app

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,12 @@
+---
+title: RAG With CoT And Self Reflection
+emoji: 💻
+colorFrom: red
+colorTo: pink
+sdk: gradio
+sdk_version: 4.44.0
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,77 @@
+import re
+from txtai import Embeddings, LLM
+import gradio as gr
+
+
+def cot(system, user):
+    system = f"""
+        {system}
+
+        You are an AI assistant that uses a Chain of Thought (CoT) approach with reflection to answer queries. Follow these steps:
+
+        1. Think through the problem step by step within the <thinking> tags.
+        2. Reflect on your thinking to check for any errors or improvements within the <reflection> tags.
+        3. Make any necessary adjustments based on your reflection.
+        4. Provide your final, concise answer within the <output> tags.
+
+        Important: The <thinking> and <reflection> sections are for your internal reasoning process only. 
+        Do not include any part of the final answer in these sections. 
+        The actual response to the query must be entirely contained within the <output> tags.
+
+        Use the following format for your response:
+        <thinking>
+        [Your step-by-step reasoning goes here. This is your internal thought process, not the final answer.]
+        <reflection>
+        [Your reflection on your reasoning, checking for errors or improvements]
+        </reflection>
+        [Any adjustments to your thinking based on your reflection]
+        </thinking>
+        <output>
+        [Your final, concise answer to the query. This is the only part that will be shown to the user.]
+        </output>
+        """
+
+    response = llm(
+        [
+            {"role": "system", "content": system},
+            {"role": "user", "content": user},
+        ],
+        maxlength=4096,
+    )
+
+    match = re.search(r"<output>(.*?)(?:</output>|$)", response, re.DOTALL)
+    return match.group(1).strip() if match else response
+
+
+def rag(question):
+    prompt = """
+    Answer the following question using only the context below. Only include information
+    specifically discussed.
+
+    question: {question}
+    context: {context}
+    """
+
+    system = "You are a friendly assistant. You answer questions from users."
+
+    context = "\n".join([x["text"] for x in embeddings.search(question)])
+
+    return cot(system, prompt.format(question=question, context=context))
+
+
+embeddings = Embeddings()
+embeddings.load(provider="huggingface-hub", container="neuml/txtai-wikipedia")
+
+llm = LLM("hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4", gpu=True)
+
+
+def predict(message, history):
+    response = rag(message)
+    return response
+
+
+gr.ChatInterface(
+    predict,
+    title="txtai Reflection Chatbot",
+    description="A chatbot that uses Chain of Thought (CoT) with self-reflection to answer queries.",
+).launch()

requirements.txt

@@ -0,0 +1,2 @@
+txtai
+autoawq