Update snomed ct vector database with fullname.

SNOMED-CT_Assistant.py

@@ -25,6 +25,10 @@ st.title("🏥 SNOMED-CT Assistant")
 st.caption("👩‍⚕️ A smart medical assistant with SNOMED-CT knowledge.")
 query_number = st.sidebar.slider("Query Numbers", 5, 20, 5)
 
+# Config Chroma DB Client
+chroma_client = chromadb.PersistentClient(path="snomed_ct_id_term_fullname_634k")
+collection = chroma_client.get_or_create_collection(name="snomed_ct_id_term_fullname")
+
 # System prompt
 system_prompt = """You are a medical expert with rich experience in SNOMED-CT professional knowledge. 
 You are skilled at assisting medical professionals and answering questions in the medical field. 
@@ -119,10 +123,6 @@ def generate_entity_identification_prompt(medical_text):
 def generate_entity_mapping_prompt(entity, query_result_dict):
     return f"""Help me to do "SNOMED-CT Entity Mapping" process with entity: {entity} and query result \n {query_result_dict} \n , output with table format, including 5 columns: "Identified Entity", "Distance", "IDs", "SNOMED CT Concept IDs", "SNOMED CT Descriptions"  \n """
 
-# Chroma DB Client
-chroma_client = chromadb.PersistentClient(path="snomed_ct_id_term_1410k")
-collection = chroma_client.get_or_create_collection(name="snomed_ct_id_term")
-
 # Func: query chrome_db
 def query_chroma_db(query_text, query_number):
     results = collection.query(
@@ -160,16 +160,6 @@ def chat_input(prompt, med_text):
             st.session_state.messages.append({"role": "assistant", "content": results_table})
             st.chat_message("assistant").write(results_table)
             
-            
-            # entity_mapping_prompt = generate_entity_mapping_prompt(entity, results_dict)
-            # st.session_state.messages.append({"role": "user", "content": entity_mapping_prompt})
-            # entity_mapping_response = client.chat.completions.create(
-            #     model=model_tag, messages=st.session_state.messages, temperature=0.5)
-            # mapping_msg = entity_mapping_response.choices[0].message.content
-            # st.session_state.messages.append({"role": "assistant", "content": mapping_msg})
-            # st.chat_message("assistant").write(mapping_msg)
-        
-            
 # Conver entity mapping result to markdown table
 def entity_mapping_result_to_table(entity, results_dict):
     
@@ -179,7 +169,7 @@ def entity_mapping_result_to_table(entity, results_dict):
     descriptions = results_dict['descriptions']
     
     # header
-    header = "| Identified Entity | Distance | IDs | SNOMED CT - Concept IDs | SNOMED CT - Descriptions |"
+    header = "| Identified Entity | Distance | SNOMED CT - IDs | SNOMED CT - Concept IDs | SNOMED CT - Descriptions |"
     seperator = "| --- | --- | --- | --- | --- |"
     
     # table
@@ -196,7 +186,7 @@ def entity_mapping_result_to_table(entity, results_dict):
 
 if "messages" not in st.session_state:
     st.session_state["messages"] = [{"role": "system", "content": system_prompt},
-                                    {"role": "assistant", "content": "👩‍⚕️ 您好，我是您的專業醫學助理。請問有任何我可以協助你的地方嗎?"}]
+                                    {"role": "assistant", "content": "👩‍⚕️ 您好，我是您的專業醫學助理。請問有任何我可以協助你的地方嗎? \n請在對話欄中輸入任意的英文電子病歷字串來測試，我會為您查詢其中相關字詞所對應的 SNOMED CT 術語。"}]
 
 for msg in st.session_state.messages:
     if msg["role"] == "system":

pages/Vector DB of SNOMED-CT.py

@@ -16,13 +16,13 @@ st.set_page_config(layout="wide")
 st.title("📚 Semantic Search with Vector Database of SNOMED-CT 💡")
 st.caption("🔍 Search any SNOMED-CT relate decription & concept with natural language.")
 st.sidebar.title("🔍 Search Setting")
-query_number = st.sidebar.slider("Query Numbers", 10, 30, 10)
+query_number = st.sidebar.slider("Query Numbers", 10, 50, 10)
 st.markdown("##### ➡️⌨️ Please input some medical description here, e.g. \"insomnia two nights a week.\", \"COPD\", \"Degenerative Joint Disease\"")
 query_text = st.text_input("Input: any medical description snippet","Type-2 Diabetes")
 
 # Chroma DB Client
-chroma_client = chromadb.PersistentClient(path="snomed_ct_id_term_1410k")
-collection = chroma_client.get_or_create_collection(name="snomed_ct_id_term")
+chroma_client = chromadb.PersistentClient(path="snomed_ct_id_term_fullname_634k")
+collection = chroma_client.get_or_create_collection(name="snomed_ct_id_term_fullname")
 start = 1.0
 end = 1.1
 st.markdown("##### ➡️Chroma DB will return " + str(query_number)  
@@ -55,5 +55,5 @@ results_df = get_df_from_chroma_results(results)
 
 #displaying the dataframe as an interactive object
 st.markdown("### 📊 Similar Search Results from Chroma Vector DB")
-st.dataframe(results_df, 1000, 500)
+st.dataframe(results_df, 1000, 800)
 

snomed_ct_id_term_fullname_634k/a2d80cd0-644c-48f7-baf2-fb9cc743736e/data_level0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373e7cdf5cdcfbd76e6f495c5ccd8a0946b68b16cf3a0dcaadfac3bf400e2bbb
+size 1062584000

snomed_ct_id_term_fullname_634k/a2d80cd0-644c-48f7-baf2-fb9cc743736e/header.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:342f57a56758253455d6ffb709e1c568b07231d5cc56273f192ebd03bfb33435
+size 100

snomed_ct_id_term_fullname_634k/a2d80cd0-644c-48f7-baf2-fb9cc743736e/index_metadata.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:863933654d8448809ffe8b4182a477727552693c363363bd5334e0be98383803
+size 23398984

snomed_ct_id_term_fullname_634k/a2d80cd0-644c-48f7-baf2-fb9cc743736e/length.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1316a43da7d1aa1c130242c0d5fef5929cd7c4dd88a52673ad0ed9c20e9008b
+size 2536000

snomed_ct_id_term_fullname_634k/a2d80cd0-644c-48f7-baf2-fb9cc743736e/link_lists.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1ad8d35c3daefb9706ec23d6da013ec64104ab7ac9889fe8471d13d24b97ea8
+size 5403220

snomed_ct_id_term_fullname_634k/chroma.sqlite3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ff1ea2b19c33b300cfd14ea27ce561662fd995bf7eb68e330f591e70b5d102
+size 1641885696