add examples with process function

README.md

@@ -34,6 +34,55 @@ We recommend to use the model with transformers `ner` pipeline:
 from transformers import AutoTokenizer, AutoModelForTokenClassification
 from transformers import pipeline
 
+def process(text, prompt, treshold=0.5):
+  """
+  Processes text by preparing prompt and adjusting indices.
+  
+  Args:
+    text (str): The text to process
+    prompt (str): The prompt to prepend to the text
+    
+  Returns:
+    list: A list of dicts with adjusted spans and scores
+  """
+
+  # Concatenate text and prompt for full input
+  input_ = f"{prompt}\n{text}" 
+  
+  results = nlp(input_) # Run NLP on full input
+  
+  processed_results = []
+
+  prompt_length = len(prompt) # Get prompt length
+  
+  for result in results:
+    # check whether score is higher than treshold
+    if result['score']<treshold:
+        continue
+    # Adjust indices by subtracting prompt length
+    start = result['start'] - prompt_length 
+
+    # If indexes belongs to the prompt - continue
+    if start<0:
+        continue
+
+    end = result['end'] - prompt_length
+    
+    # Extract span from original text using adjusted indices
+    span = text[start:end]
+
+    # Create processed result dict
+    processed_result = {
+      'span': span,
+      'start': start,  
+      'end': end,
+      'score': result['score']
+    }
+
+    processed_results.append(processed_result)
+
+  return processed_results
+
 tokenizer = AutoTokenizer.from_pretrained("knowledgator/UTC-DeBERTa-small")
 model = AutoModelForTokenClassification.from_pretrained("knowledgator/UTC-DeBERTa-small")
 
@@ -52,9 +101,7 @@ text = """Apple was founded as Apple Computer Company on April 1, 1976, by Steve
 It was incorporated by Jobs and Wozniak as Apple Computer, Inc. in 1977. The company's second computer, the Apple II, became a best seller and one of the first mass-produced microcomputers.
 Apple went public in 1980 to instant financial success."""
 
-input_ = f"{prompt} {text}"
-
-results = nlp(input_)
+results = process(text, prompt)
 
 print(results)
 ```
@@ -69,7 +116,7 @@ During his career at Microsoft, Gates held the positions of chairman, chief exec
 
 input_ = f"{question} {text}"
 
-results = nlp(input_)
+results = process(text, question)
 
 print(results)
 ```
@@ -83,9 +130,7 @@ text = """The mechanism of action was characterized using native mass spectromet
 Similarly, compound 23R showed dose-dependent stabilization of the SARS-CoV-2 Mpro in the thermal shift binding assay with an apparent Kd value of 9.43 μM, a 9.3-fold decrease compared to ML188 (1) (Figure B). In the enzymatic kinetic studies, 23R was shown to be a noncovalent inhibitor with a Ki value of 0.07 μM (Figure C, D top and middle panels). In comparison, the Ki for the parent compound ML188 (1) is 2.29 μM.
 The Lineweaver–Burk or double-reciprocal plot with different compound concentrations yielded an intercept at the Y-axis, suggesting that 23R is a competitive inhibitor similar to ML188 (1) (Figure C, D bottom panel). Buy our T-shirts for the lowerst prices you can find!!!  Overall, the enzymatic kinetic studies confirmed that compound 23R is a noncovalent inhibitor of SARS-CoV-2 Mpro."""
 
-input_ = f"{prompt}\n{text}"
-
-results = nlp(input_)
+results = process(text, prompt)
 
 print(results)
 ```
@@ -107,9 +152,7 @@ relation = "worked at"
 
 prompt = rex_prompt.format(relation, entity)
 
-input_ = f"{prompt}\n{text}"
-
-results = nlp(input_)
+results = process(text, prompt)
 
 print(results)
 ```
@@ -125,9 +168,7 @@ entity = "anethole"
 
 prompt = ent_prompt.format(entity)
 
-input_ = f"{prompt}\n{text}"
-
-results = nlp(input_)
+results = process(text, prompt)
 
 print(results)
 ```
@@ -141,9 +182,7 @@ text = """Apple was founded as Apple Computer Company on April 1, 1976, by Steve
 Apple Inc. is an American multinational technology company headquartered in Cupertino, California. Apple is the world's largest technology company by revenue, with US$394.3 billion in 2022 revenue. As of March 2023, Apple is the world's biggest company by market capitalization. As of June 2022, Apple is the fourth-largest personal computer vendor by unit sales and the second-largest mobile phone manufacturer in the world. It is considered one of the Big Five American information technology companies, alongside Alphabet (parent company of Google), Amazon, Meta Platforms, and Microsoft. 
 As the market for personal computers expanded and evolved throughout the 1990s, Apple lost considerable market share to the lower-priced duopoly of the Microsoft Windows operating system on Intel-powered PC clones (also known as "Wintel"). In 1997, weeks away from bankruptcy, the company bought NeXT to resolve Apple's unsuccessful operating system strategy and entice Jobs back to the company. Over the next decade, Jobs guided Apple back to profitability through a number of tactics including introducing the iMac, iPod, iPhone and iPad to critical acclaim, launching the "Think different" campaign and other memorable advertising campaigns, opening the Apple Store retail chain, and acquiring numerous companies to broaden the company's product portfolio. When Jobs resigned in 2011 for health reasons, and died two months later, he was succeeded as CEO by Tim Cook"""
 
-input_ = f"{prompt}\n{text}"
-
-results = nlp(input_)
+results = process(text, prompt)
 
 print(results)
 ```