DB-GPT
DB-GPT copied to clipboard
eosphoros-ai
[BUG]: NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE. (error_code: 4)
按照知乎和 Readme 的部署教程，部署并运行服务器后出现如下的错误：
2023-05-19 18:30:05 | INFO | webserver | args: Namespace(host='0.0.0.0', port=None, concurrency_count=10, model_list_mode='once', share=False)
2023-05-19 18:30:05 | INFO | stdout | /root/DB-GPT
2023-05-19 18:30:05 | INFO | stdout | Allowlisted Plugins: []
2023-05-19 18:30:05 | DEBUG | LOGGER | Allowlisted Plugins: []
2023-05-19 18:30:05 | INFO | stdout | Denylisted Plugins: []
2023-05-19 18:30:05 | DEBUG | LOGGER | Denylisted Plugins: []
2023-05-19 18:30:05 | INFO | webserver | Namespace(host='0.0.0.0', port=None, concurrency_count=10, model_list_mode='once', share=False)
2023-05-19 18:30:06 | ERROR | stderr | /root/miniconda3/envs/dbgpt_env/lib/python3.10/site-packages/gradio/deprecation.py:43: UserWarning: You have unused kwarg parameters in File, please remove them: {'accept_multiple_files': True}
2023-05-19 18:30:06 | ERROR | stderr | warnings.warn(
2023-05-19 18:30:06 | INFO | stdout | Running on local URL: http://0.0.0.0:7860
2023-05-19 18:30:06 | INFO | stdout |
2023-05-19 18:30:06 | INFO | stdout | To create a public link, set `share=True` in `launch()`.
docker运行正常
root@iZ2zeh:~/DB-GPT# docker ps
CONTAINER ID IMAGE COMMAND CREATED STATUS PORTS NAMES
453c07fd68fb mysql:latest "docker-entrypoint.s…" 2 hours ago Up 2 hours 0.0.0.0:3306->3306/tcp, :::3306->3306/tcp, 33060/tcp mysql
如果此时提问则会报错：
同时日志信息：
2023-05-19 18:31:17 | INFO | stdout | 是否是AUTO-GPT模式. False
2023-05-19 18:31:17 | INFO | webserver | Requert:
{'model': 'vicuna-13b', 'prompt': "A chat between a curious user and an artificial intelligence assistant, who very familiar with database related knowledge. The assistant gives helpful, detailed, professional and polite answers to the user's questions. ###USER: What are the key differences between mysql and postgres?###Assistant: MySQL and PostgreSQL are both popular open-source relational database management systems (RDBMS) that have many similarities but also some differences. Here are some key differences: \n1. Data Types: PostgreSQL has a more extensive set of data types, including support for array, hstore, JSON, and XML, whereas MySQL has a more limited set.\n2. ACID compliance: Both MySQL and PostgreSQL support ACID compliance (Atomicity, Consistency, Isolation, Durability), but PostgreSQL is generally considered to be more strict in enforcing it.\n3. Replication: MySQL has a built-in replication feature, which allows you to replicate data across multiple servers,whereas PostgreSQL has a similar feature, but it is not as mature as MySQL's.\n4. Performance: MySQL is generally considered to be faster and more efficient in handling large datasets, whereas PostgreSQL is known for its robustness and reliability.\n5. Licensing: MySQL is licensed under the GPL (General Public License), which means that it is free and open-source software, whereas PostgreSQL is licensed under the PostgreSQL License, which is also free and open-source but with different terms.\nUltimately, the choice between MySQL and PostgreSQL depends on the specific needs and requirements of your application. Both are excellent database management systems, and choosing the right one for your project requires careful consideration of your application's requirements, performance needs, and scalability.###USER: hi###Assistant:", 'temperature': 0.7, 'max_new_tokens': 512, 'stop': '###'}
看着是后端服务没连上，copy一下.env.template 到.env 修改里面的MODEL_SERVER=http://127.0.0.1:8000
必须用GPU才可以推理吗？
同样的配置网页上出现同样的错误 NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE. (error_code: 4)
LLMSERVER 错误日志
###USER: select all record in the table###Assistant: In
LlamaForCausalLM(
(model): LlamaModel(
(embed_tokens): Embedding(32001, 5120, padding_idx=0)
(layers): ModuleList(
(0-39): 40 x LlamaDecoderLayer(
(self_attn): LlamaAttention(
(q_proj): CLinear()
(k_proj): CLinear()
(v_proj): CLinear()
(o_proj): CLinear()
(rotary_emb): LlamaRotaryEmbedding()
)
(mlp): LlamaMLP(
(gate_proj): CLinear()
(down_proj): CLinear()
(up_proj): CLinear()
(act_fn): SiLUActivation()
)
(input_layernorm): LlamaRMSNorm()
(post_attention_layernorm): LlamaRMSNorm()
)
)
(norm): LlamaRMSNorm()
)
(lm_head): CLinear()
) LlamaTokenizer(name_or_path='/home/runner/gpt/DB-GPT/models/vicuna-13b', vocab_size=32000, model_max_length=1000000000000000019884624838656, is_fast=False, padding_side='right', truncation_side='right', special_tokens={'bos_token': AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=True), 'eos_token': AddedToken("", rstrip=False, lstrip=False, single_word=False, normalized=True), 'unk_token': AddedToken("
- Data Types: PostgreSQL has a more extensive set of data types, including support for array, hstore, JSON, and XML, whereas MySQL has a more limited set.
- ACID compliance: Both MySQL and PostgreSQL support ACID compliance (Atomicity, Consistency, Isolation, Durability), but PostgreSQL is generally considered to be more strict in enforcing it.
- Replication: MySQL has a built-in replication feature, which allows you to replicate data across multiple servers,whereas PostgreSQL has a similar feature, but it is not as mature as MySQL's.
- Performance: MySQL is generally considered to be faster and more efficient in handling large datasets, whereas PostgreSQL is known for its robustness and reliability.
- Licensing: MySQL is licensed under the GPL (General Public License), which means that it is free and open-source software, whereas PostgreSQL is licensed under the PostgreSQL License, which is also free and open-source but with different terms. Ultimately, the choice between MySQL and PostgreSQL depends on the specific needs and requirements of your application. Both are excellent database management systems, and choosing the right one for your project requires careful consideration of your application's requirements, performance needs, and scalability.###USER: select all records in table###Assistant: To
WEBSERVER错误日志
(dbgpt_env) [runner@localhost server]$ python webserver.py
playsound is relying on another python subprocess. Please use pip install pygobject if you want playsound to run more efficiently.
2023-05-24 19:28:14 | INFO | webserver | args: Namespace(host='0.0.0.0', port=None, concurrency_count=10, model_list_mode='once', share=False)
2023-05-24 19:28:14 | INFO | stdout | /home/runner/gpt/DB-GPT/pilot/server
2023-05-24 19:28:14 | INFO | stdout | Allowlisted Plugins: []
2023-05-24 19:28:14 | DEBUG | LOGGER | Allowlisted Plugins: []
2023-05-24 19:28:14 | INFO | stdout | Denylisted Plugins: []
2023-05-24 19:28:14 | DEBUG | LOGGER | Denylisted Plugins: []
2023-05-24 19:28:14 | INFO | webserver | Namespace(host='0.0.0.0', port=None, concurrency_count=10, model_list_mode='once', share=False)
2023-05-24 19:28:16 | ERROR | stderr | /home/runner/.conda/envs/dbgpt_env/lib/python3.10/site-packages/gradio/deprecation.py:43: UserWarning: You have unused kwarg parameters in File, please remove them: {'accept_multiple_files': True}
2023-05-24 19:28:16 | ERROR | stderr | warnings.warn(
2023-05-24 19:28:16 | INFO | stdout | Running on local URL: http://0.0.0.0:7860
2023-05-24 19:28:16 | INFO | stdout |
2023-05-24 19:28:16 | INFO | stdout | To create a public link, set share=True in launch().
2023-05-24 19:28:57 | INFO | webserver | load_demo. ip: 127.0.0.1. params: {'__theme': 'dark'}
2023-05-24 19:29:25 | INFO | webserver | add_text. ip: 127.0.0.1. len: 27
2023-05-24 19:29:25 | INFO | stdout | 是否是AUTO-GPT模式. False
2023-05-24 19:29:25 | INFO | webserver | Requert:
{'model': 'vicuna-13b', 'prompt': "A chat between a curious user and an artificial intelligence assistant, who very familiar with database related knowledge. The assistant gives helpful, detailed, professional and polite answers to the user's questions. ###USER: What are the key differences between mysql and postgres?###Assistant: MySQL and PostgreSQL are both popular open-source relational database management systems (RDBMS) that have many similarities but also some differences. Here are some key differences: \n1. Data Types: PostgreSQL has a more extensive set of data types, including support for array, hstore, JSON, and XML, whereas MySQL has a more limited set.\n2. ACID compliance: Both MySQL and PostgreSQL support ACID compliance (Atomicity, Consistency, Isolation, Durability), but PostgreSQL is generally considered to be more strict in enforcing it.\n3. Replication: MySQL has a built-in replication feature, which allows you to replicate data across multiple servers,whereas PostgreSQL has a similar feature, but it is not as mature as MySQL's.\n4. Performance: MySQL is generally considered to be faster and more efficient in handling large datasets, whereas PostgreSQL is known for its robustness and reliability.\n5. Licensing: MySQL is licensed under the GPL (General Public License), which means that it is free and open-source software, whereas PostgreSQL is licensed under the PostgreSQL License, which is also free and open-source but with different terms.\nUltimately, the choice between MySQL and PostgreSQL depends on the specific needs and requirements of your application. Both are excellent database management systems, and choosing the right one for your project requires careful consideration of your application's requirements, performance needs, and scalability.###USER: select all records in table###Assistant:", 'temperature': 0.7, 'max_new_tokens': 512, 'stop': '###'}
知道咋回事了。要先起一个llmserver.py的服务，再开个窗口运行webserver.py，这个webserver.py要请求llmserver.py里的服务的。
看起来是个超时错误。 如果llm server跑的是cpu，就会超时。 我的4090拉最新代码起不来gpu了。
也是出这个错误，即使是跑在纯cpu模式下。
