Update

.gitignore

@@ -0,0 +1,4 @@
+chroma_db/*
+__pycache__/*
+.venv
+.env

README.md

@@ -1,13 +1,41 @@
 ---
-title: Simple Chatbot
-emoji: 💬
-colorFrom: yellow
-colorTo: purple
+title: GAIA Chatbot - level 2
+emoji: 👁
+colorFrom: red
+colorTo: pink
 sdk: gradio
-sdk_version: 5.6.0
+sdk_version: 5.13.1
 app_file: app.py
 pinned: false
 license: mit
+short_description: Example of chatbot with RAG on one link
 ---
+# Run on a space
 
-An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+Simply push your code on a huggingface space.
+
+# Run locally
+
+You must have python (3.8)[https://www.python.org/downloads/].
+
+Check https://www.gradio.app/guides/quickstart for more details about Gradio.
+
+## Install dependencies
+
+`python -m venv .venv`
+
+`source .venv/bin/activate`
+
+`pip install -r requirements.txt`
+
+## Add Claude API Key to your environement variables
+
+ANTHROPIC_API_KEY=XXXXXXXXXXXXXXXXXX
+
+## Run your code
+
+`python3 app.py`
+
+## Open your browser to `http://127.0.0.1:7860`

app.py

@@ -1,64 +1,55 @@
+import os
+import sys
+from dotenv import load_dotenv
+import anthropic
 import gradio as gr
-from huggingface_hub import InferenceClient
+from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
+
+load_dotenv()
+
+title = "Gaia Anthropic Claude 3.5 Sonnet Chat RAG URL Demo"
+description = "Example of an assistant with Gradio, RAG from url and Claude 3.5 Sonnet via its API"
+placeholder = "Vous pouvez me posez une question sur ce contexte, appuyer sur Entrée pour valider"
+placeholder_url = "Extract text from this url"
+# llm_model = 'open-mixtral-8x22b'
+llm_model = 'claude-3-5-sonnet-latest'
+# choose api_key from .env or from input field
+# placeholder_api_key = "API key"
+# env_mistral_api_key = os.environ.get("MISTRAL_API_KEY")
+env_api_key = os.environ.get("ANTHROPIC_API_KEY")
+
+# Set-up clients
+# llm = MistralAI(api_key=env_api_key,model=llm_model)
+# llm = Anthropic(api_key=env_api_key, model=llm_model)
+# embed_model = MistralAIEmbedding(model_name='mistral-embed', api_key=env_mistral_api_key)
+# Settings.llm = llm
+# Settings.embed_model = embed_model
+# Settings.chunk_size = 1024
+
+# client = anthropic.Anthropic(api_key=env_api_key)
+
+def answer(message, history):
+    files = []
+    for msg in history:
+        if msg['role'] == "user" and isinstance(msg['content'], tuple):
+            files.append(msg['content'][0])
+    for file in message["files"]:
+        files.append(file)
+
+    documents = SimpleDirectoryReader(input_files=files).load_data()
+    index = VectorStoreIndex.from_documents(documents)
+    query_engine = index.as_query_engine()
+    return str(query_engine.query(message["text"]))
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+    answer,
+    type="messages",
+    title="Llama Index RAG Chatbot",
+    description="Upload any text or pdf files and ask questions about them!",
+    textbox=gr.MultimodalTextbox(file_types=[".pdf", ".txt", ".html"]),
+    multimodal=True
 )
 
+demo.title = title
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch(share=True)

requirements.txt

@@ -1 +1,12 @@
-huggingface_hub==0.25.2
+mistralai
+gradio
+python-dotenv
+anthropic
+faiss-cpu
+numpy
+html2text
+llama-index
+llama-index-readers-web
+llama-index-readers-file
+llama-index-llms-mistralai
+llama-index-embeddings-mistralai