This is just placeholder content to demonstrate how the widget integrates
+ seamlessly with your existing website content. The widget floats above
+ everything else without disrupting your user experience.
+
+
+
+ 🎉 Ready to add this to your website? Get your embed code from the admin panel!
+
+
+
- 
+ 
@@ -84,8 +84,8 @@ Try our demo at [https://demo.ragflow.io](https://demo.ragflow.io).
## 🔥 Latest Updates
+- 2025-10-15 Supports orchestrable ingestion pipeline.
- 2025-08-08 Supports OpenAI's latest GPT-5 series models.
-- 2025-08-04 Supports new models, including Kimi K2 and Grok 4.
- 2025-08-01 Supports agentic workflow and MCP.
- 2025-05-23 Adds a Python/JavaScript code executor component to Agent.
- 2025-05-05 Supports cross-language query.
@@ -135,7 +135,7 @@ releases! 🌟
## 🔎 System Architecture
@@ -80,8 +80,8 @@ Coba demo kami di [https://demo.ragflow.io](https://demo.ragflow.io).
## 🔥 Pembaruan Terbaru
+- 2025-10-15 Dukungan untuk jalur data yang terorkestrasi.
- 2025-08-08 Mendukung model seri GPT-5 terbaru dari OpenAI.
-- 2025-08-04 Mendukung model baru, termasuk Kimi K2 dan Grok 4.
- 2025-08-01 Mendukung alur kerja agen dan MCP.
- 2025-05-23 Menambahkan komponen pelaksana kode Python/JS ke Agen.
- 2025-05-05 Mendukung kueri lintas bahasa.
@@ -129,7 +129,7 @@ Coba demo kami di [https://demo.ragflow.io](https://demo.ragflow.io).
## 🔎 Arsitektur Sistem
@@ -80,8 +80,8 @@ Experimente nossa demo em [https://demo.ragflow.io](https://demo.ragflow.io).
## 🔥 Últimas Atualizações
+- 10-15-2025 Suporte para pipelines de dados orquestrados.
- 08-08-2025 Suporta a mais recente série GPT-5 da OpenAI.
-- 04-08-2025 Suporta novos modelos, incluindo Kimi K2 e Grok 4.
- 01-08-2025 Suporta fluxo de trabalho agente e MCP.
- 23-05-2025 Adicione o componente executor de código Python/JS ao Agente.
- 05-05-2025 Suporte a consultas entre idiomas.
@@ -129,7 +129,7 @@ Experimente nossa demo em [https://demo.ragflow.io](https://demo.ragflow.io).
## 🔎 Arquitetura do Sistema