chat llm pro

ChatLLM

From the second half of 2022 to 2023, Chatgpt appears low-key and stunning. This project is mainly based on various language models coding NLP-related applications.

flow chart

run env

 # pipreqs --force
# python>=3.8
virtualenv -p python venv
source venv/bin/activate

Compile the image

$ docker-compose -f chat_docker-compose build

Web UI

log

Limited

1. The parameter adjustment ability is limited. Limited intervention methods for responding to results
2. It is necessary to use a third-party network request, and the stability is not strong. How to deploy and use the intranet

schedule

• Implement docker server deployment
• UI DEMO interactive experience based on gradio
• Supports scenarios that summarize generation, Q&A, and emotional classification
• Supports selection of models
• Support chatpdf function
• Introduce langchain tool to accelerate application construction
• Develop document extraction server based on langchain tool. Text extraction can be realized through services.
• The text2vect model is introduced to perform word vector calculation.
• The web v3 version introduces vue3 to implement document-level question-and-answer. (Long-term plan)

Reference Documents

1. gpt-3 https://platform.openai.com/docs/models/gpt-3
2. Web interface https://gradio.app/
3. gpt3.5-api https://platform.openai.com/docs/guides/chat/instructing-chat-models

---

To obtain the experience key or Wenyin Financial Language Model, please contact [email protected]