kaarthik108 / snowchat Goto Github PK

Chat snowflake database - Text to SQL

Home Page: https://snowchat.streamlit.app/

Python 97.47% PLpgSQL 2.53%

streamlit chatgpt gpt-4 snowflake vector langchain supabase llama python snowpark

snowchat's Introduction

snowChat 💬❄️

snowChat is an intuitive and user-friendly application that allows users to interact with their Snowflake data using natural language queries. Type in your questions or requests, and SnowChat will generate the appropriate SQL query and return the data you need. No more complex SQL queries or digging through tables - SnowChat makes it easy to access your data! By bringing data one step closer, SnowChat empowers users to make data-driven decisions faster and more efficiently, reducing the barriers between users and the insights they seek.

Supported LLM's

GPT-3.5-turbo-0125
CodeLlama-70B
Mistral Medium

snowchat_showoff.mp4

🌟 Features

Conversational AI: Harnesses ChatGPT to translate natural language into precise SQL queries.
Conversational Memory: Retains context for interactive, dynamic responses.
Snowflake Integration: Offers seamless, real-time data insights straight from your Snowflake database.
Self-healing SQL: Proactively suggests solutions for SQL errors, streamlining data access.
Interactive User Interface: Transforms data querying into an engaging conversation, complete with a chat reset option.

🛠️ Installation

Clone this repository: git clone https://github.com/yourusername/snowchat.git
Install the required packages: cd snowchat pip install -r requirements.txt
Set up your OPENAI_API_KEY, ACCOUNT, USER_NAME, PASSWORD, ROLE, DATABASE, SCHEMA, WAREHOUSE, SUPABASE_URL , SUPABASE_SERVICE_KEY and REPLICATE_API_TOKEN in project directory secrets.toml.
Make you're schemas and store them in docs folder that matches you're database.
Create supabase extention, table and function from the supabase/scripts.sql.
Run python ingest.py to get convert to embeddings and store as an index file.
Run the Streamlit app to start chatting: streamlit run main.py

🚀 Additional Enhancements

Platform Integration: Connect snowChat with popular communication platforms like Slack or Discord for seamless interaction.
Voice Integration: Implement voice recognition and text-to-speech functionality to make the chatbot more interactive and user-friendly.
Advanced Analytics: Integrate with popular data visualization libraries like Plotly or Matplotlib to generate interactive visualizations based on the user's queries (AutoGPT).

Star History

[]

🤝 Contributing

Feel free to contribute to this project by submitting a pull request or opening an issue. Your feedback and suggestions are greatly appreciated!

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

snowchat's People

Contributors

Stargazers

Watchers

Forkers

kaushikepi michaelhoughtondebox rajendharmendra kevinjqliu admariner broomva zhangwow123 sachdevap akilthms sa-bird zaerog derekshain tamiaprincee tjsqlsdl rexshop dheerajc007 sfc-gh-bfarley sudhanshu-kipi j-e-e-t sleepeatazure fellow-soft aswny binshi-bing congzhong onukura liza-mazurova theculliganman pytoned vikrambalaaj curious-bigcat aruncivicscience farazjamalespark avinityanalytics adityaem vibhubgupta trevianxyz lgao2021 nguyentruongan bobzhengllm svemulapalli inayet thegreymatter know2001 tgamzheng thivagar-manickam mikeharding matardia deep-learner-msp sfc-gh-pkuchikulla nguyenhoduy henri-edh alisaad faithfulalabi anassfarah vadsam aantibar complexluise shrix jgodboutprospector itsharex ishaan-jaff mrctito nishantkumark yumyai scalabresegd david-moreno-mora misterfancysocks chitpaingsoe ax2l shavhamdamov yeyu2 modelcitizen-ai parrth007 auroramariatumminello rock73 rasiqueira kkanagal javifern18 kannandreams jayozer giannigg alyssapineda binoyyj blackwhites rameshbyndoor datagpt365 roshanabady roshan-abady filmerj nationalresearch jonnyb111 csujeong mikelin97 cajerome kahtan777 scottafair flowgeniusmz abhigampa123 mitch-zink-1 adhityaraar

snowchat's Issues

Intallation Build

I am facing a problem setting up the environment mainly in step 4 of the installation guide, can someone guide what to do specifically there?

Best way to generate schema docs from snowflake

Make you're schemas and store them in docs folder that matches you're database.

In above mentioned step, are we expected manually get(copy) the schema definitions of all tables and views from the database or there is an automated or quicker way to download all schemas with a single click from snowflake?

LICENSE?

Hey @kaarthik108 Can you please add a LICENSE.md file?

Is this able to be used commercially?

Thanks!

You're != Your

Come on folks !
"Chat on YOUR snowflake database - Text to SQL" !

database and schema name not updated

Hello,

I noticed that every time I change the name of the database and schema in secrets.toml and files in doc folder, it does not get updated in the subsequent generated queries - the queries continue to use the old database and schema. I tried clearing up the cache but it did not work. Any suggestions on how to work around this issue?

Thanks.

Is there any same way we can connect to mysql db with this model?

Hi @esanketkulkarni , In my example I have to connect with mysql db with this same model usage. can you help me how can I change it.

Documentation

Hey buddy! Amazing work. Kudos to this project.

Could you provide work flow information on how this is working (how you are stiching various things together here)?
Do you have a medium article explaining the logic of this project?

Also, Why are you using Supabase?
Really waiting to hear from you on this.

Feature: Use open source LLM

Is there a possibility that this could use open source LLM?
OpenAi costs money and there are open source LLM's out there

CF_ACCOUNT_TAG

Hi @kaarthik108 ,

In class ModelWrapper:
def init(self, config: ModelConfig):
account_tag = self.secrets["CF_ACCOUNT_TAG"]

It's asking for CF_ACCOUNT_TAG in secrets, however, I don't see in the description how to add this value. Can you provide more information for this?

Thanks.

if my database is MySQL，what should I do

origin solution is Snowflake+Supabase，but my database is MySQL，what should I do

[Feature Request] Support InternLM

Dear snowChat developer,

Greetings! I am vansinhu, a community developer and volunteer at InternLM. Your work has been immensely beneficial to me, and I believe it can be effectively utilized in InternLM as well. Welcome to add Discord https://discord.gg/gF9ezcmtM3 . I hope to get in touch with you.

Best regards,
vansinhu

python version should be claim in ReadMe

(base) yhtao@Yuhang-PC:/mnt/d/github_repo/snowChat$ pip install -r requirements.txt 
Looking in indexes: https://pypi.doubanio.com/simple/
Collecting langchain==0.0.220 (from -r requirements.txt (line 1))
  Using cached https://pypi.doubanio.com/packages/eb/69/3dc0b6cd9331f32f8d35b4240068dee05b55c5e7cda5e90d5481f504f742/langchain-0.0.220-py3-none-any.whl (1.2 MB)
Collecting pandas==1.5.0 (from -r requirements.txt (line 2))
  Using cached https://pypi.doubanio.com/packages/da/4a/a0c8d3ba8d875a25578bcb3032b6ac9b2db3d016b0a762ab41e1a13f3b52/pandas-1.5.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (12.2 MB)
Collecting pydantic==1.10.8 (from -r requirements.txt (line 3))
  Using cached https://pypi.doubanio.com/packages/15/27/c35f6fefc782aebcff9991b28728f3855b1253ff757e6dee8e3ac3815cd0/pydantic-1.10.8-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.2 MB)
Collecting snowflake_snowpark_python==1.4.0 (from -r requirements.txt (line 4))
  Using cached https://pypi.doubanio.com/packages/d5/d0/e81975ff4dc49972356e06884bd15159452fff078d388a741e077b22d3b8/snowflake_snowpark_python-1.4.0-py3-none-any.whl (284 kB)
Requirement already satisfied: streamlit==1.22.0 in /home/yhtao/anaconda3/lib/python3.8/site-packages (from -r requirements.txt (line 6)) (1.22.0)
Collecting supabase==1.0.3 (from -r requirements.txt (line 7))
  Downloading https://pypi.doubanio.com/packages/14/bd/d68c0bbe5e536993bdc1545c9942a732b42c2f470fc1430fc82116cfab1c/supabase-1.0.3-py3-none-any.whl (11 kB)
ERROR: Could not find a version that satisfies the requirement unstructured==0.7.12 (from versions: 0.0.1.dev0, 0.2.0, 0.2.1, 0.2.2, 0.2.3, 0.2.4, 0.2.5, 0.2.6.dev1, 0.3.0, 0.3.1, 0.3.2, 0.3.3, 0.3.4, 0.3.5, 0.4.0, 0.4.1, 0.4.2, 0.4.3, 0.4.4, 0.4.6, 0.4.7, 0.4.8, 0.4.9, 0.4.10, 0.4.11, 0.4.12, 0.4.13, 0.4.14, 0.4.15, 0.4.16, 0.5.0, 0.5.1, 0.5.2, 0.5.3, 0.5.4, 0.5.6, 0.5.7, 0.5.8, 0.5.9, 0.5.10, 0.5.11, 0.5.12, 0.5.13, 0.6.0, 0.6.1, 0.6.2, 0.6.3, 0.6.4, 0.6.5, 0.6.6, 0.6.7, 0.6.8, 0.6.9, 0.6.10, 0.6.11, 0.7.0, 0.7.1, 0.7.2, 0.7.3, 0.7.4, 0.7.5, 0.7.6, 0.7.7, 0.7.8, 0.7.9, 0.7.10)

According to this blog the only reason in the scenario is my python==3.8.8 version is outdated for your requirements.txt, could you tell me the version you use in this repo?

Chain import issue

Hi @kaarthik108 @esanketkulkarni, I have followed same steps and able to run the app but getting following error. Can any one please suggest me how to fix?

Table not showing

Hi!

Are you supposed to first select a table from the side bar from the database you specify in secrets.toml file? Because for me, the options are still the default ones

And even if I query the default tables I don't get a table, and the code generated is not formatted like in the demo app:

What could've been wrong? Thanks so much!