Update app.py
Browse files
app.py
CHANGED
|
@@ -1,64 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
| 1 |
import gradio as gr
|
| 2 |
-
|
| 3 |
|
| 4 |
-
|
| 5 |
-
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
|
| 6 |
-
"""
|
| 7 |
-
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
|
| 8 |
|
|
|
|
| 9 |
|
| 10 |
-
|
| 11 |
-
message,
|
| 12 |
-
history: list[tuple[str, str]],
|
| 13 |
-
system_message,
|
| 14 |
-
max_tokens,
|
| 15 |
-
temperature,
|
| 16 |
-
top_p,
|
| 17 |
-
):
|
| 18 |
-
messages = [{"role": "system", "content": system_message}]
|
| 19 |
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
response = ""
|
| 29 |
-
|
| 30 |
-
for message in client.chat_completion(
|
| 31 |
-
messages,
|
| 32 |
-
max_tokens=max_tokens,
|
| 33 |
-
stream=True,
|
| 34 |
-
temperature=temperature,
|
| 35 |
-
top_p=top_p,
|
| 36 |
-
):
|
| 37 |
-
token = message.choices[0].delta.content
|
| 38 |
|
| 39 |
-
|
| 40 |
-
|
|
|
|
| 41 |
|
|
|
|
| 42 |
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
""
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
|
| 50 |
-
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
|
| 51 |
-
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
|
| 52 |
-
gr.Slider(
|
| 53 |
-
minimum=0.1,
|
| 54 |
-
maximum=1.0,
|
| 55 |
-
value=0.95,
|
| 56 |
-
step=0.05,
|
| 57 |
-
label="Top-p (nucleus sampling)",
|
| 58 |
-
),
|
| 59 |
-
],
|
| 60 |
)
|
| 61 |
|
| 62 |
-
|
| 63 |
-
if __name__ == "__main__":
|
| 64 |
-
demo.launch()
|
|
|
|
| 1 |
+
from dotenv import load_dotenv
|
| 2 |
+
from langchain_ollama import ChatOllama
|
| 3 |
+
from langchain_core.prompts import ChatPromptTemplate
|
| 4 |
import gradio as gr
|
| 5 |
+
import os
|
| 6 |
|
| 7 |
+
load_dotenv()
|
|
|
|
|
|
|
|
|
|
| 8 |
|
| 9 |
+
OLLAMA_BASE_URL = os.getenv("OLLAMA_BASE_URL")
|
| 10 |
|
| 11 |
+
llm = ChatOllama(model="llama3", base_url = OLLAMA_BASE_URL, temperature=0.5)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
+
#prompt = ChatPromptTemplate.from_template("Tell me a joke about a {subject}")
|
| 14 |
+
prompt = ChatPromptTemplate.from_messages(
|
| 15 |
+
[
|
| 16 |
+
("system","Generate a list of synonyms for the following word, only give 5 words and no extra messages."),
|
| 17 |
+
("human","{input}")
|
| 18 |
+
]
|
| 19 |
+
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
+
def synonyms(text):
|
| 22 |
+
response = chain.invoke({"input":text})
|
| 23 |
+
return response.content
|
| 24 |
|
| 25 |
+
chain = prompt | llm
|
| 26 |
|
| 27 |
+
demo = gr.Interface(
|
| 28 |
+
fn = synonyms,
|
| 29 |
+
inputs = ["text"],
|
| 30 |
+
outputs = ["text"],
|
| 31 |
+
title = "Synonym Generator",
|
| 32 |
+
description = "Generate a list of synonyms for the following word, only give 5 words with examples i.e use word in the sentences."
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
)
|
| 34 |
|
| 35 |
+
demo.launch()
|
|
|
|
|
|