danielcwq hwchase17 commited on
Commit
d49472a
0 Parent(s):

Duplicate from hwchase17/chat-your-data-state-of-the-union

Browse files

Co-authored-by: Harrison Chase <hwchase17@users.noreply.huggingface.co>

Files changed (8) hide show
  1. .gitattributes +34 -0
  2. README.md +14 -0
  3. app.py +102 -0
  4. cli_app.py +17 -0
  5. ingest_data.py +23 -0
  6. query_data.py +34 -0
  7. requirements.txt +5 -0
  8. vectorstore.pkl +0 -0
.gitattributes ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tflite filter=lfs diff=lfs merge=lfs -text
29
+ *.tgz filter=lfs diff=lfs merge=lfs -text
30
+ *.wasm filter=lfs diff=lfs merge=lfs -text
31
+ *.xz filter=lfs diff=lfs merge=lfs -text
32
+ *.zip filter=lfs diff=lfs merge=lfs -text
33
+ *.zst filter=lfs diff=lfs merge=lfs -text
34
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ title: Chat Your Data State Of The Union
3
+ emoji: 📊
4
+ colorFrom: gray
5
+ colorTo: purple
6
+ sdk: gradio
7
+ sdk_version: 3.17.0
8
+ app_file: app.py
9
+ pinned: false
10
+ license: mit
11
+ duplicated_from: hwchase17/chat-your-data-state-of-the-union
12
+ ---
13
+
14
+ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
app.py ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import os
2
+ from typing import Optional, Tuple
3
+
4
+ import gradio as gr
5
+ import pickle
6
+ from query_data import get_chain
7
+ from threading import Lock
8
+
9
+ with open("vectorstore.pkl", "rb") as f:
10
+ vectorstore = pickle.load(f)
11
+
12
+
13
+ def set_openai_api_key(api_key: str):
14
+ """Set the api key and return chain.
15
+ If no api_key, then None is returned.
16
+ """
17
+ if api_key:
18
+ os.environ["OPENAI_API_KEY"] = api_key
19
+ chain = get_chain(vectorstore)
20
+ os.environ["OPENAI_API_KEY"] = ""
21
+ return chain
22
+
23
+ class ChatWrapper:
24
+
25
+ def __init__(self):
26
+ self.lock = Lock()
27
+ def __call__(
28
+ self, api_key: str, inp: str, history: Optional[Tuple[str, str]], chain
29
+ ):
30
+ """Execute the chat functionality."""
31
+ self.lock.acquire()
32
+ try:
33
+ history = history or []
34
+ # If chain is None, that is because no API key was provided.
35
+ if chain is None:
36
+ history.append((inp, "Please paste your OpenAI key to use"))
37
+ return history, history
38
+ # Set OpenAI key
39
+ import openai
40
+ openai.api_key = api_key
41
+ # Run chain and append input.
42
+ output = chain({"question": inp, "chat_history": history})["answer"]
43
+ history.append((inp, output))
44
+ except Exception as e:
45
+ raise e
46
+ finally:
47
+ self.lock.release()
48
+ return history, history
49
+
50
+ chat = ChatWrapper()
51
+
52
+ block = gr.Blocks(css=".gradio-container {background-color: lightgray}")
53
+
54
+ with block:
55
+ with gr.Row():
56
+ gr.Markdown("<h3><center>Chat-Your-Data (State-of-the-Union)</center></h3>")
57
+
58
+ openai_api_key_textbox = gr.Textbox(
59
+ placeholder="Paste your OpenAI API key (sk-...)",
60
+ show_label=False,
61
+ lines=1,
62
+ type="password",
63
+ )
64
+
65
+ chatbot = gr.Chatbot()
66
+
67
+ with gr.Row():
68
+ message = gr.Textbox(
69
+ label="What's your question?",
70
+ placeholder="Ask questions about the most recent state of the union",
71
+ lines=1,
72
+ )
73
+ submit = gr.Button(value="Send", variant="secondary").style(full_width=False)
74
+
75
+ gr.Examples(
76
+ examples=[
77
+ "What did the president say about Kentaji Brown Jackson",
78
+ "Did he mention Stephen Breyer?",
79
+ "What was his stance on Ukraine",
80
+ ],
81
+ inputs=message,
82
+ )
83
+
84
+ gr.HTML("Demo application of a LangChain chain.")
85
+
86
+ gr.HTML(
87
+ "<center>Powered by <a href='https://github.com/hwchase17/langchain'>LangChain 🦜️🔗</a></center>"
88
+ )
89
+
90
+ state = gr.State()
91
+ agent_state = gr.State()
92
+
93
+ submit.click(chat, inputs=[openai_api_key_textbox, message, state, agent_state], outputs=[chatbot, state])
94
+ message.submit(chat, inputs=[openai_api_key_textbox, message, state, agent_state], outputs=[chatbot, state])
95
+
96
+ openai_api_key_textbox.change(
97
+ set_openai_api_key,
98
+ inputs=[openai_api_key_textbox],
99
+ outputs=[agent_state],
100
+ )
101
+
102
+ block.launch(debug=True)
cli_app.py ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import pickle
2
+ from query_data import get_chain
3
+
4
+
5
+ if __name__ == "__main__":
6
+ with open("vectorstore.pkl", "rb") as f:
7
+ vectorstore = pickle.load(f)
8
+ qa_chain = get_chain(vectorstore)
9
+ chat_history = []
10
+ print("Chat with your docs!")
11
+ while True:
12
+ print("Human:")
13
+ question = input()
14
+ result = qa_chain({"question": question, "chat_history": chat_history})
15
+ chat_history.append((question, result["answer"]))
16
+ print("AI:")
17
+ print(result["answer"])
ingest_data.py ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from langchain.text_splitter import RecursiveCharacterTextSplitter
2
+ from langchain.document_loaders import UnstructuredFileLoader
3
+ from langchain.vectorstores.faiss import FAISS
4
+ from langchain.embeddings import OpenAIEmbeddings
5
+ import pickle
6
+
7
+ # Load Data
8
+ loader = UnstructuredFileLoader("state_of_the_union.txt")
9
+ raw_documents = loader.load()
10
+
11
+ # Split text
12
+ text_splitter = RecursiveCharacterTextSplitter()
13
+ documents = text_splitter.split_documents(raw_documents)
14
+
15
+
16
+ # Load Data to vectorstore
17
+ embeddings = OpenAIEmbeddings()
18
+ vectorstore = FAISS.from_documents(documents, embeddings)
19
+
20
+
21
+ # Save vectorstore
22
+ with open("vectorstore.pkl", "wb") as f:
23
+ pickle.dump(vectorstore, f)
query_data.py ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from langchain.prompts.prompt import PromptTemplate
2
+ from langchain.llms import OpenAI
3
+ from langchain.chains import ChatVectorDBChain
4
+
5
+ _template = """Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question.
6
+ You can assume the question about the most recent state of the union address.
7
+
8
+ Chat History:
9
+ {chat_history}
10
+ Follow Up Input: {question}
11
+ Standalone question:"""
12
+ CONDENSE_QUESTION_PROMPT = PromptTemplate.from_template(_template)
13
+
14
+ template = """You are an AI assistant for answering questions about the most recent state of the union address.
15
+ You are given the following extracted parts of a long document and a question. Provide a conversational answer.
16
+ If you don't know the answer, just say "Hmm, I'm not sure." Don't try to make up an answer.
17
+ If the question is not about the most recent state of the union, politely inform them that you are tuned to only answer questions about the most recent state of the union.
18
+ Question: {question}
19
+ =========
20
+ {context}
21
+ =========
22
+ Answer in Markdown:"""
23
+ QA_PROMPT = PromptTemplate(template=template, input_variables=["question", "context"])
24
+
25
+
26
+ def get_chain(vectorstore):
27
+ llm = OpenAI(temperature=0)
28
+ qa_chain = ChatVectorDBChain.from_llm(
29
+ llm,
30
+ vectorstore,
31
+ qa_prompt=QA_PROMPT,
32
+ condense_question_prompt=CONDENSE_QUESTION_PROMPT,
33
+ )
34
+ return qa_chain
requirements.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ langchain
2
+ openai
3
+ unstructured
4
+ faiss-cpu
5
+ gradio
vectorstore.pkl ADDED
Binary file (103 kB). View file