tweak to prompt

appStore/rag.py

@@ -14,9 +14,9 @@ model_select = "gpt-3.5-turbo-1106"
 
 
 # define a special function for putting the prompt together (as we can't use haystack)
-def get_prompt(context):
+def get_prompt(context, label):
   base_prompt="Summarize the following context efficiently in bullet points, the less the better. \
-  Summarize only activities that address the vulnerability of the given context to climate change. \
+  Summarize only activities that address the vulnerability of "+label+" to climate change. \
   Formatting example: \
     - Collect and utilize gender-disaggregated data to inform and improve climate change adaptation efforts. \
     - Prioritize gender sensitivity in adaptation options, ensuring participation and benefits for women, who are more vulnerable to climate impacts. \
@@ -53,9 +53,7 @@ def completion_with_backoff(**kwargs):
 
 
 # construct RAG query, send to openai and process response
-def run_query(df):
-    docs = df
-
+def run_query(context, label):
     '''
     For non-streamed completion, enable the following 2 lines and comment out the code below
     '''
@@ -63,7 +61,7 @@ def run_query(df):
     # result = res.choices[0].message.content
 
     # instantiate ChatCompletion as a generator object (stream is set to True)
-    response = completion_with_backoff(model=model_select, messages=[{"role": "user", "content": get_prompt(docs)}], stream=True)
+    response = completion_with_backoff(model=model_select, messages=[{"role": "user", "content": get_prompt(context, label)}], stream=True)
     # iterate through the streamed output
     report = []
     res_box = st.empty()

appStore/target.py

@@ -102,7 +102,7 @@ def target_display():
     # construct RAG query for each label, send to openai and process response
     for i in range(0,len(df_agg)):
         st.write(df_agg['Vulnerability Label'].iloc[i])
-        run_query(df_agg['text'].iloc[i])
+        run_query(context = df_agg['text'].iloc[i], label = df_agg['Vulnerability Label'].iloc[i])
         # st.write(df_agg['text'].iloc[i])