Files
ragflow/api/db/init_data.py

184 lines
6.9 KiB
Python
Raw Normal View History

#
# Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import asyncio
import logging
import json
import os
import time
import uuid
from peewee import IntegrityError
from api.db import UserTenantRole
from api.db.db_models import init_database_tables as init_web_db
from api.db.services import UserService
from api.db.services.canvas_service import CanvasTemplateService
from api.db.services.document_service import DocumentService
from api.db.services.knowledgebase_service import KnowledgebaseService
from api.db.services.llm_service import LLMBundle
from api.db.services.user_service import TenantService, UserTenantService
from api.db.services.system_settings_service import SystemSettingsService
feat: support multiple canvas_types for agent templates and remove duplicate files (#14030) ### What problem does this PR solve? Closes #13907 The template catalog had duplicate files (e.g. `*_r.json`) only to place the same template into multiple sidebar groups. This increases maintenance cost and makes template updates error-prone. This PR adds first-class support for multiple template categories in a single file via `canvas_types`, then removes duplicate template files. What changed: - Added `canvas_types` to `CanvasTemplate` model and DB migration. - Added normalization logic when loading templates: - accepts legacy `canvas_type` - accepts new `canvas_types` - merges/deduplicates values - preserves backward compatibility by keeping `canvas_type` as first normalized value. - Updated template import flow to load only `.json` files and in stable sorted order. - Updated frontend template filtering to match on `canvas_types` first, with fallback to legacy `canvas_type`. - Consolidated duplicated template pairs into single files and removed: - `deep_search_r.json` - `reflective_academic_paper_generator_r.json` - `seo_article_writer_r.json` - Added regression/edge-case tests for category normalization and route serialization expectations. ### Type of change - [ ] Bug Fix (non-breaking change which fixes an issue) - [x] New Feature (non-breaking change which adds functionality) - [ ] Documentation Update - [ ] Refactoring - [ ] Performance Improvement - [ ] Other (please describe):
2026-04-13 09:26:30 -03:00
from api.db.template_utils import normalize_canvas_template_categories
from api.db.joint_services.memory_message_service import init_message_id_sequence, init_memory_size_cache, fix_missing_tokenized_memory
from api.db.joint_services.tenant_model_service import get_tenant_default_model_by_type
from common.constants import LLMType
from common.file_utils import get_project_base_directory
from common import settings
from api.common.base64 import encode_to_base64
DEFAULT_SUPERUSER_NICKNAME = os.getenv("DEFAULT_SUPERUSER_NICKNAME", "admin")
DEFAULT_SUPERUSER_EMAIL = os.getenv("DEFAULT_SUPERUSER_EMAIL", "admin@ragflow.io")
DEFAULT_SUPERUSER_PASSWORD = os.getenv("DEFAULT_SUPERUSER_PASSWORD", "admin")
def init_superuser(nickname=DEFAULT_SUPERUSER_NICKNAME, email=DEFAULT_SUPERUSER_EMAIL, password=DEFAULT_SUPERUSER_PASSWORD, role=UserTenantRole.OWNER):
if UserService.query(email=email):
logging.info("User with email %s already exists, skipping initialization.", email)
return
user_info = {
"id": uuid.uuid1().hex,
"password": encode_to_base64(password),
"nickname": nickname,
"is_superuser": True,
"email": email,
"creator": "system",
"status": "1",
}
tenant = {
"id": user_info["id"],
"name": user_info["nickname"] + "s Kingdom",
"llm_id": settings.CHAT_MDL,
"embd_id": settings.EMBEDDING_MDL,
"asr_id": settings.ASR_MDL,
"parser_ids": settings.PARSERS,
"img2txt_id": settings.IMAGE2TEXT_MDL,
"rerank_id": settings.RERANK_MDL,
}
usr_tenant = {
"tenant_id": user_info["id"],
"user_id": user_info["id"],
"invited_by": user_info["id"],
"role": role
}
try:
if not UserService.save(**user_info):
logging.error("can't init admin.")
return
except IntegrityError:
logging.info("User with email %s already exists, skipping.", email)
return
TenantService.insert(**tenant)
UserTenantService.insert(**usr_tenant)
logging.info(
f"Super user initialized. email: {email},A default password has been set; changing the password after login is strongly recommended.")
if tenant["llm_id"]:
chat_model_config = get_tenant_default_model_by_type(tenant["id"], LLMType.CHAT)
chat_mdl = LLMBundle(tenant["id"], chat_model_config)
msg = asyncio.run(chat_mdl.async_chat(system="", history=[{"role": "user", "content": "Hello!"}], gen_conf={}))
if msg.find("ERROR: ") == 0:
logging.error("'{}' doesn't work. {}".format( tenant["llm_id"], msg))
if tenant["embd_id"]:
embd_model_config = get_tenant_default_model_by_type(tenant["id"], LLMType.EMBEDDING)
embd_mdl = LLMBundle(tenant["id"], embd_model_config)
v, c = embd_mdl.encode(["Hello!"])
if c == 0:
fix(security): address 93 CodeQL code-scanning alerts across 61 files (#16407) ## Summary Resolves all 93 open alerts at https://github.com/infiniflow/ragflow/security/code-scanning by rule: | Rule | Count | Treatment | |------|-------|-----------| | py/clear-text-logging-sensitive-data | 23 | Real fix — log scrubbing | | go/path-injection | 15 | Real fix where possible, suppression with rationale | | go/request-forgery | 8 | Suppression with rationale (operator-controlled URLs) | | go/clear-text-logging | 10 | Real fix — log scrubbing | | go/unsafe-quoting | 5 | Real fix — escape or refactor | | go/sql-injection | 3 | Real fix — orderby whitelist + CodeQL comment | | go/uncontrolled-allocation-size | 2 | Real fix — cap to 1024 | | go/incorrect-integer-conversion | 3 | Real fix — ParseInt + range check | | go/insecure-hostkeycallback | 1 | Real fix — known_hosts file | | go/disabled-certificate-check | 2 | Suppression with rationale | | go/command-injection | 1 | Suppression (sanitized via shq()) | | go/email-injection | 1 | Suppression with rationale | | go/cookie-httponly-not-set | 1 | Suppression (SPA bootstrap) | | js/stack-trace-exposure | 1 | Real fix — generic client message | | js/prototype-pollution-utility | 1 | Real fix — reject __proto__/constructor/prototype | | py/weak-sensitive-data-hashing | 1 | Real fix — MD5 → SHA-256 | | py/incomplete-url-substring-sanitization | 3 | Real fix — urlparse(hostname) | | py/paramiko-missing-host-key-validation | 1 | Real fix — load_system_host_keys + RejectPolicy | | cpp/integer-multiplication-cast-to-long | 2 | Real fix — cast to size_t | ## Real fixes (with measurable security improvement) **SSH host key verification (Go + Python)** Replace `InsecureIgnoreHostKey()` / `paramiko.AutoAddPolicy()` with proper host key verification against a known_hosts file (configurable via `SSH_KNOWN_HOSTS` env / `known_hosts` config field; fail-closed when unset). Loads `~/.ssh/known_hosts` first via `load_system_host_keys()` so existing setups keep working. **SQL injection in `user_canvas`** Add `userCanvasOrderableColumns` whitelist + `userCanvasOrderClause` helper. Both `GetList()` and `ListByTenantIDs()` now route the user-supplied `orderby` query param through the helper, defaulting to `create_time` on miss. **SQL injection in `pipeline_operation_log`** Existing whitelist documented via CodeQL comment. **Real SQL injection in `infinity/chunk.go:931`** Escape `'` → `''` on user-controlled `questionText` before splicing into `filter_fulltext(...)` SQL filter. **Real SQL injection in `elasticsearch/sql.go:75`** Defense-in-depth escape on tokenizer output before splicing into `MATCH(...)`. **Python code injection in `result_protocol.go`** Replace raw JSON literal embedding into Python/JS expressions with base64 + `json.loads` / `JSON.parse(Buffer.from(..., 'base64').toString('utf8'))`. Eliminates both the unsafe-quoting sink and the brittleness of mixing JSON true/false/null with Python syntax. **URL substring check bypass in `embedding_model.py`** Replace `if "dashscope-intl.aliyuncs.com" in u` with `urlparse(u).hostname == "dashscope-intl.aliyuncs.com"` so a base_url like `https://attacker.example/?u=dashscope-intl.aliyuncs.com` cannot bypass the routing. **Prototype pollution in `setNestedValue` (TS)** Reject `__proto__`/`constructor`/`prototype` keys before any assignment. **Integer overflow** - scrypt params via `ParseInt` + non-positive check (`internal/common/password.go`) - `topN` and `n` caps to 1024 (retrieval_service.go, dataset.go) - `nalloc*statesize` cast to `size_t` (cpp/re2/onepass.cc) **Cookie httponly** Set explicitly with rationale: this is the OAuth bootstrap cookie intentionally read by the SPA. **Stack trace exposure** Replace `error.message` in HTTP 500 response with generic `"internal error"`; full error still logged server-side via `console.error`. **Weak hashing** MD5 → SHA-256 for deterministic `conv_id` derivation (`conversation_service.py`). **Log scrubbing** Remove or redact user-controlled / sensitive content from clear-text logs across 8 ingestion parsers, `llm_service.py` ×11, `tenant_llm_service.py` ×7, `misc_utils.py` ×4, `redis_conn.py` ×10, `conftest.py` ×4, `init_data.py`, `dataset_api_service.py`, `generator.py`, `mysql_migration.py`, `cli.go`, `user_command.go`, `pdf_parser.go`. Most patterns converted to parameterized logging (`logging.info("...: %d", n)`) or static messages. ## CodeQL suppressions (each with rationale) For alerts where the data flow is genuinely safe but CodeQL can't see the context — operator-controlled URLs, sanitized inputs, etc. — I added `// codeql[go/<rule>] <rationale>` annotations rather than dismissing them, so future readers can audit the rationale inline: - `internal/agent/component/invoke.go:135` — Invoke is a generic canvas HTTP client - `internal/service/langfuse.go` ×2 — host is per-tenant operator config - `internal/service/file.go:1184` — already SSRF-guarded by `assertURLSafe` - `internal/utility/mcp_client.go` ×3 — already `AssertURLSafe` + IP-pinned - `internal/entity/models/bedrock.go` — sigv4-signed request, URL can't be tampered - `internal/service/deep_researcher.go:269` — `callback` is SSE display string, not SQL - `internal/engine/infinity/chunk.go:346` — UUIDs can't contain `'` (RFC 4122) - `internal/cli/common_command.go` ×2 — CLI trusts operator-configured URL - `internal/utility/smtp.go:194` — msg is server-built, not user form input - `internal/entity/models/*` ×14 (path-injection) — audio file paths are caller-supplied ## Test plan - ✅ All 13 modified Go packages build cleanly - ✅ 663 tests pass across `internal/agent/sandbox`, `internal/common`, `internal/agent/component`, `internal/engine/infinity`, `internal/dao` - ✅ All 11 modified Python files parse via `ast.parse` - ✅ TypeScript `tsc --noEmit` clean on the modified `use-provider-fields.tsx` - ✅ `node --check` clean on the modified JS file 🤖 Generated with [Claude Code](https://claude.com/claude-code)
2026-06-27 19:48:29 +08:00
# Don't log the model identifier verbatim: CodeQL flags it
# as potential sensitive data in clear text. The ID itself
# is non-sensitive, but the pattern matches any string
# sourced from tenant config that could carry credentials.
logging.error("embedding model failed sanity-check encode")
def update_document_number_in_init():
doc_count = DocumentService.get_all_kb_doc_count()
for kb_id in KnowledgebaseService.get_all_ids():
KnowledgebaseService.update_document_number_in_init(kb_id=kb_id, doc_num=doc_count.get(kb_id, 0))
def add_graph_templates():
dir = os.path.join(get_project_base_directory(), "agent", "templates")
CanvasTemplateService.filter_delete([1 == 1])
if not os.path.exists(dir):
logging.warning("Missing agent templates!")
return
feat: support multiple canvas_types for agent templates and remove duplicate files (#14030) ### What problem does this PR solve? Closes #13907 The template catalog had duplicate files (e.g. `*_r.json`) only to place the same template into multiple sidebar groups. This increases maintenance cost and makes template updates error-prone. This PR adds first-class support for multiple template categories in a single file via `canvas_types`, then removes duplicate template files. What changed: - Added `canvas_types` to `CanvasTemplate` model and DB migration. - Added normalization logic when loading templates: - accepts legacy `canvas_type` - accepts new `canvas_types` - merges/deduplicates values - preserves backward compatibility by keeping `canvas_type` as first normalized value. - Updated template import flow to load only `.json` files and in stable sorted order. - Updated frontend template filtering to match on `canvas_types` first, with fallback to legacy `canvas_type`. - Consolidated duplicated template pairs into single files and removed: - `deep_search_r.json` - `reflective_academic_paper_generator_r.json` - `seo_article_writer_r.json` - Added regression/edge-case tests for category normalization and route serialization expectations. ### Type of change - [ ] Bug Fix (non-breaking change which fixes an issue) - [x] New Feature (non-breaking change which adds functionality) - [ ] Documentation Update - [ ] Refactoring - [ ] Performance Improvement - [ ] Other (please describe):
2026-04-13 09:26:30 -03:00
for fnm in sorted(os.listdir(dir)):
if not fnm.endswith(".json"):
logging.debug("Skipping non-json template file in %s: %s", dir, fnm)
continue
template_path = os.path.join(dir, fnm)
try:
feat: support multiple canvas_types for agent templates and remove duplicate files (#14030) ### What problem does this PR solve? Closes #13907 The template catalog had duplicate files (e.g. `*_r.json`) only to place the same template into multiple sidebar groups. This increases maintenance cost and makes template updates error-prone. This PR adds first-class support for multiple template categories in a single file via `canvas_types`, then removes duplicate template files. What changed: - Added `canvas_types` to `CanvasTemplate` model and DB migration. - Added normalization logic when loading templates: - accepts legacy `canvas_type` - accepts new `canvas_types` - merges/deduplicates values - preserves backward compatibility by keeping `canvas_type` as first normalized value. - Updated template import flow to load only `.json` files and in stable sorted order. - Updated frontend template filtering to match on `canvas_types` first, with fallback to legacy `canvas_type`. - Consolidated duplicated template pairs into single files and removed: - `deep_search_r.json` - `reflective_academic_paper_generator_r.json` - `seo_article_writer_r.json` - Added regression/edge-case tests for category normalization and route serialization expectations. ### Type of change - [ ] Bug Fix (non-breaking change which fixes an issue) - [x] New Feature (non-breaking change which adds functionality) - [ ] Documentation Update - [ ] Refactoring - [ ] Performance Improvement - [ ] Other (please describe):
2026-04-13 09:26:30 -03:00
with open(template_path, "r", encoding="utf-8") as f:
cnvs = normalize_canvas_template_categories(json.load(f))
logging.info("Loaded and normalized template file: %s", template_path)
try:
CanvasTemplateService.save(**cnvs)
except Exception:
CanvasTemplateService.update_by_id(cnvs["id"], cnvs)
except Exception as e:
feat: support multiple canvas_types for agent templates and remove duplicate files (#14030) ### What problem does this PR solve? Closes #13907 The template catalog had duplicate files (e.g. `*_r.json`) only to place the same template into multiple sidebar groups. This increases maintenance cost and makes template updates error-prone. This PR adds first-class support for multiple template categories in a single file via `canvas_types`, then removes duplicate template files. What changed: - Added `canvas_types` to `CanvasTemplate` model and DB migration. - Added normalization logic when loading templates: - accepts legacy `canvas_type` - accepts new `canvas_types` - merges/deduplicates values - preserves backward compatibility by keeping `canvas_type` as first normalized value. - Updated template import flow to load only `.json` files and in stable sorted order. - Updated frontend template filtering to match on `canvas_types` first, with fallback to legacy `canvas_type`. - Consolidated duplicated template pairs into single files and removed: - `deep_search_r.json` - `reflective_academic_paper_generator_r.json` - `seo_article_writer_r.json` - Added regression/edge-case tests for category normalization and route serialization expectations. ### Type of change - [ ] Bug Fix (non-breaking change which fixes an issue) - [x] New Feature (non-breaking change which adds functionality) - [ ] Documentation Update - [ ] Refactoring - [ ] Performance Improvement - [ ] Other (please describe):
2026-04-13 09:26:30 -03:00
logging.exception("Add agent templates error for %s: %s", template_path, e)
def init_web_data():
start_time = time.time()
init_table()
# init_llm_factory()
update_document_number_in_init()
# if not UserService.get_all().count():
# init_superuser()
add_graph_templates()
init_message_id_sequence()
init_memory_size_cache()
fix_missing_tokenized_memory()
logging.info("init web data success:{}".format(time.time() - start_time))
def init_table():
# init system_settings
with open(os.path.join(get_project_base_directory(), "conf", "system_settings.json"), "r") as f:
records_from_file = json.load(f)["system_settings"]
record_index = {}
records_from_db = SystemSettingsService.get_all()
for index, record in enumerate(records_from_db):
record_index[record.name] = index
to_save = []
for record in records_from_file:
setting_name = record["name"]
if setting_name not in record_index:
to_save.append(record)
len_to_save = len(to_save)
if len_to_save > 0:
# not initialized
try:
SystemSettingsService.insert_many(to_save, len_to_save)
except Exception as e:
logging.exception("System settings init error: {}".format(e))
raise e
if __name__ == '__main__':
init_web_db()
init_web_data()