Initial Commit

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+data/s-class-manual/index.faiss filter=lfs diff=lfs merge=lfs -text

InnovationHub/llm/chain.py

@@ -0,0 +1,91 @@
+import os
+import pprint
+import codecs
+import chardet
+import gradio as gr
+from langchain.llms import HuggingFacePipeline
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from langchain import OpenAI, ConversationChain, LLMChain, PromptTemplate
+from langchain.chains.conversation.memory import ConversationalBufferWindowMemory
+from EdgeGPT import Chatbot
+
+db_path = 'data/s-class-manual'
+cookie_path = 'data/cookies.json'
+embeddings = HuggingFaceEmbeddings()
+
+
+index = FAISS.load_local(folder_path=db_path, embeddings=embeddings)
+bot = Chatbot(cookiePath=cookie_path)
+
+def init_chain():
+    template = """
+    {history}
+    Human: {human_input}
+    Assistant:"""
+
+    prompt = PromptTemplate(
+        input_variables=["history", "human_input"],
+        template=template
+    )
+
+    chatgpt_chain = LLMChain(
+        llm=OpenAI(temperature=0),
+        prompt=prompt,
+        verbose=True,
+        memory=ConversationalBufferWindowMemory(k=2),
+    )
+    human_input = """I want you to act as a voice assistant for a mercedes-benz vehicle. I will provide you with exerts from a vehicle manual. You must use the exerts to answer the user question as best as you can. If you are unsure about the answer, you will truthfully say "not sure"."""
+    bot_response = chatgpt_chain.predict(human_input=human_input)
+    print(bot_response)
+    return chatgpt_chain
+
+
+def get_prompt(question, index, k=4):
+    prompt = """I need information from my vehicle manual. I will provide an [EXCERT] from the manual. Use the [EXCERT] and nothing else to answer the [QUESTION]. You must refer to the "[EXCERT]" as "S-Clss Manual" in your response. Here is the [EXCERT]:"""
+    similar_docs = index.similarity_search(query=question, k=k)
+    context = []
+    for d in similar_docs:
+        content = d.page_content
+        context.append(content)
+    user_input = prompt + '\n[EXCERT]' + '\n' + \
+        '\n'.join(context[:k]) + '\n' + '[QUESTION]\n' + question
+    return user_input
+
+
+async def ask_question(question, index, backend='bing', k=2, create_bot=False):
+    global bot
+    if bot is None or create_bot:
+        bot = Chatbot(cookiePath=cookie_path)
+    if backend == 'bing':
+        prompt = get_prompt(question=question, index=index, k=k)
+        response = (await bot.ask(prompt=prompt))["item"]["messages"][1]["adaptiveCards"][0]["body"][0]["text"]
+    elif backend == 'gpt3':
+        prompt = get_prompt(question=question, index=index, k=k)
+        response = chatgpt_chain.predict(human_input=prompt)
+    else:
+        raise ValueError(f"Invalid backend specified: {backend}")
+    return response
+
+
+async def chatbot(question, create_bot=False, k=2):
+    response = await ask_question(question=question, index=index, backend='bing', k=k, create_bot=create_bot)
+    return response
+
+
+def start_ui():
+	chatbot_interface = gr.Interface(
+		fn=chatbot,
+		inputs=["text", gr.inputs.Checkbox(label="Create bot"), gr.inputs.Slider(
+			minimum=1, maximum=10, step=1, label="k")],
+		outputs="text",
+		title="Owner's Manual",
+		description="Ask your vehicle manual and get a response.",
+		examples=[
+			["What are the different features of the dashboard console?", True, 2],
+			["What do they do?", False, 3]
+		]
+	)
+
+	chatbot_interface.launch()

InnovationHub/llm/vector_store.py

@@ -0,0 +1,81 @@
+import os
+import pprint
+import codecs
+import chardet
+import gradio as gr
+from langchain.llms import HuggingFacePipeline
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from langchain import OpenAI, ConversationChain, LLMChain, PromptTemplate
+from langchain.chains.conversation.memory import ConversationalBufferWindowMemory
+from EdgeGPT import Chatbot
+
+
+def get_content(input_file):
+    # Read the input file in binary mode
+    with open(input_file, 'rb') as f:
+        raw_data = f.read()
+
+    # Detect the encoding of the file
+    result = chardet.detect(raw_data)
+    encoding = result['encoding']
+
+    # Decode the contents using the detected encoding
+    with codecs.open(input_file, 'r', encoding=encoding) as f:
+        raw_text = f.read()
+
+    # Return the content of the input file
+    return raw_text
+
+
+def create_docs(input_file):
+    # Create a text splitter object with a separator character
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=1000,
+        chunk_overlap=0,
+        length_function=len,
+    )
+
+    basename = os.path.basename(input_file)
+    basename = os.path.splitext(basename)[0]
+    texts = get_content(input_file=input_file)
+    metadatas = {'source': basename}
+    docs = text_splitter.create_documents(texts=[texts], metadatas=[metadatas])
+    return docs
+
+
+def get_similar_docs(query, index):
+    similar_docs = index.similarity_search(query=query)
+    result = [(d.summary, d.metadata) for d in similar_docs]
+    return result
+
+
+def convert_to_html(similar_docs):
+    result = []
+    for summary, metadata in similar_docs:
+        record = '<tr><td>' + summary + '</td><td>' + \
+            metadata['source'] + '</td></tr>'
+        result.append(record)
+    html = '<table><thead><th>Page Content</th><th>Source</th></thead><tbody>' + \
+        '\n'.join(result) + '</tbody></table>'
+    return html
+
+
+def start_ui(index):
+    def query_index(query):
+        similar_docs = get_similar_docs(query=query, index=index)
+        formatted_output = convert_to_html(similar_docs=similar_docs)
+        return formatted_output
+
+    # Define input and output types
+    input = gr.inputs.Textbox(lines=2)
+    output = gr.outputs.HTML()
+
+    # Create interface object
+    iface = gr.Interface(fn=query_index,
+                         inputs=input,
+                         outputs=output)
+
+    # Launch interface
+    iface.launch()

app.py

@@ -0,0 +1,31 @@
+from InnovationHub.llm.vector_store import *
+from InnovationHub.llm.chain import *
+"""
+# Create the vector index
+db_path = "./data/s-class-manual"
+# docs = create_docs(input_file=input_file)
+embeddings = HuggingfaceEmbeddings()
+index = FAISS(docs=docs, folder_path=db_path, embeddings=embeddings)
+
+
+"""
+# Launch the Gradio UI
+def start_gradio():
+    chatbot_interface = gr.Interface(
+        fn=chatbot,
+        inputs=["text", gr.inputs.Checkbox(label="Create bot"), gr.inputs.Slider(
+            minimum=1, maximum=10, step=1, label="k")],
+        outputs="text",
+        title="Owner's Manual",
+        description="Ask your vehicle manual and get a response.",
+        examples=[
+            ["What are the different features of the dashboard console?", True, 2],
+            ["What do they do?", False, 3]
+        ]
+    )
+    chatbot_interface.launch()
+
+
+if __name__ == '__main__':
+    start_ui()
+

data/cookies.json

@@ -0,0 +1,334 @@
+[
+    {
+        "domain": ".bing.com",
+        "expirationDate": 1693084730.995954,
+        "hostOnly": false,
+        "httpOnly": false,
+        "name": "SnrOvr",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": false,
+        "storeId": null,
+        "value": "X=rebateson"
+    },
+    {
+        "domain": ".bing.com",
+        "expirationDate": 1693084728.242456,
+        "hostOnly": false,
+        "httpOnly": false,
+        "name": "SRCHUSR",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": false,
+        "storeId": null,
+        "value": "DOB=20230213&T=1677532610000&TPC=1677532618000&POEX=W"
+    },
+    {
+        "domain": "www.bing.com",
+        "expirationDate": 1677534414,
+        "hostOnly": true,
+        "httpOnly": false,
+        "name": "ai_session",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": false,
+        "storeId": null,
+        "value": "T/ScFymgAbapbThIbe8VVn|1677532614979|1677532614979"
+    },
+    {
+        "domain": ".bing.com",
+        "expirationDate": 1677575810.751611,
+        "hostOnly": false,
+        "httpOnly": true,
+        "name": "SUID",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": false,
+        "storeId": null,
+        "value": "A"
+    },
+    {
+        "domain": ".bing.com",
+        "expirationDate": 1678137537.360376,
+        "hostOnly": false,
+        "httpOnly": false,
+        "name": "SRCHHPGUSR",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": false,
+        "storeId": null,
+        "value": "SRCHLANG=en&BRW=XW&BRH=M&CW=1920&CH=951&SCW=1903&SCH=3553&DPR=1.0&UTC=-300&DM=1&HV=1677532731&PRVCW=1920&PRVCH=951&WTS=63813129410"
+    },
+    {
+        "domain": ".bing.com",
+        "expirationDate": 1693084729.526404,
+        "hostOnly": false,
+        "httpOnly": false,
+        "name": "ANON",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": false,
+        "storeId": null,
+        "value": "A=0CEEFDC684B6E0003319CE0CFFFFFFFF&E=1bfb&W=1"
+    },
+    {
+        "domain": "www.bing.com",
+        "expirationDate": 1678137414.836653,
+        "hostOnly": true,
+        "httpOnly": false,
+        "name": "MicrosoftApplicationsTelemetryDeviceId",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": false,
+        "storeId": null,
+        "value": "e73ad670-27f9-42a1-ab2c-11ba565d0d40"
+    },
+    {
+        "domain": ".bing.com",
+        "hostOnly": false,
+        "httpOnly": false,
+        "name": "_SS",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": true,
+        "storeId": null,
+        "value": "SID=11F05B259A64654F23E7496D9B066475&R=615&RB=615&GB=0&RG=0&RP=615&OCID=MY0291"
+    },
+    {
+        "domain": ".bing.com",
+        "hostOnly": false,
+        "httpOnly": false,
+        "name": "ipv6",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": true,
+        "storeId": null,
+        "value": "hit=1677536212634&t=4"
+    },
+    {
+        "domain": ".bing.com",
+        "hostOnly": false,
+        "httpOnly": false,
+        "name": "dsc",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": true,
+        "storeId": null,
+        "value": "order=News"
+    },
+    {
+        "domain": ".bing.com",
+        "expirationDate": 1678742329.526777,
+        "hostOnly": false,
+        "httpOnly": false,
+        "name": "_U",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": false,
+        "storeId": null,
+        "value": "187HIdeq_GJRLjSKHkwb4YIkSMlAVA9OfUbP61r-Qf9tviJx-N77BZ89XjJB7Poh0Oq_nWPX8520bV_6aOrt_NSNc8T3gPdFl91ZZgNfdPKuvrVa9x1alQXULme4YfoDYl0RVx3Tgz4zzu17UP8gUE4QXJrp3vEqYUPlo_7PxE-NyGIpI2jJYwyUqJndAHkziKootSgBohaAS4Y60GmG5hA"
+    },
+    {
+        "domain": ".bing.com",
+        "expirationDate": 1682258471.766994,
+        "hostOnly": false,
+        "httpOnly": false,
+        "name": "SRCHD",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": false,
+        "storeId": null,
+        "value": "AF=NOFORM"
+    },
+    {
+        "domain": ".bing.com",
+        "expirationDate": 1693084729.52654,
+        "hostOnly": false,
+        "httpOnly": false,
+        "name": "PPLState",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": false,
+        "storeId": null,
+        "value": "1"
+    },
+    {
+        "domain": ".bing.com",
+        "expirationDate": 1682258471.766982,
+        "hostOnly": false,
+        "httpOnly": true,
+        "name": "_EDGE_V",
+        "path": "/",
+        "sameSite": null,
+        "secure": false,
+        "session": false,
+        "storeId": null,
+        "value": "1"
+    },
+    {
+        "domain": ".bing.com",
+        "expirationDate": 1693084729.526456,
+        "hostOnly": false,
+        "httpOnly": false,
+        "name": "NAP",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": false,
+        "storeId": null,
+        "value": "V=1.9&E=1ba1&C=5ZkcuIJ3eTDwUrPvHRSZnNESxen1NOb4VIgq9GwVEvhgwC07YecacA&W=1"
+    },
+    {
+        "domain": ".bing.com",
+        "expirationDate": 1693084731.141086,
+        "hostOnly": false,
+        "httpOnly": false,
+        "name": "_RwBf",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": false,
+        "storeId": null,
+        "value": "ilt=4&ihpd=0&ispd=1&rc=615&rb=615&gb=0&rg=0&pc=615&mtu=0&rbb=0.0&g=0&cid=&clo=0&v=4&l=2023-02-27T08:00:00.0000000Z&lft=0001-01-01T00:00:00.0000000&aof=0&o=16&p=bingcopilotwaitlist&c=MY00IA&t=5310&s=2023-02-13T21:02:03.7661483+00:00&ts=2023-02-27T21:18:50.8966302+00:00&rwred=0&wls=2&lka=0&lkt=0&TH=&r=1&mta=0&e=qrjt2pnF9zgGkFyTjKYk_pR5phu-vA3LG-HB7vbdRi5701fZlCuHQQ0hG_jHg-igw_yz1W8hZCN-9vQlB0HB9A&A=0CEEFDC684B6E0003319CE0CFFFFFFFF"
+    },
+    {
+        "domain": ".bing.com",
+        "expirationDate": 1678137412.161922,
+        "hostOnly": false,
+        "httpOnly": false,
+        "name": "_UR",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": false,
+        "storeId": null,
+        "value": "QS=0&TQS=0"
+    },
+    {
+        "domain": ".bing.com",
+        "hostOnly": false,
+        "httpOnly": true,
+        "name": "_EDGE_S",
+        "path": "/",
+        "sameSite": null,
+        "secure": false,
+        "session": true,
+        "storeId": null,
+        "value": "SID=39AA513F3093609E2B0443FA31F161B1"
+    },
+    {
+        "domain": ".bing.com",
+        "hostOnly": false,
+        "httpOnly": true,
+        "name": "CSRFCookie",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": true,
+        "storeId": null,
+        "value": "c2152df9-052a-46ab-aaae-a7ac4f74cb61"
+    },
+    {
+        "domain": "www.bing.com",
+        "expirationDate": 1693084733.570912,
+        "hostOnly": true,
+        "httpOnly": true,
+        "name": "MUIDB",
+        "path": "/",
+        "sameSite": null,
+        "secure": false,
+        "session": false,
+        "storeId": null,
+        "value": "3F1FBCB532FD6CAB0705AEFD339F6D8E"
+    },
+    {
+        "domain": ".bing.com",
+        "expirationDate": 1693084612.247552,
+        "hostOnly": false,
+        "httpOnly": false,
+        "name": "_HPVN",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": false,
+        "storeId": null,
+        "value": "CS=eyJQbiI6eyJDbiI6NCwiU3QiOjAsIlFzIjowLCJQcm9kIjoiUCJ9LCJTYyI6eyJDbiI6NCwiU3QiOjAsIlFzIjowLCJQcm9kIjoiSCJ9LCJReiI6eyJDbiI6NCwiU3QiOjAsIlFzIjowLCJQcm9kIjoiVCJ9LCJBcCI6dHJ1ZSwiTXV0ZSI6dHJ1ZSwiTGFkIjoiMjAyMy0wMi0yN1QwMDowMDowMFoiLCJJb3RkIjowLCJHd2IiOjAsIkRmdCI6bnVsbCwiTXZzIjowLCJGbHQiOjAsIkltcCI6OX0="
+    },
+    {
+        "domain": ".bing.com",
+        "expirationDate": 1693084729.526585,
+        "hostOnly": false,
+        "httpOnly": true,
+        "name": "KievRPSSecAuth",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": false,
+        "storeId": null,
+        "value": "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"
+    },
+    {
+        "domain": ".bing.com",
+        "expirationDate": 1682258471.766947,
+        "hostOnly": false,
+        "httpOnly": false,
+        "name": "MUID",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": false,
+        "storeId": null,
+        "value": "3F1FBCB532FD6CAB0705AEFD339F6D8E"
+    },
+    {
+        "domain": ".bing.com",
+        "expirationDate": 1682258471.767004,
+        "hostOnly": false,
+        "httpOnly": false,
+        "name": "SRCHUID",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": false,
+        "storeId": null,
+        "value": "V=2&GUID=14CDDFE80626458BA11A57DAD375375A&dmnchg=1"
+    },
+    {
+        "domain": ".bing.com",
+        "expirationDate": 1678742329.678283,
+        "hostOnly": false,
+        "httpOnly": true,
+        "name": "WLID",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": false,
+        "storeId": null,
+        "value": "SPtvurHJd3r52IJoz+GIPFUD0x/sd9UoT6NOitZQR3XtKw4qP9lEUzFkD+Gr3uXVaSBDTJb4MwnYGWl5sokdnzpNmkQR7NokV7nrirpPzec="
+    },
+    {
+        "domain": ".bing.com",
+        "hostOnly": false,
+        "httpOnly": false,
+        "name": "WLS",
+        "path": "/",
+        "sameSite": "no_restriction",
+        "secure": true,
+        "session": true,
+        "storeId": null,
+        "value": "C=c696172d38f1d852&N=chase"
+    }
+]

data/s-class-manual/index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cc3da5a2b2c309ca81cc41a1cf1192c619c91ee1a1bfac39cf58b99bc8995fa
+size 3062829

data/s-class-manual/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1749b9feae4721bbc0390b20cd9ceef84cb531d8fda7a44b89797e65b144af5
+size 1023700