Duplicate from psyne/MLSLAzurePDFGPTMulti

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,14 @@
+---
+title: MLSLAzurePDFGPT
+emoji: 🏆
+colorFrom: yellow
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.32.0
+app_file: app.py
+pinned: false
+license: unlicense
+duplicated_from: psyne/MLSLAzurePDFGPTMulti
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,188 @@
+import urllib.request
+import fitz
+import re
+import numpy as np
+import tensorflow_hub as hub
+import openai
+import gradio as gr
+import os
+from sklearn.neighbors import NearestNeighbors
+
+
+def download_pdf(url, output_path):
+    urllib.request.urlretrieve(url, output_path)
+
+
+def preprocess(text):
+    text = text.replace('\n', ' ')
+    text = re.sub('\s+', ' ', text)
+    return text
+
+
+def pdf_to_text(path, start_page=1, end_page=None):
+    doc = fitz.open(path)
+    total_pages = doc.page_count
+
+    if end_page is None:
+        end_page = total_pages
+
+    text_list = []
+
+    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
+
+
+class SemanticSearch:
+
+    def __init__(self):
+        self.use = hub.load('https://tfhub.dev/google/universal-sentence-encoder/4')
+        self.fitted = False
+
+    def fit(self, data, batch=1000, n_neighbors=5):
+        self.data = data
+        self.embeddings = self.get_text_embedding(data, batch=batch)
+        n_neighbors = min(n_neighbors, len(self.embeddings))
+        self.nn = NearestNeighbors(n_neighbors=n_neighbors)
+        self.nn.fit(self.embeddings)
+        self.fitted = True
+
+    def __call__(self, text, return_data=True):
+        inp_emb = self.use([text])
+        neighbors = self.nn.kneighbors(inp_emb, return_distance=False)[0]
+
+        if return_data:
+            return [self.data[i] for i in neighbors]
+        else:
+            return neighbors
+
+    def get_text_embedding(self, texts, batch=1000):
+        embeddings = []
+        for i in range(0, len(texts), batch):
+            text_batch = texts[i:(i+batch)]
+            emb_batch = self.use(text_batch)
+            embeddings.append(emb_batch)
+        embeddings = np.vstack(embeddings)
+        return embeddings
+
+
+recommender = SemanticSearch()
+pdf_paths = []  # List to store multiple PDF paths
+
+
+def load_recommender(paths, start_page=1):
+    global recommender, pdf_paths
+    pdf_paths = paths
+    texts = []
+    for path in paths:
+        texts.extend(pdf_to_text(path, start_page=start_page))
+    chunks = text_to_chunks(texts, start_page=start_page)
+    recommender.fit(chunks)
+    return 'Corpus Loaded.'
+
+
+def generate_text(prompt, engine="mlsgpt3"):
+    completions = openai.Completion.create(
+        engine=engine,
+        prompt=prompt,
+        max_tokens=512,
+        n=1,
+        stop=None,
+        temperature=0.7,
+    )
+    message = completions.choices[0].text
+    return message
+
+
+def generate_answer(question):
+    topn_chunks = recommender(question)
+    prompt = ""
+    prompt += 'search results:\n\n'
+    for c in topn_chunks:
+        prompt += c + '\n\n'
+
+    prompt += "Instructions: Compose a comprehensive reply to the query using the search results given. " \
+              "Cite each reference using [number] notation (every result has this number at the beginning). " \
+              "Citation should be done at the end of each sentence. 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. " \
+              "If the text does not relate to the query, simply state 'Found Nothing'. Ignore outlier " \
+              "search results which have nothing to do with the question. Only answer what is asked. The " \
+              "answer should be short and concise.\n\nQuery: {question}\nAnswer: "
+
+    prompt += f"Query: {question}\nAnswer:"
+    answer = generate_text(prompt)
+    return answer
+
+
+def question_answer(files, question, secret):
+    api_key = os.environ.get('AzureKey')
+    url_base = os.environ.get('AzureUrlBase')
+
+    if api_key is None or url_base is None:
+        return '[ERROR]: Please provide the Azure API Key and URL Base as environment variables.'
+
+    openai.api_key = api_key
+    openai.api_type = "azure"
+    openai.api_base = url_base
+    openai.api_version = "2022-12-01"
+
+    if files == []:
+        return '[ERROR]: Please provide at least one PDF.'
+
+    if secret != os.environ.get('Secret'):
+        return '[Error]: Please provide the correct secret'
+
+    else:
+        loaded_files = []
+        for file in files:
+            old_file_name = file.name
+            file_name = file.name
+            file_name = file_name[:-12] + file_name[-4:]
+            os.rename(old_file_name, file_name)
+            loaded_files.append(file_name)
+        load_recommender(loaded_files)
+
+    if question.strip() == '':
+        return '[ERROR]: Question field is empty.'
+
+    return generate_answer(question)
+
+
+title = 'AzurePDFGPT'
+description = "A test platform for indexing PDFs to in order to 'chat' with them. It is hardcoded to the Jaytest and MLSLGPT engine"
+
+with gr.Interface(
+    fn=question_answer,
+    inputs=[
+        gr.File(label='PDFs', file_types=['.pdf'], file_count="multiple"),
+        gr.Textbox(label='Question'),
+        gr.Textbox(label='Secret')
+    ],
+    outputs=gr.Textbox(label='Answer'),
+    title=title,
+    description=description
+) as iface:
+    iface.launch()

requirements.txt

@@ -0,0 +1,5 @@
+PyMuPDF
+openai
+tensorflow==2.9.2
+tensorflow-hub==0.12.0
+scikit-learn==1.0.2