File size: 5,437 Bytes
6ad6aab 02c516e 6ad6aab 02c516e 6ad6aab 02c516e 6ad6aab 02c516e 6ad6aab 02c516e 6ad6aab 02c516e 6ad6aab |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 |
# import gradio as gr
# from huggingface_hub import InferenceClient
# """
# 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)",
# ),
# ],
# )
# if __name__ == "__main__":
# demo.launch()
import gradio as gr
from huggingface_hub import InferenceClient
import torch
from transformers import RagRetriever, RagSequenceForGeneration, AutoTokenizer
"""
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
"""
def strip_title(title):
if title.startswith('"'):
title = title[1:]
if title.endswith('"'):
title = title[:-1]
return title
def retrieved_info(rag_model, query):
# Tokenize query
retriever_input_ids = rag_model.retriever.question_encoder_tokenizer.batch_encode_plus(
[query],
return_tensors="pt",
padding=True,
truncation=True,
)["input_ids"].to(device)
# Retrieve documents
question_enc_outputs = rag_model.rag.question_encoder(retriever_input_ids)
question_enc_pool_output = question_enc_outputs[0]
result = rag_model.retriever(
retriever_input_ids,
question_enc_pool_output.cpu().detach().to(torch.float32).numpy(),
prefix=rag_model.rag.generator.config.prefix,
n_docs=rag_model.config.n_docs,
return_tensors="pt",
)
# Display retrieved documents including URLs
all_docs = rag_model.retriever.index.get_doc_dicts(result.doc_ids)
retrieved_context = []
for docs in all_docs:
titles = [strip_title(title) for title in docs["title"]]
texts = docs["text"]
for title, text in zip(titles, texts):
#print(f"Title: {title}")
#print(f"Context: {text}")
retrieved_context.append(f"{title}: {text}")
answer = retrieved_context
def respond(
message,
history: list[tuple[str, str]],
system_message,
):
# Load model
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
dataset_path = "/IndexedDataFiles/my_knowledge_dataset"
index_path = "/IndexedDataFiles/my_knowledge_dataset_hnsw_index.faiss"
tokenizer = AutoTokenizer.from_pretrained("facebook/rag-sequence-nq")
retriever = RagRetriever.from_pretrained("facebook/rag-sequence-nq", index_name="custom",
passages_path = dataset_path,
index_path = index_path,
n_docs = 1)
rag_model = RagSequenceForGeneration.from_pretrained('facebook/rag-sequence-nq', retriever=retriever)
rag_model.retriever.init_retrieval()
rag_model.to(device)
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 = ""
response = retrieved_info(rag_model, message)
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)",
),
],
)
if __name__ == "__main__":
demo.launch()
|