ContextQMD
Back to Llama Index

Chat Engine - Simple Mode REPL

docs/examples/chat_engine/chat_engine_repl.ipynb

0.14.211.4 KB
Original Source

<a href="https://colab.research.google.com/github/run-llama/llama_index/blob/main/docs/examples/chat_engine/chat_engine_repl.ipynb" target="_parent"></a>

Chat Engine - Simple Mode REPL

If you're opening this Notebook on colab, you will probably need to install LlamaIndex 🦙.

python
%pip install llama-index-llms-openai
python
!pip install llama-index

Get started in 3 lines of code

Using GPT3 ("text-davinci-003")

python
from llama_index.core.chat_engine import SimpleChatEngine

chat_engine = SimpleChatEngine.from_defaults()
chat_engine.chat_repl()

Customize LLM

Use ChatGPT ("gpt-3.5-turbo")

python
from llama_index.llms.openai import OpenAI

llm = OpenAI(temperature=0.0, model="gpt-3.5-turbo")
python
from llama_index.core.chat_engine import SimpleChatEngine

chat_engine = SimpleChatEngine.from_defaults(llm=llm)
chat_engine.chat_repl()

Streaming Support

python
from llama_index.llms.openai import OpenAI

llm = OpenAI(temperature=0.0, model="gpt-3.5-turbo-0613")
python
from llama_index.core.chat_engine import SimpleChatEngine

chat_engine = SimpleChatEngine.from_defaults(llm=llm)
python
response = chat_engine.stream_chat(
    "Write me a poem about raining cats and dogs."
)
for token in response.response_gen:
    print(token, end="")