HF space

README.md

@@ -10,7 +10,7 @@ _Go and give it a try [here](https://hf.co/chat/assistant/660d9a4f590a7924eed02a
    <img src="https://img.shields.io/badge/Release-v0.1.0-blue" alt="Static Badge">
    <img src="https://img.shields.io/badge/Docker_image_size-6.44GB-red" alt="Static Badge">
    <div>
-        <a href="https://astrabert.github.io/everything-rag/"><img src="./data/example_chat.png" alt="Example chat" align="center"></a>
+        <a href="https://huggingface.co/spaces/as-cle-bert/everything-rag"><img src="./data/example_chat.png" alt="Example chat" align="center"></a>
         <p><i>Example chat with everything-rag, mediated by google/flan-t5-base</i></p>
    </div>
 </div>
@@ -26,6 +26,20 @@ _Go and give it a try [here](https://hf.co/chat/assistant/660d9a4f590a7924eed02a
 5. [Contributing](#contributing)
 6. [References](#reference)
 
+## TL;DR
+
+* Q: This README is soooooo long, I want to get my hands dirty!!!
+    >A: You can do it in the [dedicated HuggingFace space](https://huggingface.co/spaces/as-cle-bert/everything-rag), based on google/flan-t5-base.
+
+<div>
+    <iframe
+        src="https://as-cle-bert-everything-rag.hf.space"
+        frameborder="0"
+        width="850"
+        height="450"
+    ></iframe>
+</div>
+
 ## Introduction
 
 Introducing **everything-rag**, your fully customizable and local chatbot assistant! 🤖

docker/Dockerfile

@@ -1,37 +1,3 @@
-# Use an official Python runtime as a parent image
-FROM python:3.10-slim-buster
-
-# Set the working directory in the container to /app
-WORKDIR /app
-
-# Add the current directory contents into the container at /app
-ADD . /app
-
-# Update and install system dependencies
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    libpq-dev \
-    libffi-dev \
-    libssl-dev \
-    musl-dev \
-    libxml2-dev \
-    libxslt1-dev \
-    zlib1g-dev \
-    && rm -rf /var/lib/apt/lists/*
-
-# Install Python dependencies
-RUN python3 -m pip cache purge
-RUN python3 -m pip install --no-cache-dir -r requirements.txt
-
-# Set version
-ARG version="v0.1.0"
-
-# Echo version
-RUN echo "Started everything-rag ${version}"
-
-# Expose the port that the application will run on
-EXPOSE 7860
-
-# Set the entrypoint with a default command and allow the user to override it
-ENTRYPOINT ["python3", "chat.py"]
+FROM ghcr.io/astrabert/everything-rag:latest
 
+ENTRYPOINT [ "python3", "chat.py" ]

docker/chat.py

@@ -34,7 +34,7 @@ def bot(history):
                 yield history
         else:
             try:
-                response = just_chatting(model=model, tokenizer=tokenizer, query=history[-1][0], vectordb=vectordb, chat_history=[convert_none_to_str(his) for his in history])["answer"]
+                response = just_chatting(task=tsk, model=model, tokenizer=tokenizer, query=history[-1][0], vectordb=vectordb, chat_history=[convert_none_to_str(his) for his in history])["answer"]
                 history[-1][1] = ""
                 for character in response:
                     history[-1][1] += character
@@ -70,9 +70,10 @@ def bot(history):
     bot_msg.then(lambda: gr.MultimodalTextbox(interactive=True), None, [chat_input])
 
     chatbot.like(print_like_dislike, None, None)
-    gr.ClearButton(chatbot)
+    clear = gr.ClearButton(chatbot)
+
 demo.queue()
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", share=False)
+    demo.launch(share=False)
 
 

docker/utils.py

@@ -140,7 +140,7 @@ def just_chatting(
                     model=model,
                     tokenizer=tokenizer,
                     max_new_tokens = 2048,
-                    repetition_penalty = float(10),
+                    repetition_penalty = float(1.2),
     )
 
     local_llm = HuggingFacePipeline(pipeline=pipe)
@@ -159,7 +159,6 @@ def just_chatting(
         mod,
     )
 
-    tokenizer.pad_token = tokenizer.eos_token
 
     model = TASK_TO_MODEL[tsk].from_pretrained(
         mod,