add github workflow to sync-with-huggingface

.github/workflows/sync-with-huggingface.yml

@@ -0,0 +1,50 @@
+name: Sync with Hugging Face
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - .github/workflows/sync-with-huggingface.yml
+      - app/**
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+    - name: Sync with Hugging Face
+      uses: nateraw/[email protected]
+      with:
+        # The github repo you are syncing from. Required.
+        github_repo_id: 'myscale/ChatData'
+
+        # The Hugging Face repo id you want to sync to. (ex. 'username/reponame')
+        # A repo with this name will be created if it doesn't exist. Required.
+        huggingface_repo_id: 'myscale/ChatData'
+
+        # Hugging Face token with write access. Required.
+        # Here, we provide a token that we called `HF_TOKEN` when we added the secret to our GitHub repo.
+        hf_token: ${{ secrets.HF_TOKEN }}
+
+        # The type of repo you are syncing to: model, dataset, or space.
+        # Defaults to space.
+        repo_type: 'space'
+
+        # If true and the Hugging Face repo doesn't already exist, it will be created
+        # as a private repo.
+        #
+        # Note: this param has no effect if the repo already exists.
+        private: false
+
+        # If repo type is space, specify a space_sdk. One of: streamlit, gradio, or static
+        #
+        # This option is especially important if the repo has not been created yet.
+        # It won't really be used if the repo already exists.
+        space_sdk: 'streamlit'
+
+        # If provided, subdirectory will determine which directory of the repo will be synced.
+        # By default, this action syncs the entire GitHub repo.
+        #
+        # An example using this option can be seen here:
+        # https://github.com/huggingface/fuego/blob/830ed98/.github/workflows/sync-with-huggingface.yml
+        subdirectory: app

README.md

@@ -1,4 +1,5 @@
 # ChatData 🔍 📖
+
 ***We are constantly improving LangChain's self-query retriever. Some of the features are not merged yet.***
 
 [![](https://dcbadge.vercel.app/api/server/D2qpkqc4Jq?compact=true&style=flat)](https://discord.gg/D2qpkqc4Jq)
@@ -38,7 +39,7 @@ To enhance your experience and seamlessly continue interactions with existing se
 
 In addition to tapping into ChatData's external knowledge base powered by MyScale for answers, you also have the option to upload your own files and establish a personalized knowledge base. We've implemented the Unstructured API for this purpose, ensuring that only processed texts from your documents are stored, prioritizing your data privacy.
 
-In conclusion, with ChatData, you can effortlessly navigate through vast amounts of data, effortlessly accessing precisely what you need. Whether you're a researcher, a student, or a knowledge enthusiast, ChatData empowers you to explore academic papers and research documents like never before. Unlock the true potential of information retrieval with ChatData and discover a world of knowledge at your fingertips. 
+In conclusion, with ChatData, you can effortlessly navigate through vast amounts of data, effortlessly accessing precisely what you need. Whether you're a researcher, a student, or a knowledge enthusiast, ChatData empowers you to explore academic papers and research documents like never before. Unlock the true potential of information retrieval with ChatData and discover a world of knowledge at your fingertips.
 
 ➡️ Dive in and experience ChatData on [Hugging Face](https://huggingface.co/spaces/myscale/ChatData)🤗
 
@@ -126,8 +127,10 @@ python3 -m streamlit run app.py
 ```
 
 ### Where can I get those arXiv data?
-  - [From parquet files on S3](docs/self-query.md#insert-data)
-  - <a name="data-service"></a>Or Directly use MyScale database as service... for **FREE** ✨
+
+- [From parquet files on S3](docs/self-query.md#insert-data)
+- <a name="data-service"></a>Or Directly use MyScale database as service... for **FREE** ✨
+
     ```python
     import clickhouse_connect
 
@@ -155,26 +158,32 @@ python3 -m streamlit run app.py
 
 ### Quickstart
 
-1. Create an virtual environment
+1. Enter directory `app/`
+
+```bash
+cd app/
+```
+
+2. Create an virtual environment
 
 ```bash
 python3 -m venv .venv
 source .venv/bin/activate
 ```
 
-2. Install dependencies
+3. Install dependencies
 
-> This app is currently using [MyScale's technical preview of LangChain](https://github.com/myscale/langchain/tree/preview). 
->> 
+> This app is currently using [MyScale's technical preview of LangChain](https://github.com/myscale/langchain/tree/preview).
+>
 >> It contains improved SQLDatabaseChain in [this PR](https://github.com/hwchase17/langchain/pull/7454)
->> 
+>>
 >> It contains [improved prompts](https://github.com/hwchase17/langchain/pull/6737#discussion_r1243527112) for comparators `LIKE` and `CONTAIN` in [MyScale self-query retriever](https://github.com/hwchase17/langchain/pull/6143).
 
 ```bash
 python3 -m pip install -r requirements.txt
 ```
 
-3. Run the app!
+4. Run the app!
 
 ```python
 # fill you OpenAI key in .streamlit/secrets.toml
@@ -187,7 +196,6 @@ python3 -m streamlit run app.py
 
  [*Read the full article*](https://blog.myscale.com/2023/07/17/teach-your-llm-vector-sql/)
 
-
 - [Why Vector SQL?](https://blog.myscale.com/2023/07/17/teach-your-llm-vector-sql/#automate-the-whole-process-with-sql-and-vector-search)
 - [How did LangChain and MyScale convert natural language to structured filters?](https://docs.myscale.com/en/advanced-applications/chatdata/#selfqueryretriever)
 - [How to make chain execution more responsive in LangChain?](https://docs.myscale.com/en/advanced-applications/chatdata/#add-callbacks)

.streamlit/secrets.example.toml → app/.streamlit/secrets.example.toml

@@ -1,4 +1,4 @@
-MYSCALE_HOST = "msc-1decbcc9.us-east-1.aws.staging.myscale.cloud"
+MYSCALE_HOST = "msc-4a9e710a.us-east-1.aws.staging.myscale.cloud"
 MYSCALE_PORT = 443
 MYSCALE_USER = "chatdata"
 MYSCALE_PASSWORD = "myscale_rocks"