Update functions.py

functions.py

@@ -211,6 +211,54 @@ def embed_text(query,title,embedding_model,_docsearch):
     answer = chain({"query": query})
 
     return answer
+
+@st.cache_data
+def gen_sentiment(text):
+    '''Generate sentiment of given text'''
+    return sent_pipe(text)[0]['label']
+
+@st.cache_data 
+def gen_annotated_text(df):
+    '''Generate annotated text'''
+    
+    tag_list=[]
+    for row in df.itertuples():
+        label = row[2]
+        text = row[1]
+        if label == 'Positive':
+            tag_list.append((text,label,'#8fce00'))
+        elif label == 'Negative':
+            tag_list.append((text,label,'#f44336'))
+        else:
+            tag_list.append((text,label,'#000000'))
+        
+    return tag_list
+
+@st.cache_data
+def generate_eval(raw_text, N, chunk):
+
+    # Generate N questions from context of chunk chars
+    # IN: text, N questions, chunk size to draw question from in the doc
+    # OUT: eval set as JSON list
+
+    # raw_text = ','.join(raw_text)
+    
+    st.info("`Generating sample questions ...`")
+    n = len(raw_text)
+    starting_indices = [random.randint(0, n-chunk) for _ in range(N)]
+    sub_sequences = [raw_text[i:i+chunk] for i in starting_indices]
+    chain = QAGenerationChain.from_llm(ChatOpenAI(temperature=0))
+    eval_set = []
+    for i, b in enumerate(sub_sequences):
+        try:
+            qa = chain.run(b)
+            eval_set.append(qa)
+            st.write("Creating Question:",i+1)
+        except Exception as e:
+            st.warning('Error generating question %s.' % str(i+1), icon="⚠️")
+            st.write(e)
+    eval_set_full = list(itertools.chain.from_iterable(eval_set))
+    return eval_set_full
     
 @st.cache_resource
 def get_spacy():