gradio chatbot examples

.gitignore

@@ -3,4 +3,246 @@
 
 env
 venv
-temp
+temp
+gradio_cached_examples
+
+# File created using '.gitignore Generator' for Visual Studio Code: https://bit.ly/vscode-gig
+# Created by https://www.toptal.com/developers/gitignore/api/windows,visualstudiocode,git,python
+# Edit at https://www.toptal.com/developers/gitignore?templates=windows,visualstudiocode,git,python
+
+### Git ###
+# Created by git for backups. To disable backups in Git:
+# $ git config --global mergetool.keepBackup false
+*.orig
+
+# Created by git when using merge tools for conflicts
+*.BACKUP.*
+*.BASE.*
+*.LOCAL.*
+*.REMOTE.*
+*_BACKUP_*.txt
+*_BASE_*.txt
+*_LOCAL_*.txt
+*_REMOTE_*.txt
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+### Windows ###
+# Windows thumbnail cache files
+Thumbs.db
+Thumbs.db:encryptable
+ehthumbs.db
+ehthumbs_vista.db
+
+# Dump file
+*.stackdump
+
+# Folder config file
+[Dd]esktop.ini
+
+# Recycle Bin used on file shares
+$RECYCLE.BIN/
+
+# Windows Installer files
+*.cab
+*.msi
+*.msix
+*.msm
+*.msp
+
+# Windows shortcuts
+*.lnk
+
+# End of https://www.toptal.com/developers/gitignore/api/windows,visualstudiocode,git,python
+
+# Custom rules (everything added below won't be overriden by 'Generate .gitignore File' if you use 'Update' option)
+

app.py

@@ -1,7 +1,9 @@
+import time
 import gradio as gr
 
-def greet(name):
-    return "Hello " + name + "!!"
+def slow_echo(message, history):
+    for i in range(len(message)):
+        time.sleep(0.3)
+        yield "You typed: " + message[: i+1]
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch()
+gr.ChatInterface(slow_echo).launch()

chat-10-api.py

@@ -0,0 +1,47 @@
+import gradio as gr
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
+from threading import Thread
+
+tokenizer = AutoTokenizer.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1")
+model = AutoModelForCausalLM.from_pretrained("togethercomputer/RedPajama-INCITE-Chat-3B-v1", torch_dtype=torch.float16)
+model = model.to('cuda:0')
+
+class StopOnTokens(StoppingCriteria):
+    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
+        stop_ids = [29, 0]
+        for stop_id in stop_ids:
+            if input_ids[0][-1] == stop_id:
+                return True
+        return False
+
+def predict(message, history):
+    history_transformer_format = history + [[message, ""]]
+    stop = StopOnTokens()
+
+    messages = "".join(["".join(["\n<human>:"+item[0], "\n<bot>:"+item[1]])
+                for item in history_transformer_format])
+
+    model_inputs = tokenizer([messages], return_tensors="pt").to("cuda")
+    streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
+    generate_kwargs = dict(
+        model_inputs,
+        streamer=streamer,
+        max_new_tokens=1024,
+        do_sample=True,
+        top_p=0.95,
+        top_k=1000,
+        temperature=1.0,
+        num_beams=1,
+        stopping_criteria=StoppingCriteriaList([stop])
+        )
+    t = Thread(target=model.generate, kwargs=generate_kwargs)
+    t.start()
+
+    partial_message = ""
+    for new_token in streamer:
+        if new_token != '<':
+            partial_message += new_token
+            yield partial_message
+
+gr.ChatInterface(predict).launch()

chat-2-interface.py

@@ -0,0 +1,15 @@
+import gradio as gr
+
+# def greet(name):
+#     return "Hello " + name + "!!"
+
+# demo = gr.Interface(fn=greet, inputs="text", outputs="text")
+# demo.launch()
+
+import random
+
+def random_response(message, history):
+    return random.choice(["Yes", "No"])
+
+
+gr.ChatInterface(random_response).launch()

chat-3-interface.py

@@ -0,0 +1,9 @@
+import time
+import gradio as gr
+
+def slow_echo(message, history):
+    for i in range(len(message)):
+        time.sleep(0.3)
+        yield "You typed: " + message[: i+1]
+
+gr.ChatInterface(slow_echo).launch()

chat-4.py

@@ -0,0 +1,21 @@
+import gradio as gr
+
+def yes_man(message, history):
+    if message.endswith("?"):
+        return "Yes"
+    else:
+        return "Ask me anything!"
+
+gr.ChatInterface(
+    yes_man,
+    chatbot=gr.Chatbot(height=300),
+    textbox=gr.Textbox(placeholder="Ask me a yes or no question", container=False, scale=7),
+    title="Yes Man",
+    description="Ask Yes Man any question",
+    theme="soft",
+    examples=["Hello", "Am I cool?", "Are tomatoes vegetables?"],
+    cache_examples=True,
+    retry_btn=None,
+    undo_btn="Delete Previous",
+    clear_btn="Clear",
+).launch()

chat-5.py

@@ -0,0 +1,10 @@
+import gradio as gr
+import time
+
+def count_files(message, history):
+    num_files = len(message["files"])
+    return f"You uploaded {num_files} files"
+
+demo = gr.ChatInterface(fn=count_files, examples=[{"text": "Hello", "files": []}], title="Echo Bot", multimodal=True)
+
+demo.launch()

chat-6.py

@@ -0,0 +1,19 @@
+import gradio as gr
+import time
+
+def echo(message, history, system_prompt, tokens):
+    response = f"System prompt: {system_prompt}\n Message: {message}."
+    for i in range(min(len(response), int(tokens))):
+        time.sleep(0.05)
+        yield response[: i+1]
+
+demo = gr.ChatInterface(echo, 
+                        additional_inputs=[
+                            gr.Textbox("You are helpful AI.", label="System Prompt"), 
+                            gr.Slider(10, 100)
+                        ]
+                       )
+
+if __name__ == "__main__":
+    demo.queue().launch()
+    

chat-7.py

@@ -0,0 +1,18 @@
+import gradio as gr
+import time
+
+def echo(message, history, system_prompt, tokens):
+    response = f"System prompt: {system_prompt}\n Message: {message}."
+    for i in range(min(len(response), int(tokens))):
+        time.sleep(0.05)
+        yield response[: i+1]
+
+with gr.Blocks() as demo:
+    system_prompt = gr.Textbox("You are helpful AI.", label="System Prompt")
+    slider = gr.Slider(10, 100, render=False)
+
+    gr.ChatInterface(
+        echo, additional_inputs=[system_prompt, slider]
+    )
+
+demo.launch()

chat-8-api.py

@@ -0,0 +1,26 @@
+
+from langchain.chat_models import ChatOpenAI
+from langchain.schema import AIMessage, HumanMessage
+from langchain_community.chat_models import ChatOpenAI
+from langchain_openai import ChatOpenAI
+import openai, os
+import gradio as gr
+from dotenv import load_dotenv
+load_dotenv()   
+
+OPENAI_API_KEY = os.environ['GROQ_API_KEY']
+
+# llm = ChatOpenAI(temperature=1.0, model='gpt-3.5-turbo-0613')
+llm = openai(temperature=1.0, model='gpt-4-turbo')
+# llm = openai(temperature=1.0, model='gpt-4o')
+
+def predict(message, history):
+    history_langchain_format = []
+    for human, ai in history:
+        history_langchain_format.append(HumanMessage(content=human))
+        history_langchain_format.append(AIMessage(content=ai))
+    history_langchain_format.append(HumanMessage(content=message))
+    gpt_response = llm(history_langchain_format)
+    return gpt_response.content
+
+gr.ChatInterface(predict).launch()

chat-9-api.py

@@ -0,0 +1,25 @@
+from openai import OpenAI
+import gradio as gr
+
+api_key = "sk-..."  # Replace with your key
+client = OpenAI(api_key=api_key)
+
+def predict(message, history):
+    history_openai_format = []
+    for human, assistant in history:
+        history_openai_format.append({"role": "user", "content": human })
+        history_openai_format.append({"role": "assistant", "content":assistant})
+    history_openai_format.append({"role": "user", "content": message})
+  
+    response = client.chat.completions.create(model='gpt-3.5-turbo',
+    messages= history_openai_format,
+    temperature=1.0,
+    stream=True)
+
+    partial_message = ""
+    for chunk in response:
+        if chunk.choices[0].delta.content is not None:
+              partial_message = partial_message + chunk.choices[0].delta.content
+              yield partial_message
+
+gr.ChatInterface(predict).launch()