无法收到GPT3/GPT4消息,反复打印:ERROR: [uvicorn.error] ASGI callable returned without starting response.
tudoujunha opened this issue · comments
Version
v0.4.5
What's your deploying environment?
- Docker
- Caddy
- Other
Describe the problem
前端页面一直报错:Request Error,发送GPT3/GPT4消息无法接收到回复,chatgpt官网上可以看到发送出去的消息,但cws收不到回复,控制台一直在打印( ERROR: [uvicorn.error] ASGI callable returned without starting response.),貌似原因是(ASGI 在返回响应之前就已经结束了,但并没有正确地启动 HTTP 响应过程)
Expected behavior
cws不再提示Request Error错误, 不再提示 ERROR: [uvicorn.error] ASGI callable returned without starting response.
cws 发送 GPT3/GPT4消息能正常接收到回复。
Your config.yaml or other configurations
openai_web:
enabled: true
is_plus_account: true
chatgpt_base_url: http://192.168.10.210:7999/backend-api/
proxy:
common_timeout: 20
ask_timeout: 600
sync_conversations_on_startup: false
sync_conversations_schedule: false
sync_conversations_schedule_interval_hours: 12
enabled_models:
- gpt_3_5
- gpt_4
- gpt_4_plugins
model_code_mapping:
gpt_3_5: text-davinci-002-render-sha
gpt_3_5_mobile: text-davinci-002-render-sha-mobile
gpt_4: gpt-4
gpt_4_mobile: gpt-4-mobile
gpt_4_browsing: gpt-4-browsing
gpt_4_plugins: gpt-4-plugins
gpt_4_code_interpreter: gpt-4-code-interpreter
gpt_4_dalle: gpt-4-dalle
file_upload_strategy: browser_upload_only
disable_uploading: false
openai_api:
enabled: true
openai_base_url: https://api.openai.com/v1/
proxy:
connect_timeout: 10
read_timeout: 20
enabled_models: - gpt_3_5
- gpt_4
model_code_mapping:
gpt_3_5: gpt-3.5-turbo
gpt_4: gpt-4
common:
print_sql: false
create_initial_admin_user: true
initial_admin_user_username: admin
initial_admin_user_password: password
http:
host: 127.0.0.1
port: 8000
cors_allow_origins: - http://localhost:8000
- http://localhost:5173
- http://127.0.0.1:8000
- http://127.0.0.1:5173
data:
data_dir: ./data
database_url: sqlite+aiosqlite:///data/database.db
mongodb_url: mongodb://cws:password@192.168.10.210:27017
mongodb_db_name: cws
run_migration: false
max_file_upload_size: 104857600
auth:
jwt_secret: AEkoNSKzlSCNXSHm
jwt_lifetime_seconds: 259200
cookie_max_age: 259200
user_secret: cijBt7QbSRBZsiOU
stats:
ask_stats_ttl: 7776000
request_stats_ttl: 2592000
request_stats_filter_keywords: - /status
log:
console_log_level: INFO
Docker compose:
version: "3"
services:
chatgpt-web-share:
image: ghcr.io/chatpire/chatgpt-web-share:latest
container_name: cws
restart: unless-stopped
ports:
- 5000:80
volumes:
- ./data:/app/backend/data
environment:
- TZ=${TZ}
- CWS_CONFIG_DIR=/app/backend/data/config
depends_on:
- mongo
mongo:
container_name: mongo
image: mongo:6.0
restart: always
ports:
- 27017:27017
volumes:
- ./mongo_data:/data/db
environment:
MONGO_INITDB_DATABASE: ${MONGO_INITDB_DATABASE}
MONGO_INITDB_ROOT_USERNAME: ${MONGO_INITDB_ROOT_USERNAME}
MONGO_INITDB_ROOT_PASSWORD: ${MONGO_INITDB_ROOT_PASSWORD}
ninja:
image: ghcr.io/gngpp/ninja:latest
container_name: ninja
restart: unless-stopped
command: run
ports:
- "7999:7999"
environment:
- TZ=Asia/Shanghai
volumes:
- "./har/gpt3:/root/.ninja/gpt3"
- "./har/gpt4:/root/.ninja/gpt4"
Additional context
补充 database.db 和 config.yaml,按照文档配置的,密码都没改.
db&config.zip
一样的问题,昨天还是正常的,今天就不行了,可能是GPT修改了什么东西,但是没有同步
更新到最新版本重试一下
更新到最新版本重试一下
最新版本一样现象