Comments (4)
- you can update local manager mode in manager.py to support multi llm start.
if run_locally:
# TODO start ModelController
worker_params.standalone = True
worker_params.register = True
worker_params.port = local_port
logger.info(f"Worker params: {worker_params}")
_setup_fastapi(worker_params, app, ignore_exception=True)
_start_local_worker(worker_manager, worker_params)
worker_manager.after_start(start_listener)
_start_local_embedding_worker(
worker_manager, embedding_model_name, embedding_model_path
)
- llm persistence will support soon.
from db-gpt.
- you can update local manager mode in manager.py to support multi llm start.
if run_locally: # TODO start ModelController worker_params.standalone = True worker_params.register = True worker_params.port = local_port logger.info(f"Worker params: {worker_params}") _setup_fastapi(worker_params, app, ignore_exception=True) _start_local_worker(worker_manager, worker_params) worker_manager.after_start(start_listener) _start_local_embedding_worker( worker_manager, embedding_model_name, embedding_model_path )
- llm persistence will support soon.
How should I configure different proxyllm? Different proxyllm api-keys and urls are different. It seems that the PROXY_API_KEY and PROXY_SERVER_URL in the environment variables are used.
xx_model_worker_params = ModelWorkerParameters(
model_name='test_llm',
model_path='chatgpt_proxyllm'
)
_start_local_worker(worker_manager, xx_model_worker_params)
from db-gpt.
Could you explain this implementation process in detail :) I add "_start_local_worker" after worker_manager.after_start(start_listener)
However, it setups 2 same model path LLM and named is chatglm3-6b-128k ;<
from db-gpt.
Is there any date for model persistence?
from db-gpt.
Related Issues (20)
- [Bug] [Agent] Request error HOT 2
- [Bug] [chat agent] Web show markdown table failed HOT 1
- [Feature][ChatData] integrate feature like vannai?
- [Feature]DB-GPT integrate xinference HOT 5
- [Feature][model] Support Qwen1.5-110B-Chat
- After creating the model, restart the service and the model created will disappear HOT 1
- https://tigi.ai/ is Product of DB-GPT ? HOT 5
- Error starting worker manager: model [email protected](10.10.12.118:5670) start failed, Traceback (most recent call last)
- [Bug] [chatglm3-6b] Using chatglm3-6b model QUANTIZE_8bit can be successful, but QUANTIZE_4bit is invalid, and the error message is that the video memory is not enough OOM HOT 1
- [New Feature] ES VectorStore HOT 1
- Dirty data encountered during session data storage, resulting in session consistency failure
- [Feature][model] Support DeepSeek proxy LLM.
- How to use uvicorn to start multiple processes when deploying?
- [Bug] [dashboard] 'ClickhouseConnector' object has no attribute 'session' HOT 1
- [Bug]If you encounter a bug when uploading files to csv, you can upload files in CSV format, but by default you cannot attach pictures as shown below.
- Can't connect to databases HOT 1
- if tokenizer.eos_token_id not in stop_token_ids: AttributeError: 'NoneType' object has no attribute 'eos_token_id' HOT 2
- [Bug] [rag] The EmbeddingRetriever faile to use a ranker that requires a query for re-ranking the retrieval results
- [Bug] [Knowledge] sync file error. HOT 5
- [Feature][Knowledge] Add GraphRAG framework and integrate TuGraph
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from db-gpt.