First commit

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/Chat_QnA_v2.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,34 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <value>
+          <list size="14">
+            <item index="0" class="java.lang.String" itemvalue="scikit-image" />
+            <item index="1" class="java.lang.String" itemvalue="scipy" />
+            <item index="2" class="java.lang.String" itemvalue="thop" />
+            <item index="3" class="java.lang.String" itemvalue="tabulate" />
+            <item index="4" class="java.lang.String" itemvalue="opencv-python" />
+            <item index="5" class="java.lang.String" itemvalue="torch" />
+            <item index="6" class="java.lang.String" itemvalue="numpy" />
+            <item index="7" class="java.lang.String" itemvalue="loguru" />
+            <item index="8" class="java.lang.String" itemvalue="torchvision" />
+            <item index="9" class="java.lang.String" itemvalue="tqdm" />
+            <item index="10" class="java.lang.String" itemvalue="matplotlib" />
+            <item index="11" class="java.lang.String" itemvalue="pycocotools" />
+            <item index="12" class="java.lang.String" itemvalue="opencv_python" />
+            <item index="13" class="java.lang.String" itemvalue="Pillow" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="PyPep8NamingInspection" enabled="true" level="WEAK WARNING" enabled_by_default="true">
+      <option name="ignoredErrors">
+        <list>
+          <option value="N806" />
+        </list>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/Chat_QnA_v2.iml" filepath="$PROJECT_DIR$/.idea/Chat_QnA_v2.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

app.py

@@ -0,0 +1,256 @@
+import os
+import gradio as gr
+import openai
+import re
+import numpy as np
+from sklearn.neighbors import NearestNeighbors
+import tensorflow_hub as hub
+import fitz
+
+my_api_key = "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"
+openai.api_key = my_api_key
+
+
+def add_source_numbers(lst, source_name="Source", use_source=True):
+    if use_source:
+        return [f'[{idx + 1}]\t "{item[0]}"\n{source_name}: {item[1]}' for idx, item in enumerate(lst)]
+    else:
+        return [f'[{idx + 1}]\t "{item}"' for idx, item in enumerate(lst)]
+
+
+def add_details(lst):
+    nodes = []
+    for index, txt in enumerate(lst):
+        brief = txt[:25].replace("\n", "")
+        nodes.append(
+            f"<details><summary>{brief}...</summary><p>{txt}</p></details>"
+        )
+    return nodes
+
+
+prompt_template = "Instructions: Compose a comprehensive reply to the query using the search results given. " \
+                  "Make sure to cite results using [number] notation after the reference. " \
+                  "If the search results mention multiple subjects " \
+                  "with the same name, create separate answers for each. Only include information found in the results and " \
+                  "don't add any additional information. Make sure the answer is correct and don't output false content. " \
+                  "Ignore outlier search results which has nothing to do with the question. Only answer what is asked. " \
+                  "The answer should be short and concise.\n\nQuery: {question}\nAnswer: "
+
+# MODELS = ["universal-sentence-encoder", "instructor-large"]
+MODELS = ["text-davinci-001", "text-davinci-002", "text-davinci-003"]
+
+
+def add_source_numbers(lst):
+    return [item[:3] + '\t' + item[3:] for item in (lst)]
+
+
+def add_details(lst):
+    nodes = []
+    for index, txt in enumerate(lst):
+        brief = txt[:25].replace("\n", "")
+        nodes.append(
+            f"<details><summary>{brief}...</summary><p>{txt}</p></details>"
+        )
+    return nodes
+
+
+def preprocess(text):
+    text = text.replace('\n', ' ')
+    text = re.sub('\s+', ' ', text)
+    return text
+
+
+def pdf_to_text(files_src, start_page=1, end_page=None):
+    text_list = []
+    for file in files_src:
+        if os.path.splitext(file.name)[1] == ".pdf":
+            doc = fitz.open(file.name)
+            total_pages = doc.page_count
+            if end_page is None:
+                end_page = total_pages
+            for i in range(start_page - 1, end_page):
+                text = doc.load_page(i).get_text("text")
+                text = preprocess(text)
+                text_list.append(text)
+            doc.close()
+
+    return text_list
+
+
+def text_to_chunks(texts, word_length=150, start_page=1):
+    text_toks = [t.split(' ') for t in texts]
+    page_nums = []
+    chunks = []
+
+    for idx, words in enumerate(text_toks):
+        for i in range(0, len(words), word_length):
+            chunk = words[i:i + word_length]
+            if (i + word_length) > len(words) and (len(chunk) < word_length) and (
+                    len(text_toks) != (idx + 1)):
+                text_toks[idx + 1] = chunk + text_toks[idx + 1]
+                continue
+            chunk = ' '.join(chunk).strip()
+            chunk = f'[{idx + start_page}]' + ' ' + '"' + chunk + '"'
+            chunks.append(chunk)
+    return chunks
+
+
+def embedding(model, files_src, batch=1000):
+    name_file = '_'.join([os.path.basename(file.name).split('.')[0] for file in files_src])
+    embeddings_file = f"{name_file}.npy"
+    texts = pdf_to_text(files_src)
+    chunks = text_to_chunks(texts)
+    if os.path.isfile(embeddings_file):
+        embeddings = np.load(embeddings_file)
+        return embeddings, chunks
+    # texts = pdf_to_text(files_src)
+    # chunks = text_to_chunks(texts)
+    data = chunks
+    embeddings = []
+    for i in range(0, len(data), batch):
+        text_batch = data[i:(i + batch)]
+        emb_batch = model(text_batch)
+        embeddings.append(emb_batch)
+    embeddings = np.vstack(embeddings)
+    np.save(embeddings_file, embeddings)
+    return embeddings, chunks
+
+
+def get_top_chunks(inp_emb, data, n_neighbors=5):
+    n_neighbors = min(n_neighbors, len(data))
+    nn = NearestNeighbors(n_neighbors=n_neighbors)
+    nn.fit(data)
+    neighbors = nn.kneighbors(inp_emb, return_distance=False)[0]
+    return neighbors
+
+
+def predict(
+        history,
+        chatbot,
+        inputs,
+        temperature,
+        selected_model=MODELS[0],
+        files=None
+):
+    old_inputs = None
+    display_reference = []
+    if files:
+        old_inputs = inputs
+        emb_model = hub.load('https://tfhub.dev/google/universal-sentence-encoder/4')
+
+        vector_emb, chunks = embedding(emb_model, files)
+
+        input_emb = emb_model([inputs])
+        index_top_chunks = get_top_chunks(input_emb, vector_emb)
+        topn_chunks = [chunks[i] for i in index_top_chunks]
+        prompt = ""
+        prompt += 'search results:\n\n'
+        for c in topn_chunks:
+            prompt += c + '\n\n'
+        prompt += prompt_template
+        prompt += f"Query: {inputs}\nAnswer:"
+        inputs = prompt
+        reference_results = add_source_numbers(topn_chunks)
+        display_reference = add_details(reference_results)
+        display_reference = "\n\n" + "".join(display_reference)
+    else:
+        display_reference = ""
+
+    history.append(inputs)
+    if old_inputs:
+        chatbot.append((old_inputs, ""))
+    else:
+        chatbot.append((inputs, ""))
+    completions = openai.Completion.create(
+        engine=selected_model,
+        prompt=inputs,
+        max_tokens=256,
+        stop=None,
+        temperature=temperature,
+    )
+    message = completions.choices[0].text
+    # print(message)
+    if old_inputs is not None:
+        history[-1] = old_inputs
+    chatbot[-1] = (chatbot[-1][0], message + display_reference)
+    return chatbot, history
+
+
+# Create theme
+with open("assets/custom.css", "r", encoding="utf-8") as f:
+    customCSS = f.read()
+beautiful_theme = gr.themes.Soft(
+    primary_hue=gr.themes.Color(
+        c50="#02C160",
+        c100="rgba(2, 193, 96, 0.2)",
+        c200="#02C160",
+        c300="rgba(2, 193, 96, 0.32)",
+        c400="rgba(2, 193, 96, 0.32)",
+        c500="rgba(2, 193, 96, 1.0)",
+        c600="rgba(2, 193, 96, 1.0)",
+        c700="rgba(2, 193, 96, 0.32)",
+        c800="rgba(2, 193, 96, 0.32)",
+        c900="#02C160",
+        c950="#02C160",
+    ),
+    radius_size=gr.themes.sizes.radius_sm,
+).set(
+    button_primary_background_fill="#06AE56",
+    button_primary_background_fill_dark="#06AE56",
+    button_primary_background_fill_hover="#07C863",
+    button_primary_border_color="#06AE56",
+    button_primary_border_color_dark="#06AE56",
+    button_primary_text_color="#FFFFFF",
+    button_primary_text_color_dark="#FFFFFF",
+    block_title_text_color="*primary_500",
+    block_title_background_fill="*primary_100",
+    input_background_fill="#F6F6F6",
+)
+
+# Gradio app
+title = """<h1 align="left" style="min-width:200px; margin-top:6px; white-space: nowrap;">ChatGPT 🚀</h1>"""
+with gr.Blocks(css=customCSS, theme=beautiful_theme) as demo:
+    history = gr.State([])
+    user_question = gr.State("")
+
+    with gr.Row():
+        with gr.Column(scale=1):
+            gr.HTML(title)
+
+    with gr.Row().style(equal_height=True):
+        with gr.Column(scale=5):
+            with gr.Row():
+                chatbot = gr.Chatbot(elem_id="chatbot").style(height="100%")
+            with gr.Row():
+                with gr.Column(scale=12):
+                    user_input = gr.Textbox(
+                        show_label=False, placeholder="Enter here"
+                    ).style(container=False)
+                with gr.Column(min_width=70, scale=1):
+                    submitBtn = gr.Button("Send", variant="primary")
+
+        with gr.Column():
+            with gr.Column(min_width=50, scale=1):
+                with gr.Tab(label="ChatGPT"):
+                    model_select_dropdown = gr.Dropdown(
+                        label="Select model", choices=MODELS, multiselect=False, value=MODELS[0]
+                    )
+                    index_files = gr.Files(label="Files", type="file", multiple=True)
+                    gr.Markdown(
+                        "⚠️Be careful to change ⚠️\n\nIf you can't use it, please restore the default settings")
+                    with gr.Accordion("Parameter", open=False):
+                        temperature = gr.Slider(
+                            minimum=-0,
+                            maximum=1.0,
+                            value=0.0,
+                            step=0.1,
+                            interactive=True,
+                            label="Temperature",
+                        )
+    user_input.submit(predict, inputs=[history, chatbot, user_input, temperature, model_select_dropdown, index_files],
+                      outputs=[chatbot, history])
+    user_input.submit(lambda: "", None, user_input)
+    submitBtn.click(predict, inputs=[history, chatbot, user_input, temperature, model_select_dropdown, index_files],
+                    outputs=[chatbot, history])
+    submitBtn.click(lambda: "", None, user_input)
+    demo.queue(concurrency_count=10).launch(server_name="0.0.0.0", server_port=7860, debug=True)

custom.css

@@ -0,0 +1,239 @@
+:root {
+    --chatbot-color-light: #F3F3F3;
+    --chatbot-color-dark: #121111;
+}
+
+/* 覆盖gradio的页脚信息QAQ */
+footer {
+    display: none !important;
+}
+#footer{
+    text-align: center;
+}
+#footer div{
+    display: inline-block;
+}
+#footer .versions{
+    font-size: 85%;
+    opacity: 0.85;
+}
+
+/* status_display */
+#status_display {
+    display: flex;
+    min-height: 2.5em;
+    align-items: flex-end;
+    justify-content: flex-end;
+}
+#status_display p {
+    font-size: .85em;
+    font-family: monospace;
+    color: var(--body-text-color-subdued);
+}
+
+#chuanhu_chatbot, #status_display {
+    transition: all 0.6s;
+}
+
+/* usage_display */
+#usage_display {
+    position: relative;
+    margin: 0;
+    box-shadow: var(--block-shadow);
+    border-width: var(--block-border-width);
+    border-color: var(--block-border-color);
+    border-radius: var(--block-radius);
+    background: var(--block-background-fill);
+    width: 100%;
+    line-height: var(--line-sm);
+    min-height: 2em;
+}
+#usage_display p, #usage_display span {
+    margin: 0;
+    padding: .5em 1em;
+    font-size: .85em;
+    color: var(--body-text-color-subdued);
+}
+.progress-bar {
+    background-color: var(--input-background-fill);;
+    margin: 0 1em;
+    height: 20px;
+    border-radius: 10px;
+    overflow: hidden;
+}
+.progress {
+    background-color: var(--block-title-background-fill);;
+    height: 100%;
+    border-radius: 10px;
+    text-align: right;
+    transition: width 0.5s ease-in-out;
+}
+.progress-text {
+    /* color: white; */
+    color: var(--color-accent) !important;
+    font-size: 1em !important;
+    font-weight: bold;
+    padding-right: 10px;
+    line-height: 20px;
+}
+/* list */
+ol:not(.options), ul:not(.options) {
+    padding-inline-start: 2em !important;
+}
+
+/* 亮色 */
+@media (prefers-color-scheme: light) {
+    #chuanhu_chatbot {
+        background-color: var(--chatbot-color-light) !important;
+        color: #000000 !important;
+    }
+    [data-testid = "bot"] {
+        background-color: #FFFFFF !important;
+    }
+    [data-testid = "user"] {
+        background-color: #95EC69 !important;
+    }
+}
+/* 暗色 */
+@media (prefers-color-scheme: dark) {
+    #chuanhu_chatbot {
+        background-color: var(--chatbot-color-dark) !important;
+        color: #FFFFFF !important;
+    }
+    [data-testid = "bot"] {
+        background-color: #2C2C2C !important;
+    }
+    [data-testid = "user"] {
+        background-color: #26B561 !important;
+    }
+    body {
+        background-color: var(--neutral-950) !important;
+    }
+}
+
+/* 对话气泡 */
+[class *= "message"] {
+    border-radius: var(--radius-xl) !important;
+    border: none;
+    padding: var(--spacing-xl) !important;
+    font-size: var(--text-md) !important;
+    line-height: var(--line-md) !important;
+    min-height: calc(var(--text-md)*var(--line-md) + 2*var(--spacing-xl));
+    min-width: calc(var(--text-md)*var(--line-md) + 2*var(--spacing-xl));
+}
+[data-testid = "bot"] {
+    max-width: 85%;
+    border-bottom-left-radius: 0 !important;
+}
+[data-testid = "user"] {
+    max-width: 85%;
+    width: auto !important;
+    border-bottom-right-radius: 0 !important;
+}
+/* 表格 */
+table {
+    margin: 1em 0;
+    border-collapse: collapse;
+    empty-cells: show;
+}
+td,th {
+    border: 1.2px solid var(--border-color-primary) !important;
+    padding: 0.2em;
+}
+thead {
+    background-color: rgba(175,184,193,0.2);
+}
+thead th {
+    padding: .5em .2em;
+}
+/* 行内代码 */
+code {
+    display: inline;
+    white-space: break-spaces;
+    border-radius: 6px;
+    margin: 0 2px 0 2px;
+    padding: .2em .4em .1em .4em;
+    background-color: rgba(175,184,193,0.2);
+}
+/* 代码块 */
+pre code {
+    display: block;
+    overflow: auto;
+    white-space: pre;
+    background-color: hsla(0, 0%, 0%, 80%)!important;
+    border-radius: 10px;
+    padding: 1.4em 1.2em 0em 1.4em;
+    margin: 1.2em 2em 1.2em 0.5em;
+    color: #FFF;
+    box-shadow: 6px 6px 16px hsla(0, 0%, 0%, 0.2);
+}
+/* 代码高亮样式 */
+.highlight .hll { background-color: #49483e }
+.highlight .c { color: #75715e } /* Comment */
+.highlight .err { color: #960050; background-color: #1e0010 } /* Error */
+.highlight .k { color: #66d9ef } /* Keyword */
+.highlight .l { color: #ae81ff } /* Literal */
+.highlight .n { color: #f8f8f2 } /* Name */
+.highlight .o { color: #f92672 } /* Operator */
+.highlight .p { color: #f8f8f2 } /* Punctuation */
+.highlight .ch { color: #75715e } /* Comment.Hashbang */
+.highlight .cm { color: #75715e } /* Comment.Multiline */
+.highlight .cp { color: #75715e } /* Comment.Preproc */
+.highlight .cpf { color: #75715e } /* Comment.PreprocFile */
+.highlight .c1 { color: #75715e } /* Comment.Single */
+.highlight .cs { color: #75715e } /* Comment.Special */
+.highlight .gd { color: #f92672 } /* Generic.Deleted */
+.highlight .ge { font-style: italic } /* Generic.Emph */
+.highlight .gi { color: #a6e22e } /* Generic.Inserted */
+.highlight .gs { font-weight: bold } /* Generic.Strong */
+.highlight .gu { color: #75715e } /* Generic.Subheading */
+.highlight .kc { color: #66d9ef } /* Keyword.Constant */
+.highlight .kd { color: #66d9ef } /* Keyword.Declaration */
+.highlight .kn { color: #f92672 } /* Keyword.Namespace */
+.highlight .kp { color: #66d9ef } /* Keyword.Pseudo */
+.highlight .kr { color: #66d9ef } /* Keyword.Reserved */
+.highlight .kt { color: #66d9ef } /* Keyword.Type */
+.highlight .ld { color: #e6db74 } /* Literal.Date */
+.highlight .m { color: #ae81ff } /* Literal.Number */
+.highlight .s { color: #e6db74 } /* Literal.String */
+.highlight .na { color: #a6e22e } /* Name.Attribute */
+.highlight .nb { color: #f8f8f2 } /* Name.Builtin */
+.highlight .nc { color: #a6e22e } /* Name.Class */
+.highlight .no { color: #66d9ef } /* Name.Constant */
+.highlight .nd { color: #a6e22e } /* Name.Decorator */
+.highlight .ni { color: #f8f8f2 } /* Name.Entity */
+.highlight .ne { color: #a6e22e } /* Name.Exception */
+.highlight .nf { color: #a6e22e } /* Name.Function */
+.highlight .nl { color: #f8f8f2 } /* Name.Label */
+.highlight .nn { color: #f8f8f2 } /* Name.Namespace */
+.highlight .nx { color: #a6e22e } /* Name.Other */
+.highlight .py { color: #f8f8f2 } /* Name.Property */
+.highlight .nt { color: #f92672 } /* Name.Tag */
+.highlight .nv { color: #f8f8f2 } /* Name.Variable */
+.highlight .ow { color: #f92672 } /* Operator.Word */
+.highlight .w { color: #f8f8f2 } /* Text.Whitespace */
+.highlight .mb { color: #ae81ff } /* Literal.Number.Bin */
+.highlight .mf { color: #ae81ff } /* Literal.Number.Float */
+.highlight .mh { color: #ae81ff } /* Literal.Number.Hex */
+.highlight .mi { color: #ae81ff } /* Literal.Number.Integer */
+.highlight .mo { color: #ae81ff } /* Literal.Number.Oct */
+.highlight .sa { color: #e6db74 } /* Literal.String.Affix */
+.highlight .sb { color: #e6db74 } /* Literal.String.Backtick */
+.highlight .sc { color: #e6db74 } /* Literal.String.Char */
+.highlight .dl { color: #e6db74 } /* Literal.String.Delimiter */
+.highlight .sd { color: #e6db74 } /* Literal.String.Doc */
+.highlight .s2 { color: #e6db74 } /* Literal.String.Double */
+.highlight .se { color: #ae81ff } /* Literal.String.Escape */
+.highlight .sh { color: #e6db74 } /* Literal.String.Heredoc */
+.highlight .si { color: #e6db74 } /* Literal.String.Interpol */
+.highlight .sx { color: #e6db74 } /* Literal.String.Other */
+.highlight .sr { color: #e6db74 } /* Literal.String.Regex */
+.highlight .s1 { color: #e6db74 } /* Literal.String.Single */
+.highlight .ss { color: #e6db74 } /* Literal.String.Symbol */
+.highlight .bp { color: #f8f8f2 } /* Name.Builtin.Pseudo */
+.highlight .fm { color: #a6e22e } /* Name.Function.Magic */
+.highlight .vc { color: #f8f8f2 } /* Name.Variable.Class */
+.highlight .vg { color: #f8f8f2 } /* Name.Variable.Global */
+.highlight .vi { color: #f8f8f2 } /* Name.Variable.Instance */
+.highlight .vm { color: #f8f8f2 } /* Name.Variable.Magic */
+.highlight .il { color: #ae81ff } /* Literal.Number.Integer.Long */

requirements.txt

@@ -0,0 +1,5 @@
+gradio
+markdown
+PyMuPDF
+openai
+tensorflow_hub