Duplicate from lukestanley/streaming_chat_with_gpt-3.5-turbo_using_langchain_sorta

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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 +1,14 @@
+---
+title: Streaming Chat With Gpt-3.5-turbo Using Langchain Sorta
+emoji: 📚
+colorFrom: purple
+colorTo: purple
+sdk: gradio
+sdk_version: 3.19.1
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: lukestanley/streaming_chat_with_gpt-3.5-turbo_using_langchain_sorta
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,83 @@
+from typing import List, Tuple, Dict, Generator
+from langchain.llms import OpenAI
+import gradio as gr
+
+model_name = "gpt-3.5-turbo"
+LLM = OpenAI(model_name=model_name, temperature=0.1)
+
+def create_history_messages(history: List[Tuple[str, str]]) -> List[dict]:
+    history_messages = [{"role": "user", "content": m[0]} for m in history]
+    history_messages.extend([{"role": "assistant", "content": m[1]} for m in history])
+    return history_messages
+
+def create_formatted_history(history_messages: List[dict]) -> List[Tuple[str, str]]:
+    formatted_history = []
+    user_messages = []
+    assistant_messages = []
+
+    for message in history_messages:
+        if message["role"] == "user":
+            user_messages.append(message["content"])
+        elif message["role"] == "assistant":
+            assistant_messages.append(message["content"])
+
+        if user_messages and assistant_messages:
+            formatted_history.append(
+                ("".join(user_messages), "".join(assistant_messages))
+            )
+            user_messages = []
+            assistant_messages = []
+
+    # append any remaining messages
+    if user_messages:
+        formatted_history.append(("".join(user_messages), None))
+    elif assistant_messages:
+        formatted_history.append((None, "".join(assistant_messages)))
+
+    return formatted_history
+
+def chat(
+    message: str, state: List[Dict[str, str]], client = LLM.client
+) -> Generator[Tuple[List[Tuple[str, str]], List[Dict[str, str]]], None, None]:
+    history_messages = state
+    if history_messages == None:
+        history_messages = []
+        history_messages.append({"role": "system", "content": "A helpful assistant."})
+
+    history_messages.append({"role": "user", "content": message})
+    # We have no content for the assistant's response yet but we will update this:
+    history_messages.append({"role": "assistant", "content": ""})
+
+    response_message = ""
+
+    chat_generator = client.create(
+        messages=history_messages, stream=True, model=model_name
+    )
+
+    for chunk in chat_generator:
+        if "choices" in chunk:
+            for choice in chunk["choices"]:
+                if "delta" in choice and "content" in choice["delta"]:
+                    new_token = choice["delta"]["content"]
+                    # Add the latest token:
+                    response_message += new_token
+                    # Update the assistant's response in our model:
+                    history_messages[-1]["content"] = response_message
+
+                if "finish_reason" in choice and choice["finish_reason"] == "stop":
+                    break
+        formatted_history = create_formatted_history(history_messages)
+        yield formatted_history, history_messages
+
+chatbot = gr.Chatbot(label="Chat").style(color_map=("yellow", "purple"))
+iface = gr.Interface(
+    fn=chat,
+    inputs=[
+        gr.Textbox(placeholder="Hello! How are you? etc.", label="Message"),
+        "state",
+    ],
+    outputs=[chatbot, "state"],
+    allow_flagging="never",
+)
+
+iface.queue().launch()

requirements.txt

@@ -0,0 +1,2 @@
+langchain
+openai