Update app.py

app.py

@@ -54,89 +54,6 @@ def text_to_chunks(texts, word_length=150, start_page=1):
     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
-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'[Page no. {idx+start_page}]' + ' ' + '"' + chunk + '"'
-            chunks.append(chunk)
-    return chunks
-
-
 class SemanticSearch:
 
     def __init__(self):
@@ -178,7 +95,7 @@ def load_recommender(path, start_page=1):
     return 'Corpus Loaded.'
 
 
-def generate_text(openAI_key, prompt, engine="text-davinci-003"):
+def generate_text(openAI_key, prompt, engine="davinci"):
     openai.api_key = openAI_key
     completions = openai.Completion.create(
         engine=engine,
@@ -205,11 +122,11 @@ def generate_answer(question, openAI_key):
               "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 'Text Not Found in PDF'. Ignore outlier "\
-              "search results which has nothing to do with the question. Only answer what is asked. The "\
+              "search results which have nothing to do with the question. Only answer what is asked. The "\
               "answer should be short and concise. Answer step-by-step. \n\nQuery: {question}\nAnswer: "
 
     prompt += f"Query: {question}\nAnswer:"
-    answer = generate_text(openAI_key, prompt, "text-davinci-003")
+    answer = generate_text(openAI_key, prompt, "davinci")
     return answer
 
 
@@ -245,8 +162,7 @@ recommender = SemanticSearch()
 title = 'PDF GPT'
 description = """ PDF GPT allows you to chat with your PDF file using Universal Sentence Encoder and Open AI. It gives hallucination free response than other tools as the embeddings are better than OpenAI. The returned response can even cite the page number in square brackets([]) where the information is located, adding credibility to the responses and helping to locate pertinent information quickly."""
 
-with gr.Interface(fn=question_answer, inputs
-    =[url, file, question, openAI_key], outputs=[answer], title=title, description=description) as iface:
-        iface.launch()
+with gr.Interface(fn=question_answer, inputs=[url, file, question openAI_key], outputs=[answer], title=title, description=description) as iface:
+    iface.launch()