File size: 3,663 Bytes
1afde00 af5492a 3cd0964 af5492a 3cd0964 af5492a 3cd0964 af5492a 3cd0964 |
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 |
import os
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")
ABS_PATH = os.path.dirname(os.path.abspath(__file__))
DB_DIR = os.path.join(ABS_PATH, "db")
def replace_newlines_and_spaces(text):
# Replace all newline characters with spaces
text = text.replace("\n", " ")
# Replace multiple spaces with a single space
text = re.sub(r'\s+', ' ', text)
return text
def get_documents():
return PyPDFLoader("AI-smart-water-management-systems.pdf").load()
def init_chromadb():
# Delete existing index directory and recreate the directory
if os.path.exists(DB_DIR):
import shutil
shutil.rmtree(DB_DIR, ignore_errors=True)
os.mkdir(DB_DIR)
documents = []
for num, doc in enumerate(get_documents()):
doc.page_content = replace_newlines_and_spaces(doc.page_content)
documents.append(doc)
# Split the documents into chunks
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
texts = text_splitter.split_documents(documents)
# Select which embeddings we want to use
#embeddings = OpenAIEmbeddings()
#query_chromadb()
# Create the vectorestore to use as the index
vectorstore = Chroma.from_documents(texts, embeddings, persist_directory=DB_DIR)
vectorstore.persist()
print(vectorstore)
vectorstore = None
def query_chromadb(ASK):
if not os.path.exists(DB_DIR):
raise Exception(f"{DB_DIR} does not exist, nothing can be queried")
# Select which embeddings we want to use
embeddings = OpenAIEmbeddings()
# Load Vector store from local disk
vectorstore = Chroma(persist_directory=DB_DIR, embedding_function=embeddings)
result = vectorstore.similarity_search_with_score(query=ASK, k=4)
jsonable_result = jsonable_encoder(result)
print(json.dumps(jsonable_result, indent=2))
return json.dumps(jsonable_result, indent=2)
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
yield query_chromadb(message)
"""
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)",
),
],
)
def main():
init_chromadb()
demo.launch()
if __name__ == "__main__":
main()
#demo.launch()
|