mirror of
https://github.com/csunny/DB-GPT.git
synced 2025-07-30 15:21:02 +00:00
Merge remote-tracking branch 'origin/main' into feat_rag_graph
This commit is contained in:
aries_ckt
commit
07ad8fac67
@ -23,6 +23,15 @@ WEB_SERVER_PORT=7860
|
||||
#*******************************************************************#
|
||||
# LLM_MODEL, see /pilot/configs/model_config.LLM_MODEL_CONFIG
|
||||
LLM_MODEL=vicuna-13b-v1.5
|
||||
## LLM model path, by default, DB-GPT will read the model path from LLM_MODEL_CONFIG based on the LLM_MODEL.
|
||||
## Of course you can specify your model path according to LLM_MODEL_PATH
|
||||
## In DB-GPT, the priority from high to low to read model path:
|
||||
## 1. environment variable with key: {LLM_MODEL}_MODEL_PATH (Avoid multi-model conflicts)
|
||||
## 2. environment variable with key: MODEL_PATH
|
||||
## 3. environment variable with key: LLM_MODEL_PATH
|
||||
## 4. the config in /pilot/configs/model_config.LLM_MODEL_CONFIG
|
||||
# LLM_MODEL_PATH=/app/models/vicuna-13b-v1.5
|
||||
# LLM_PROMPT_TEMPLATE=vicuna_v1.1
|
||||
MODEL_SERVER=http://127.0.0.1:8000
|
||||
LIMIT_MODEL_CONCURRENCY=5
|
||||
MAX_POSITION_EMBEDDINGS=4096
|
||||
|
||||
30
README.md
30
README.md
@ -25,8 +25,8 @@
|
||||
<a href="https://github.com/eosphoros-ai/DB-GPT/issues">
|
||||
<img alt="Open Issues" src="https://img.shields.io/github/issues-raw/eosphoros-ai/DB-GPT" />
|
||||
</a>
|
||||
<a href="https://discord.gg/vqBrcV7Nd">
|
||||
<img alt="Discord" src="https://dcbadge.vercel.app/api/server/vqBrcV7Nd?compact=true&style=flat" />
|
||||
<a href="https://discord.gg/nASQyBjvY">
|
||||
<img alt="Discord" src="https://dcbadge.vercel.app/api/server/nASQyBjvY?compact=true&style=flat" />
|
||||
</a>
|
||||
<a href="https://codespaces.new/eosphoros-ai/DB-GPT">
|
||||
<img alt="Open in GitHub Codespaces" src="https://github.com/codespaces/badge.svg" />
|
||||
@ -34,7 +34,7 @@
|
||||
</p>
|
||||
|
||||
|
||||
[**简体中文**](README.zh.md) |[**Discord**](https://discord.gg/vqBrcV7Nd) |[**Documents**](https://db-gpt.readthedocs.io/en/latest/)|[**Wechat**](https://github.com/eosphoros-ai/DB-GPT/blob/main/README.zh.md#%E8%81%94%E7%B3%BB%E6%88%91%E4%BB%AC)|[**Community**](https://github.com/eosphoros-ai/community)
|
||||
[**简体中文**](README.zh.md) |[**Discord**](https://discord.gg/nASQyBjvY) |[**Documents**](https://db-gpt.readthedocs.io/en/latest/)|[**Wechat**](https://github.com/eosphoros-ai/DB-GPT/blob/main/README.zh.md#%E8%81%94%E7%B3%BB%E6%88%91%E4%BB%AC)|[**Community**](https://github.com/eosphoros-ai/community)
|
||||
</div>
|
||||
|
||||
## What is DB-GPT?
|
||||
@ -107,11 +107,11 @@ Currently, we have released multiple key features, which are listed below to dem
|
||||
|
||||
- Multi-Agents&Plugins
|
||||
|
||||
Supports custom plug-ins to perform tasks, natively supports the Auto-GPT plug-in model, and the Agents protocol adopts the Agent Protocol standard
|
||||
It supports custom plug-ins to perform tasks, natively supports the Auto-GPT plug-in model, and the Agents protocol adopts the Agent Protocol standard.
|
||||
|
||||
- Fine-tuning text2SQL
|
||||
|
||||
An automated fine-tuning lightweight framework built around large language models, Text2SQL data sets, LoRA/QLoRA/Pturning and other fine-tuning methods, making TextSQL fine-tuning as convenient as an assembly line. [DB-GPT-Hub](https://github.com/eosphoros-ai/DB-GPT-Hub)
|
||||
An automated fine-tuning lightweight framework built around large language models, Text2SQL data sets, LoRA/QLoRA/Pturning, and other fine-tuning methods, making TextSQL fine-tuning as convenient as an assembly line. [DB-GPT-Hub](https://github.com/eosphoros-ai/DB-GPT-Hub)
|
||||
|
||||
- Multi LLMs Support, Supports multiple large language models, currently supporting
|
||||
|
||||
@ -141,7 +141,7 @@ Currently, we have released multiple key features, which are listed below to dem
|
||||
- [Llama2-Chinese-13b-Chat](https://huggingface.co/FlagAlpha/Llama2-Chinese-13b-Chat)
|
||||
- [OpenLLaMa OpenInstruct](https://huggingface.co/VMware/open-llama-7b-open-instruct)
|
||||
|
||||
etc.
|
||||
Etc.
|
||||
|
||||
- Support API Proxy LLMs
|
||||
- [x] [ChatGPT](https://api.openai.com/)
|
||||
@ -151,14 +151,14 @@ Currently, we have released multiple key features, which are listed below to dem
|
||||
|
||||
- Privacy and security
|
||||
|
||||
The privacy and security of data are ensured through various technologies such as privatized large models and proxy desensitization.
|
||||
The privacy and security of data are ensured through various technologies, such as privatized large models and proxy desensitization.
|
||||
|
||||
- Support Datasources
|
||||
|
||||
| DataSource | support | Notes |
|
||||
| ------------------------------------------------------------------------------ | ----------- | ------------------------------------------- |
|
||||
| [MySQL](https://www.mysql.com/) | Yes | |
|
||||
| [PostgresSQL](https://www.postgresql.org/) | Yes | |
|
||||
| [PostgreSQL](https://www.postgresql.org/) | Yes | |
|
||||
| [Spark](https://github.com/apache/spark) | Yes | |
|
||||
| [DuckDB](https://github.com/duckdb/duckdb) | Yes | |
|
||||
| [Sqlite](https://github.com/sqlite/sqlite) | Yes | |
|
||||
@ -185,7 +185,7 @@ Is the architecture of the entire DB-GPT shown in the following figure:
|
||||
|
||||
The core capabilities mainly consist of the following parts:
|
||||
1. Multi-Models: Support multi-LLMs, such as LLaMA/LLaMA2、CodeLLaMA、ChatGLM, QWen、Vicuna and proxy model ChatGPT、Baichuan、tongyi、wenxin etc
|
||||
2. Knowledge Based QA: You can perform high-quality intelligent Q&A based on local documents such as pdf, word, excel and other data.
|
||||
2. Knowledge-Based QA: You can perform high-quality intelligent Q&A based on local documents such as PDF, word, excel, and other data.
|
||||
3. Embedding: Unified data vector storage and indexing, Embed data as vectors and store them in vector databases, providing content similarity search.
|
||||
4. Multi-Datasources: Used to connect different modules and data sources to achieve data flow and interaction.
|
||||
5. Multi-Agents: Provides Agent and plugin mechanisms, allowing users to customize and enhance the system's behavior.
|
||||
@ -199,7 +199,7 @@ The core capabilities mainly consist of the following parts:
|
||||
|
||||
### SubModule
|
||||
- [DB-GPT-Hub](https://github.com/eosphoros-ai/DB-GPT-Hub) Text-to-SQL performance by applying Supervised Fine-Tuning (SFT) on large language models.
|
||||
- [DB-GPT-Plugins](https://github.com/eosphoros-ai/DB-GPT-Plugins) DB-GPT Plugins, Can run autogpt plugin directly
|
||||
- [DB-GPT-Plugins](https://github.com/eosphoros-ai/DB-GPT-Plugins) DB-GPT Plugins Can run autogpt plugin directly
|
||||
- [DB-GPT-Web](https://github.com/eosphoros-ai/DB-GPT-Web) ChatUI for DB-GPT
|
||||
|
||||
## Image
|
||||
@ -213,7 +213,7 @@ The core capabilities mainly consist of the following parts:
|
||||
|
||||
## Contribution
|
||||
|
||||
- Please run `black .` before submitting the code. contributing guidelines, [how to contribution](https://github.com/csunny/DB-GPT/blob/main/CONTRIBUTING.md)
|
||||
- Please run `black .` before submitting the code. Contributing guidelines, [how to contribution](https://github.com/csunny/DB-GPT/blob/main/CONTRIBUTING.md)
|
||||
|
||||
## RoadMap
|
||||
|
||||
@ -224,7 +224,7 @@ The core capabilities mainly consist of the following parts:
|
||||
### KBQA RAG optimization
|
||||
- [x] Multi Documents
|
||||
- [x] PDF
|
||||
- [x] Excel, csv
|
||||
- [x] Excel, CSV
|
||||
- [x] Word
|
||||
- [x] Text
|
||||
- [x] MarkDown
|
||||
@ -235,7 +235,7 @@ The core capabilities mainly consist of the following parts:
|
||||
- [ ] Graph Database
|
||||
- [ ] Neo4j Graph
|
||||
- [ ] Nebula Graph
|
||||
- [x] Multi Vector Database
|
||||
- [x] Multi-Vector Database
|
||||
- [x] Chroma
|
||||
- [x] Milvus
|
||||
- [x] Weaviate
|
||||
@ -254,7 +254,7 @@ The core capabilities mainly consist of the following parts:
|
||||
|
||||
- Multi Datasource Support
|
||||
- [x] MySQL
|
||||
- [x] PostgresSQL
|
||||
- [x] PostgreSQL
|
||||
- [x] Spark
|
||||
- [x] DuckDB
|
||||
- [x] Sqlite
|
||||
@ -331,7 +331,7 @@ The MIT License (MIT)
|
||||
|
||||
## Contact Information
|
||||
We are working on building a community, if you have any ideas about building the community, feel free to contact us.
|
||||
[](https://discord.gg/vqBrcV7Nd)
|
||||
[](https://discord.gg/nASQyBjvY)
|
||||
|
||||
<p align="center">
|
||||
<img src="./assets/wechat.jpg" width="300px" />
|
||||
|
||||
@ -22,15 +22,15 @@
|
||||
<a href="https://github.com/eosphoros-ai/DB-GPT/issues">
|
||||
<img alt="Open Issues" src="https://img.shields.io/github/issues-raw/csunny/DB-GPT" />
|
||||
</a>
|
||||
<a href="https://discord.gg/vqBrcV7Nd">
|
||||
<img alt="Discord" src="https://dcbadge.vercel.app/api/server/vqBrcV7Nd?compact=true&style=flat" />
|
||||
<a href="https://discord.gg/nASQyBjvY">
|
||||
<img alt="Discord" src="https://dcbadge.vercel.app/api/server/nASQyBjvY?compact=true&style=flat" />
|
||||
</a>
|
||||
<a href="https://codespaces.new/eosphoros-ai/DB-GPT">
|
||||
<img alt="Open in GitHub Codespaces" src="https://github.com/codespaces/badge.svg" />
|
||||
</a>
|
||||
</p>
|
||||
|
||||
[**English**](README.md)|[**Discord**](https://discord.gg/vqBrcV7Nd)|[**文档**](https://db-gpt.readthedocs.io/projects/db-gpt-docs-zh-cn/zh_CN/latest/)|[**微信**](https://github.com/csunny/DB-GPT/blob/main/README.zh.md#%E8%81%94%E7%B3%BB%E6%88%91%E4%BB%AC)|[**社区**](https://github.com/eosphoros-ai/community)
|
||||
[**English**](README.md)|[**Discord**](https://discord.gg/nASQyBjvY)|[**文档**](https://db-gpt.readthedocs.io/projects/db-gpt-docs-zh-cn/zh_CN/latest/)|[**微信**](https://github.com/csunny/DB-GPT/blob/main/README.zh.md#%E8%81%94%E7%B3%BB%E6%88%91%E4%BB%AC)|[**社区**](https://github.com/eosphoros-ai/community)
|
||||
</div>
|
||||
|
||||
## DB-GPT 是什么？
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
LLM USE FAQ
|
||||
==================================
|
||||
##### Q1:how to use openai chatgpt service
|
||||
##### Q1: how to use openai chatgpt service
|
||||
change your LLM_MODEL in `.env`
|
||||
````shell
|
||||
LLM_MODEL=proxyllm
|
||||
@ -15,7 +15,7 @@ PROXY_SERVER_URL=https://api.openai.com/v1/chat/completions
|
||||
|
||||
make sure your openapi API_KEY is available
|
||||
|
||||
##### Q2 What difference between `python dbgpt_server --light` and `python dbgpt_server`
|
||||
##### Q2: What difference between `python dbgpt_server --light` and `python dbgpt_server`
|
||||
```{note}
|
||||
* `python dbgpt_server --light` dbgpt_server does not start the llm service. Users can deploy the llm service separately by using `python llmserver`, and dbgpt_server accesses the llm service through set the LLM_SERVER environment variable in .env. The purpose is to allow for the separate deployment of dbgpt's backend service and llm service.
|
||||
|
||||
@ -35,7 +35,7 @@ python pilot/server/dbgpt_server.py --light
|
||||
```
|
||||
|
||||
|
||||
##### Q3 How to use MultiGPUs
|
||||
##### Q3: How to use MultiGPUs
|
||||
|
||||
DB-GPT will use all available gpu by default. And you can modify the setting `CUDA_VISIBLE_DEVICES=0,1` in `.env` file
|
||||
to use the specific gpu IDs.
|
||||
@ -52,7 +52,7 @@ CUDA_VISIBLE_DEVICES=3,4,5,6 python3 pilot/server/dbgpt_server.py
|
||||
|
||||
You can modify the setting `MAX_GPU_MEMORY=xxGib` in `.env` file to configure the maximum memory used by each GPU.
|
||||
|
||||
##### Q4 Not Enough Memory
|
||||
##### Q4: Not Enough Memory
|
||||
|
||||
DB-GPT supported 8-bit quantization and 4-bit quantization.
|
||||
|
||||
@ -60,9 +60,9 @@ You can modify the setting `QUANTIZE_8bit=True` or `QUANTIZE_4bit=True` in `.env
|
||||
|
||||
Llama-2-70b with 8-bit quantization can run with 80 GB of VRAM, and 4-bit quantization can run with 48 GB of VRAM.
|
||||
|
||||
Note: you need to install the latest dependencies according to [requirements.txt](https://github.com/eosphoros-ai/DB-GPT/blob/main/requirements.txt).
|
||||
Note: you need to install the quantization dependencies with `pip install -e ".[quantization]"`
|
||||
|
||||
##### Q5 How to Add LLM Service dynamic local mode
|
||||
##### Q5: How to Add LLM Service dynamic local mode
|
||||
|
||||
Now DB-GPT through multi-llm service switch, so how to add llm service dynamic,
|
||||
|
||||
@ -75,7 +75,7 @@ eg: dbgpt model start --model_name chatglm2-6b --model_path /root/DB-GPT/models/
|
||||
chatgpt
|
||||
eg: dbgpt model start --model_name chatgpt_proxyllm --model_path chatgpt_proxyllm --proxy_api_key ${OPENAI_KEY} --proxy_server_url {OPENAI_URL}
|
||||
```
|
||||
##### Q6 How to Add LLM Service dynamic in remote mode
|
||||
##### Q6: How to Add LLM Service dynamic in remote mode
|
||||
If you deploy llm service in remote machine instance, and you want to add model service to dbgpt server to manage
|
||||
|
||||
use dbgpt start worker and set --controller_addr.
|
||||
@ -88,13 +88,13 @@ eg: dbgpt start worker --model_name vicuna-13b-v1.5 \
|
||||
|
||||
```
|
||||
|
||||
##### Q7 dbgpt command not found
|
||||
##### Q7: dbgpt command not found
|
||||
|
||||
```commandline
|
||||
pip install -e "pip install -e ".[default]"
|
||||
```
|
||||
|
||||
##### Q8 When starting the worker_manager on a cloud server and registering it with the controller, it is noticed that the worker's exposed IP is a private IP instead of a public IP, which leads to the inability to access the service.
|
||||
##### Q8: When starting the worker_manager on a cloud server and registering it with the controller, it is noticed that the worker's exposed IP is a private IP instead of a public IP, which leads to the inability to access the service.
|
||||
|
||||
```commandline
|
||||
|
||||
@ -103,4 +103,14 @@ pip install -e "pip install -e ".[default]"
|
||||
automatically determined
|
||||
```
|
||||
|
||||
##### Q9: How to customize model path and prompt template
|
||||
|
||||
DB-GPT will read the model path from `pilot.configs.model_config.LLM_MODEL_CONFIG` based on the `LLM_MODEL`.
|
||||
Of course, you can use the environment variable `LLM_MODEL_PATH` to specify the model path and `LLM_PROMPT_TEMPLATE` to specify your model prompt template.
|
||||
|
||||
```
|
||||
LLM_MODEL=vicuna-13b-v1.5
|
||||
LLM_MODEL_PATH=/app/models/vicuna-13b-v1.5
|
||||
# LLM_PROMPT_TEMPLATE=vicuna_v1.1
|
||||
```
|
||||
|
||||
|
||||
@ -59,11 +59,11 @@ Embedding Chunk size, default 500
|
||||
Embedding Chunk Overlap, default 100
|
||||
* KNOWLEDGE_CHUNK_OVERLAP=100
|
||||
|
||||
embeding recall top k,5
|
||||
embedding recall top k,5
|
||||
|
||||
* KNOWLEDGE_SEARCH_TOP_SIZE=5
|
||||
|
||||
embeding recall max token ,2000
|
||||
embedding recall max token ,2000
|
||||
|
||||
* KNOWLEDGE_SEARCH_MAX_TOKEN=5
|
||||
```
|
||||
|
||||
@ -8,7 +8,7 @@ msgid ""
|
||||
msgstr ""
|
||||
"Project-Id-Version: DB-GPT 👏👏 0.3.5\n"
|
||||
"Report-Msgid-Bugs-To: \n"
|
||||
"POT-Creation-Date: 2023-10-20 22:29+0800\n"
|
||||
"POT-Creation-Date: 2023-10-30 11:37+0800\n"
|
||||
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
|
||||
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
|
||||
"Language: zh_CN\n"
|
||||
@ -19,34 +19,36 @@ msgstr ""
|
||||
"Content-Transfer-Encoding: 8bit\n"
|
||||
"Generated-By: Babel 2.12.1\n"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:1 54763acec7da4deb90669195c54ec3a1
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:1 98e23f85313c45169ff2ba7f80193356
|
||||
msgid "LLM USE FAQ"
|
||||
msgstr "LLM模型使用FAQ"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:3 66f73fd2ee7b462e92d3f263792a5e33
|
||||
msgid "Q1:how to use openai chatgpt service"
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:3 0d49acfb4af947cb969b249346b00d33
|
||||
#, fuzzy
|
||||
msgid "Q1: how to use openai chatgpt service"
|
||||
msgstr "我怎么使用OPENAI服务"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:4 9d178d8462b74cb188bbacf2ac2ac12b
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:4 7010fec33e264987a29de86c54da93e8
|
||||
#, fuzzy
|
||||
msgid "change your LLM_MODEL in `.env`"
|
||||
msgstr "通过在.env文件设置LLM_MODEL"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:9 f7ca82f257be4ac09639a7f8af5e83eb
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:9 0982d6d5d0b3434fb00698aaf675f3f3
|
||||
msgid "set your OPENAPI KEY"
|
||||
msgstr "set your OPENAPI KEY"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:16 d6255b20dce34a2690df7e2af3505d97
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:16 63650494c1574de09c007e1d470dd53d
|
||||
msgid "make sure your openapi API_KEY is available"
|
||||
msgstr "确认openapi API_KEY是否可用"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:18 6f1c6dbdb31f4210a6d21f0f3a6ae589
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:18 5721ec71e344499d96c55b7e531d7c08
|
||||
#, fuzzy
|
||||
msgid ""
|
||||
"Q2 What difference between `python dbgpt_server --light` and `python "
|
||||
"Q2: What difference between `python dbgpt_server --light` and `python "
|
||||
"dbgpt_server`"
|
||||
msgstr "Q2 `python dbgpt_server --light` 和 `python dbgpt_server`的区别是什么?"
|
||||
msgstr "Q2: `python dbgpt_server --light` 和 `python dbgpt_server`的区别是什么?"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:20 b839771ae9e34e998b0edf8d69deabdd
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:20 76a650f195dd40b6a3a3564030cdc040
|
||||
msgid ""
|
||||
"`python dbgpt_server --light` dbgpt_server does not start the llm "
|
||||
"service. Users can deploy the llm service separately by using `python "
|
||||
@ -58,75 +60,75 @@ msgstr ""
|
||||
"用户可以通过`python "
|
||||
"llmserver`单独部署模型服务，dbgpt_server通过LLM_SERVER环境变量来访问模型服务。目的是为了可以将dbgpt后台服务和大模型服务分离部署。"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:22 aba39cef6fe84799bcd03e8f36c41296
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:22 8cd87e3504784d9e891e1fb96c79e143
|
||||
msgid ""
|
||||
"`python dbgpt_server` dbgpt_server service and the llm service are "
|
||||
"deployed on the same instance. when dbgpt_server starts the service, it "
|
||||
"also starts the llm service at the same time."
|
||||
msgstr "`python dbgpt_server` 是将后台服务和模型服务部署在同一台实例上.dbgpt_server在启动服务的时候同时开启模型服务."
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:27 c65270d479af49e28e99b35a7932adbd
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:27 58a6eaf57e6d425685f67058b1a642d4
|
||||
msgid ""
|
||||
"If you want to access an external LLM service(deployed by DB-GPT), you "
|
||||
"need to"
|
||||
msgstr "如果模型服务部署(通过DB-GPT部署)在别的机器，想通过dbgpt服务访问模型服务"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:29 da153e6d18c543f28e0c4e85618e3d3d
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:29 67ac8823ca2e49ba9c833368e2cfb53c
|
||||
msgid ""
|
||||
"1.set the variables LLM_MODEL=YOUR_MODEL_NAME, "
|
||||
"MODEL_SERVER=YOUR_MODEL_SERVER（eg:http://localhost:5000） in the .env "
|
||||
"file."
|
||||
msgstr ""
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:31 cd89b8a2075f4407b8036a74151a6377
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:31 e5c066bcdf0649a1b33bbfc7fd3b1a66
|
||||
msgid "2.execute dbgpt_server.py in light mode"
|
||||
msgstr "2.execute dbgpt_server.py light 模式"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:33 8f4b9401ac4f4a25a7479bee9ef5e8c1
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:33 402ff01d7ee94d97be4a0eb964e39b97
|
||||
msgid "python pilot/server/dbgpt_server.py --light"
|
||||
msgstr ""
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:38 69e1064cd7554ce6b49da732f800eacc
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:38 86190c689d8f4d9a9b58d904e0b5867b
|
||||
#, fuzzy
|
||||
msgid "Q3 How to use MultiGPUs"
|
||||
msgstr "Q2 怎么使用 MultiGPUs"
|
||||
msgid "Q3: How to use MultiGPUs"
|
||||
msgstr "Q3: 怎么使用 MultiGPUs"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:40 6de3f105ce96430db5756f38bbd9ca12
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:40 6b08cff88750440b98956203d8b8a084
|
||||
msgid ""
|
||||
"DB-GPT will use all available gpu by default. And you can modify the "
|
||||
"setting `CUDA_VISIBLE_DEVICES=0,1` in `.env` file to use the specific gpu"
|
||||
" IDs."
|
||||
msgstr "DB-GPT默认加载可利用的gpu，你也可以通过修改 在`.env`文件 `CUDA_VISIBLE_DEVICES=0,1`来指定gpu IDs"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:43 87cb9bfb20af4b259d719df797c42a7d
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:43 93b39089e5be4475b9e90e7813f5a7d9
|
||||
msgid ""
|
||||
"Optionally, you can also specify the gpu ID to use before the starting "
|
||||
"command, as shown below:"
|
||||
msgstr "你也可以指定gpu ID启动"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:53 bcfa35cda6304ee5ab9a775a2d4eda63
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:53 62e3074c109d401fa4bf1ddbdc6c7be1
|
||||
msgid ""
|
||||
"You can modify the setting `MAX_GPU_MEMORY=xxGib` in `.env` file to "
|
||||
"configure the maximum memory used by each GPU."
|
||||
msgstr "同时你可以通过在.env文件设置`MAX_GPU_MEMORY=xxGib`修改每个GPU的最大使用内存"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:55 a05c5484927844c8bb4791f0a9ccc82e
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:55 d235bd83545c476f8e12572658d1c723
|
||||
#, fuzzy
|
||||
msgid "Q4 Not Enough Memory"
|
||||
msgstr "Q3 机器显存不够 "
|
||||
msgid "Q4: Not Enough Memory"
|
||||
msgstr "Q4: 机器显存不够 "
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:57 fe17a023b6eb4a92b1b927e1b94e3784
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:57 b3243ed9147f42bba987d7f9b778e66f
|
||||
msgid "DB-GPT supported 8-bit quantization and 4-bit quantization."
|
||||
msgstr "DB-GPT 支持 8-bit quantization 和 4-bit quantization."
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:59 76c3684c10864b8e87e5c2255b6c0b7f
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:59 1ddb9f94ab994bfebfee46d1c19888d4
|
||||
msgid ""
|
||||
"You can modify the setting `QUANTIZE_8bit=True` or `QUANTIZE_4bit=True` "
|
||||
"in `.env` file to use quantization(8-bit quantization is enabled by "
|
||||
"default)."
|
||||
msgstr "你可以通过在.env文件设置`QUANTIZE_8bit=True` or `QUANTIZE_4bit=True`"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:61 c5d849a38f1a4f0687bbcffb6699dc39
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:61 54b85daa3fb24b17b67a6da31d2be8b0
|
||||
msgid ""
|
||||
"Llama-2-70b with 8-bit quantization can run with 80 GB of VRAM, and 4-bit"
|
||||
" quantization can run with 48 GB of VRAM."
|
||||
@ -134,49 +136,77 @@ msgstr ""
|
||||
"Llama-2-70b with 8-bit quantization 可以运行在 80 GB VRAM机器， 4-bit "
|
||||
"quantization可以运行在 48 GB VRAM"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:63 867329a5e3b0403083e96f72b8747fb2
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:63 097d680aed184fee9eceebee55a47ac1
|
||||
msgid ""
|
||||
"Note: you need to install the latest dependencies according to "
|
||||
"[requirements.txt](https://github.com/eosphoros-ai/DB-"
|
||||
"GPT/blob/main/requirements.txt)."
|
||||
"Note: you need to install the quantization dependencies with `pip install"
|
||||
" -e \".[quantization]\"`"
|
||||
msgstr ""
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:65 60ceee25e9fb4ddba40c5306bfb0a82f
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:65 f3a51056043c49eb84471040f2b364aa
|
||||
#, fuzzy
|
||||
msgid "Q5 How to Add LLM Service dynamic local mode"
|
||||
msgstr "Q5 怎样动态新增模型服务"
|
||||
msgid "Q5: How to Add LLM Service dynamic local mode"
|
||||
msgstr "Q5: 怎样动态新增模型服务"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:67 c99eb7f7ae844884a8f0da94238ea7e0
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:67 43ee6b0f23814c94a4ddb2429801a5e1
|
||||
msgid ""
|
||||
"Now DB-GPT through multi-llm service switch, so how to add llm service "
|
||||
"dynamic,"
|
||||
msgstr "DB-GPT支持多个模型服务切换, 怎样添加一个模型服务呢"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:78 cd89b8a2075f4407b8036a74151a6377
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:78 c217bbf0d2b6425fa7a1c691b7704a8d
|
||||
#, fuzzy
|
||||
msgid "Q6 How to Add LLM Service dynamic in remote mode"
|
||||
msgstr "Q5 怎样动态新增模型服务"
|
||||
msgid "Q6: How to Add LLM Service dynamic in remote mode"
|
||||
msgstr "Q6: 怎样动态新增模型服务"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:79 8833ce89465848259b08ef0a4fa68d96
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:79 195bdaa937a94c7aa0d8c6e1a5430d6e
|
||||
msgid ""
|
||||
"If you deploy llm service in remote machine instance, and you want to "
|
||||
"add model service to dbgpt server to manage"
|
||||
msgstr "如果你想在远程机器实例部署大模型服务并添加到本地dbgpt_server进行管理"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:81 992eb37e3cca48829636c15ba3ec2ee8
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:81 c64098b838a94821963a1d16e56497ff
|
||||
msgid "use dbgpt start worker and set --controller_addr."
|
||||
msgstr "使用1`dbgpt start worker`命令并设置注册地址--controller_addr"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:91 0d06d7d6dd3d4780894ecd914c89b5a2
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:91 cb12d5e9d9d24f14abc3ebea877a4b24
|
||||
#, fuzzy
|
||||
msgid "Q7 dbgpt command not found"
|
||||
msgstr "Q6 dbgpt command not found"
|
||||
msgid "Q7: dbgpt command not found"
|
||||
msgstr "Q7: dbgpt command not found"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:97 5d9beed0d95a4503a43d0e025664273b
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:97 f95cdccfa82d4b3eb2a23dd297131faa
|
||||
#, fuzzy
|
||||
msgid ""
|
||||
"Q8 When starting the worker_manager on a cloud server and registering it "
|
||||
"with the controller, it is noticed that the worker's exposed IP is a "
|
||||
"Q8: When starting the worker_manager on a cloud server and registering it"
|
||||
" with the controller, it is noticed that the worker's exposed IP is a "
|
||||
"private IP instead of a public IP, which leads to the inability to access"
|
||||
" the service."
|
||||
msgstr "云服务器启动worker_manager注册到controller时，发现worker暴露的ip是私网ip, 没有以公网ip暴露，导致服务访问不到"
|
||||
msgstr ""
|
||||
"Q8: 云服务器启动worker_manager注册到controller时，发现worker暴露的ip是私网ip, "
|
||||
"没有以公网ip暴露，导致服务访问不到"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:106
|
||||
#: 739a2983f3484acf98e877dc12f4ccda
|
||||
msgid "Q9: How to customize model path and prompt template"
|
||||
msgstr "Q9: 如何自定义模型路径和 prompt 模板"
|
||||
|
||||
#: ../../getting_started/faq/llm/llm_faq.md:108
|
||||
#: 8b82a33a311649c7850c30c00c987c72
|
||||
#, fuzzy
|
||||
msgid ""
|
||||
"DB-GPT will read the model path from "
|
||||
"`pilot.configs.model_config.LLM_MODEL_CONFIG` based on the `LLM_MODEL`. "
|
||||
"Of course, you can use the environment variable `LLM_MODEL_PATH` to "
|
||||
"specify the model path and `LLM_PROMPT_TEMPLATE` to specify your model "
|
||||
"prompt template."
|
||||
msgstr ""
|
||||
"DB-GPT 会根据 `LLM_MODEL` 从 `pilot.configs.model_config.LLM_MODEL_CONFIG` "
|
||||
"中读取模型路径。当然，你可以使用环境 `LLM_MODEL_PATH` 来指定模型路径，以及使用 `LLM_PROMPT_TEMPLATE` "
|
||||
"来指定模型的 prompt 模板。"
|
||||
|
||||
#~ msgid ""
|
||||
#~ "Note: you need to install the "
|
||||
#~ "latest dependencies according to "
|
||||
#~ "[requirements.txt](https://github.com/eosphoros-ai/DB-"
|
||||
#~ "GPT/blob/main/requirements.txt)."
|
||||
#~ msgstr ""
|
||||
|
||||
|
||||
@ -1,4 +1,4 @@
|
||||
# Knownledge
|
||||
# Knowledge
|
||||
|
||||
As the knowledge base is currently the most significant user demand scenario, we natively support the construction and processing of knowledge bases. At the same time, we also provide multiple knowledge base management strategies in this project, such as:
|
||||
1. Default built-in knowledge base
|
||||
@ -32,4 +32,4 @@ Optionally, you can run `dbgpt knowledge load --help` command to see more usage.
|
||||
|
||||
3.Add the knowledge repository in the interface by entering the name of your knowledge repository (if not specified, enter "default") so you can use it for Q&A based on your knowledge base.
|
||||
|
||||
Note that the default vector model used is text2vec-large-chinese (which is a large model, so if your personal computer configuration is not enough, it is recommended to use text2vec-base-chinese). Therefore, ensure that you download the model and place it in the models directory.
|
||||
Note that the default vector model used is text2vec-large-chinese (which is a large model, so if your personal computer configuration is not enough, it is recommended to use text2vec-base-chinese). Therefore, ensure that you download the model and place it in the models directory.
|
||||
@ -194,6 +194,8 @@ class Config(metaclass=Singleton):
|
||||
|
||||
### LLM Model Service Configuration
|
||||
self.LLM_MODEL = os.getenv("LLM_MODEL", "vicuna-13b-v1.5")
|
||||
self.LLM_MODEL_PATH = os.getenv("LLM_MODEL_PATH")
|
||||
|
||||
### Proxy llm backend, this configuration is only valid when "LLM_MODEL=proxyllm"
|
||||
### When we use the rest API provided by deployment frameworks like fastchat as a proxyllm, "PROXYLLM_BACKEND" is the model they actually deploy.
|
||||
### We need to use "PROXYLLM_BACKEND" to load the prompt of the corresponding scene.
|
||||
|
||||
@ -13,7 +13,7 @@ from pilot.utils.api_utils import (
|
||||
_api_remote as api_remote,
|
||||
_sync_api_remote as sync_api_remote,
|
||||
)
|
||||
from pilot.utils.utils import setup_logging
|
||||
from pilot.utils.utils import setup_logging, setup_http_service_logging
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@ -149,6 +149,7 @@ def initialize_controller(
|
||||
else:
|
||||
import uvicorn
|
||||
|
||||
setup_http_service_logging()
|
||||
app = FastAPI()
|
||||
app.include_router(router, prefix="/api", tags=["Model"])
|
||||
uvicorn.run(app, host=host, port=port, log_level="info")
|
||||
@ -179,7 +180,8 @@ def run_model_controller():
|
||||
parser = EnvArgumentParser()
|
||||
env_prefix = "controller_"
|
||||
controller_params: ModelControllerParameters = parser.parse_args_into_dataclass(
|
||||
ModelControllerParameters, env_prefix=env_prefix
|
||||
ModelControllerParameters,
|
||||
env_prefixes=[env_prefix],
|
||||
)
|
||||
|
||||
setup_logging(
|
||||
|
||||
@ -76,7 +76,7 @@ class DefaultModelWorker(ModelWorker):
|
||||
model_type = self.llm_adapter.model_type()
|
||||
model_params: ModelParameters = model_args.parse_args_into_dataclass(
|
||||
param_cls,
|
||||
env_prefix=env_prefix,
|
||||
env_prefixes=[env_prefix, "LLM_"],
|
||||
command_args=command_args,
|
||||
model_name=self.model_name,
|
||||
model_path=self.model_path,
|
||||
|
||||
@ -106,7 +106,7 @@ def _parse_embedding_params(
|
||||
env_prefix = EnvArgumentParser.get_env_prefix(model_name)
|
||||
model_params: BaseEmbeddingModelParameters = model_args.parse_args_into_dataclass(
|
||||
param_cls,
|
||||
env_prefix=env_prefix,
|
||||
env_prefixes=[env_prefix],
|
||||
command_args=command_args,
|
||||
model_name=model_name,
|
||||
model_path=model_path,
|
||||
|
||||
@ -38,7 +38,7 @@ from pilot.utils.parameter_utils import (
|
||||
_dict_to_command_args,
|
||||
_get_dict_from_obj,
|
||||
)
|
||||
from pilot.utils.utils import setup_logging
|
||||
from pilot.utils.utils import setup_logging, setup_http_service_logging
|
||||
from pilot.utils.tracer import initialize_tracer, root_tracer, SpanType, SpanTypeRunName
|
||||
from pilot.utils.system_utils import get_system_info
|
||||
|
||||
@ -735,6 +735,8 @@ def _setup_fastapi(
|
||||
):
|
||||
if not app:
|
||||
app = FastAPI()
|
||||
setup_http_service_logging()
|
||||
|
||||
if worker_params.standalone:
|
||||
from pilot.model.cluster.controller.controller import initialize_controller
|
||||
from pilot.model.cluster.controller.controller import (
|
||||
@ -781,7 +783,7 @@ def _parse_worker_params(
|
||||
env_prefix = EnvArgumentParser.get_env_prefix(model_name)
|
||||
worker_params: ModelWorkerParameters = worker_args.parse_args_into_dataclass(
|
||||
ModelWorkerParameters,
|
||||
env_prefix=env_prefix,
|
||||
env_prefixes=[env_prefix],
|
||||
model_name=model_name,
|
||||
model_path=model_path,
|
||||
**kwargs,
|
||||
@ -790,7 +792,7 @@ def _parse_worker_params(
|
||||
# Read parameters agein with prefix of model name.
|
||||
new_worker_params = worker_args.parse_args_into_dataclass(
|
||||
ModelWorkerParameters,
|
||||
env_prefix=env_prefix,
|
||||
env_prefixes=[env_prefix],
|
||||
model_name=worker_params.model_name,
|
||||
model_path=worker_params.model_path,
|
||||
**kwargs,
|
||||
|
||||
@ -95,7 +95,7 @@ class ModelLoader:
|
||||
env_prefix = env_prefix.replace("-", "_")
|
||||
model_params = args_parser.parse_args_into_dataclass(
|
||||
param_cls,
|
||||
env_prefix=env_prefix,
|
||||
env_prefixes=[env_prefix],
|
||||
device=self.device,
|
||||
model_path=self.model_path,
|
||||
model_name=self.model_name,
|
||||
|
||||
@ -445,17 +445,47 @@ class VLLMModelAdaperWrapper(LLMModelAdaper):
|
||||
|
||||
# Covering the configuration of fastcaht, we will regularly feedback the code here to fastchat.
|
||||
# We also recommend that you modify it directly in the fastchat repository.
|
||||
|
||||
# source: https://huggingface.co/BAAI/AquilaChat2-34B/blob/4608b75855334b93329a771aee03869dbf7d88cc/predict.py#L212
|
||||
register_conv_template(
|
||||
Conversation(
|
||||
name="internlm-chat",
|
||||
system_message="A chat between a curious <|User|> and an <|Bot|>. The <|Bot|> gives helpful, detailed, and polite answers to the <|User|>'s questions.\n\n",
|
||||
roles=("<|User|>", "<|Bot|>"),
|
||||
sep_style=SeparatorStyle.CHATINTERN,
|
||||
sep="<eoh>",
|
||||
sep2="<eoa>",
|
||||
stop_token_ids=[1, 103028],
|
||||
# TODO feedback stop_str to fastchat
|
||||
stop_str="<eoa>",
|
||||
),
|
||||
override=True,
|
||||
name="aquila-legacy",
|
||||
system_message="A chat between a curious human and an artificial intelligence assistant. "
|
||||
"The assistant gives helpful, detailed, and polite answers to the human's questions.\n\n",
|
||||
roles=("### Human: ", "### Assistant: ", "System"),
|
||||
messages=(),
|
||||
offset=0,
|
||||
sep_style=SeparatorStyle.NO_COLON_TWO,
|
||||
sep="\n",
|
||||
sep2="</s>",
|
||||
stop_str=["</s>", "[UNK]"],
|
||||
)
|
||||
)
|
||||
# source: https://huggingface.co/BAAI/AquilaChat2-34B/blob/4608b75855334b93329a771aee03869dbf7d88cc/predict.py#L227
|
||||
register_conv_template(
|
||||
Conversation(
|
||||
name="aquila",
|
||||
system_message="A chat between a curious human and an artificial intelligence assistant. "
|
||||
"The assistant gives helpful, detailed, and polite answers to the human's questions.",
|
||||
roles=("Human", "Assistant", "System"),
|
||||
messages=(),
|
||||
offset=0,
|
||||
sep_style=SeparatorStyle.ADD_COLON_TWO,
|
||||
sep="###",
|
||||
sep2="</s>",
|
||||
stop_str=["</s>", "[UNK]"],
|
||||
)
|
||||
)
|
||||
# source: https://huggingface.co/BAAI/AquilaChat2-34B/blob/4608b75855334b93329a771aee03869dbf7d88cc/predict.py#L242
|
||||
register_conv_template(
|
||||
Conversation(
|
||||
name="aquila-v1",
|
||||
roles=("<|startofpiece|>", "<|endofpiece|>", ""),
|
||||
messages=(),
|
||||
offset=0,
|
||||
sep_style=SeparatorStyle.NO_COLON_TWO,
|
||||
sep="",
|
||||
sep2="</s>",
|
||||
stop_str=["</s>", "<|endoftext|>"],
|
||||
)
|
||||
)
|
||||
|
||||
@ -5,8 +5,6 @@ import os
|
||||
from typing import List
|
||||
import logging
|
||||
|
||||
import openai
|
||||
|
||||
from pilot.model.proxy.llms.proxy_model import ProxyModel
|
||||
from pilot.model.parameter import ProxyModelParameters
|
||||
from pilot.scene.base_message import ModelMessage, ModelMessageRoleType
|
||||
@ -15,6 +13,14 @@ logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _initialize_openai(params: ProxyModelParameters):
|
||||
try:
|
||||
import openai
|
||||
except ImportError as exc:
|
||||
raise ValueError(
|
||||
"Could not import python package: openai "
|
||||
"Please install openai by command `pip install openai` "
|
||||
) from exc
|
||||
|
||||
api_type = params.proxy_api_type or os.getenv("OPENAI_API_TYPE", "open_ai")
|
||||
|
||||
api_base = params.proxy_api_base or os.getenv(
|
||||
@ -106,6 +112,8 @@ def _build_request(model: ProxyModel, params):
|
||||
def chatgpt_generate_stream(
|
||||
model: ProxyModel, tokenizer, params, device, context_len=2048
|
||||
):
|
||||
import openai
|
||||
|
||||
history, payloads = _build_request(model, params)
|
||||
|
||||
res = openai.ChatCompletion.create(messages=history, **payloads)
|
||||
@ -121,6 +129,8 @@ def chatgpt_generate_stream(
|
||||
async def async_chatgpt_generate_stream(
|
||||
model: ProxyModel, tokenizer, params, device, context_len=2048
|
||||
):
|
||||
import openai
|
||||
|
||||
history, payloads = _build_request(model, params)
|
||||
|
||||
res = await openai.ChatCompletion.acreate(messages=history, **payloads)
|
||||
|
||||
@ -2,6 +2,7 @@ import os
|
||||
import argparse
|
||||
import sys
|
||||
from typing import List
|
||||
import logging
|
||||
|
||||
ROOT_PATH = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
sys.path.append(ROOT_PATH)
|
||||
@ -39,6 +40,7 @@ from pilot.utils.utils import (
|
||||
setup_logging,
|
||||
_get_logging_level,
|
||||
logging_str_to_uvicorn_level,
|
||||
setup_http_service_logging,
|
||||
)
|
||||
from pilot.utils.tracer import root_tracer, initialize_tracer, SpanType, SpanTypeRunName
|
||||
from pilot.utils.parameter_utils import _get_dict_from_obj
|
||||
@ -127,6 +129,7 @@ def initialize_app(param: WebWerverParameters = None, args: List[str] = None):
|
||||
setup_logging(
|
||||
"pilot", logging_level=param.log_level, logger_filename=param.log_file
|
||||
)
|
||||
|
||||
# Before start
|
||||
system_app.before_start()
|
||||
|
||||
@ -141,7 +144,7 @@ def initialize_app(param: WebWerverParameters = None, args: List[str] = None):
|
||||
|
||||
model_name = param.model_name or CFG.LLM_MODEL
|
||||
|
||||
model_path = LLM_MODEL_CONFIG.get(model_name)
|
||||
model_path = CFG.LLM_MODEL_PATH or LLM_MODEL_CONFIG.get(model_name)
|
||||
if not param.light:
|
||||
print("Model Unified Deployment Mode!")
|
||||
if not param.remote_embedding:
|
||||
@ -180,6 +183,7 @@ def initialize_app(param: WebWerverParameters = None, args: List[str] = None):
|
||||
def run_uvicorn(param: WebWerverParameters):
|
||||
import uvicorn
|
||||
|
||||
setup_http_service_logging()
|
||||
uvicorn.run(
|
||||
app,
|
||||
host=param.host,
|
||||
|
||||
@ -190,6 +190,17 @@ def _genenv_ignoring_key_case(env_key: str, env_prefix: str = None, default_valu
|
||||
)
|
||||
|
||||
|
||||
def _genenv_ignoring_key_case_with_prefixes(
|
||||
env_key: str, env_prefixes: List[str] = None, default_value=None
|
||||
) -> str:
|
||||
if env_prefixes:
|
||||
for env_prefix in env_prefixes:
|
||||
env_var_value = _genenv_ignoring_key_case(env_key, env_prefix)
|
||||
if env_var_value:
|
||||
return env_var_value
|
||||
return _genenv_ignoring_key_case(env_key, default_value=default_value)
|
||||
|
||||
|
||||
class EnvArgumentParser:
|
||||
@staticmethod
|
||||
def get_env_prefix(env_key: str) -> str:
|
||||
@ -201,18 +212,16 @@ class EnvArgumentParser:
|
||||
def parse_args_into_dataclass(
|
||||
self,
|
||||
dataclass_type: Type,
|
||||
env_prefix: str = None,
|
||||
env_prefixes: List[str] = None,
|
||||
command_args: List[str] = None,
|
||||
**kwargs,
|
||||
) -> Any:
|
||||
"""Parse parameters from environment variables and command lines and populate them into data class"""
|
||||
parser = argparse.ArgumentParser()
|
||||
for field in fields(dataclass_type):
|
||||
env_var_value = _genenv_ignoring_key_case(field.name, env_prefix)
|
||||
if not env_var_value:
|
||||
# Read without env prefix
|
||||
env_var_value = _genenv_ignoring_key_case(field.name)
|
||||
|
||||
env_var_value = _genenv_ignoring_key_case_with_prefixes(
|
||||
field.name, env_prefixes
|
||||
)
|
||||
if env_var_value:
|
||||
env_var_value = env_var_value.strip()
|
||||
if field.type is int or field.type == Optional[int]:
|
||||
|
||||
@ -3,6 +3,8 @@
|
||||
|
||||
import logging
|
||||
import logging.handlers
|
||||
from typing import Any, List
|
||||
|
||||
import os
|
||||
import sys
|
||||
import asyncio
|
||||
@ -186,3 +188,42 @@ def logging_str_to_uvicorn_level(log_level_str):
|
||||
"NOTSET": "info",
|
||||
}
|
||||
return level_str_mapping.get(log_level_str.upper(), "info")
|
||||
|
||||
|
||||
class EndpointFilter(logging.Filter):
|
||||
"""Disable access log on certain endpoint
|
||||
|
||||
source: https://github.com/encode/starlette/issues/864#issuecomment-1254987630
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
path: str,
|
||||
*args: Any,
|
||||
**kwargs: Any,
|
||||
):
|
||||
super().__init__(*args, **kwargs)
|
||||
self._path = path
|
||||
|
||||
def filter(self, record: logging.LogRecord) -> bool:
|
||||
return record.getMessage().find(self._path) == -1
|
||||
|
||||
|
||||
def setup_http_service_logging(exclude_paths: List[str] = None):
|
||||
"""Setup http service logging
|
||||
|
||||
Now just disable some logs
|
||||
|
||||
Args:
|
||||
exclude_paths (List[str]): The paths to disable log
|
||||
"""
|
||||
if not exclude_paths:
|
||||
# Not show heartbeat log
|
||||
exclude_paths = ["/api/controller/heartbeat"]
|
||||
uvicorn_logger = logging.getLogger("uvicorn.access")
|
||||
if uvicorn_logger:
|
||||
for path in exclude_paths:
|
||||
uvicorn_logger.addFilter(EndpointFilter(path=path))
|
||||
httpx_logger = logging.getLogger("httpx")
|
||||
if httpx_logger:
|
||||
httpx_logger.setLevel(logging.WARNING)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user