Fix datatype related issues

.gitignore

@@ -2,4 +2,6 @@
 .ipynb_checkpoints
 .venv
 .streamlit
-
+*.pyc
+duck.db.wal
+__pycache__/

README.md

@@ -5,9 +5,11 @@ colorFrom: blue
 colorTo: green
 sdk: streamlit
 sdk_version: 1.37.1
-app_file: app.py
+app_file: fiboa/app.py
 pinned: false
 license: bsd
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+Run it: `streamlit run fiboa/app.py`

app.py → fiboa/app.py

@@ -1,36 +1,23 @@
+import ibis
 import streamlit as st
-from langchain_openai import ChatOpenAI 
-from langchain_community.llms import Ollama
-from langchain_community.utilities import SQLDatabase
+
 from langchain.chains import create_sql_query_chain
-import geopandas as gpd
+from langchain_community.utilities import SQLDatabase
+from langchain_core.prompts.prompt import PromptTemplate
+from langchain_openai import ChatOpenAI
 
+from query import execute_prompt
 
-import ibis
-from ibis import _
 geoparquet = "https://data.source.coop/fiboa/be-vlg/be_vlg.parquet"
 con = ibis.duckdb.connect("duck.db", extensions = ["spatial"])
 #con.raw_sql(f'CREATE OR REPLACE VIEW crops AS SELECT *, ST_GEOMFROMWKB(geometry) AS "geometry" FROM read_parquet("{geoparquet}")')
 crops = con.read_parquet(geoparquet, "crops").cast({"geometry": "geometry"})
-# df = crops.to_pandas()
-
-# +
-# df = crops.to_pandas()
-
-# +
-#gdf = gpd.read_parquet("be_vlg.parquet")
-#gdf.crs
-# -
 
 st.set_page_config(
-    page_title="fiboa chat tool",
+    page_title="fiboaGPT",
     page_icon="🦜",
 )
-st.title("FiobaGPT Prototype")
-
-# +
-# from langchain.chains.sql_database.prompt import PROMPT # peek at the default
-from langchain_core.prompts.prompt import PromptTemplate
+st.title("fiboaGPT")
 
 new_prompt = PromptTemplate(input_variables=['dialect', 'input', 'table_info', 'top_k'], 
                         template=
@@ -58,59 +45,13 @@ Only use that table, do not use the "testing" table. Pay close attention to this
 Question: {input}
 '''
 )
-# -
 
 llm = ChatOpenAI(model="gpt-4o-mini", temperature=0, api_key=st.secrets["OPENAI_API_KEY"])
 
-# +
 # Create the SQL query chain with the custom prompt
 db = SQLDatabase.from_uri("duckdb:///duck.db", view_support=True)
-chain = create_sql_query_chain(llm, db, prompt=new_prompt, k= 11)
-
-## testing
-#user_input = "Show on a map the 10 largest fields?"
-#sql_query = chain.invoke({"question": user_input})
-#print(sql_query)
-# 
-
+chain = create_sql_query_chain(llm, db, prompt=new_prompt, k=11)
 
-# -
-
-
-
-
-# +
-import geopandas as gpd
-from ibis import _
-import re
-import leafmap.maplibregl as leafmap
-m = leafmap.Map()
-
-def as_geopandas(response):
-    response = re.sub(";$", "", response)
-    sql_query = f"CREATE OR REPLACE VIEW testing AS ({response})"
-    con.raw_sql(sql_query)
-    gdf = con.table("testing")
-    if 'geometry' in gdf.columns:
-        gdf = (gdf
-               .cast({"geometry": "geometry"})
-               .mutate(geometry = _.geometry.convert("EPSG:31370", "EPSG:4326"))
-               .to_pandas()
-              ).set_crs(epsg=4326, inplace=True) 
-        return gdf
-    return gdf.to_pandas()
-
-
-# -
-
-response = "SELECT geometry, area FROM crops ORDER BY area DESC LIMIT 10;"
-as_geopandas(response)
-#if 'geometry' in gdf.columns:
-#    m.add_gdf(gdf)
-#    m
-#gdf
-
-# +
 '''
 Ask me about fiboa data! Request "a map" to get map output, or table for tabular output, e.g.
 
@@ -125,20 +66,11 @@ with st.container():
     if prompt := st.chat_input(example, key="chain"):
         st.chat_message("user").write(prompt)
         with st.chat_message("assistant"):
-            response = chain.invoke({"question": prompt})
-            st.write(response)
-            gdf = as_geopandas(response)
-            if 'geometry' in gdf.columns:
-                m.add_gdf(gdf)
-                m.to_streamlit()
-            else:
-                st.dataframe(gdf)
-
-# +
+            execute_prompt(con, chain, prompt)
+
 st.divider()
 
 '''
 Data sources: https://beta.source.coop/fiboa/be-vlg
 Software License: BSD
-
 '''

fiboa/query.py

@@ -0,0 +1,46 @@
+import re
+
+import leafmap.maplibregl as leafmap
+import pandas as pd
+import streamlit as st
+from ibis import _
+
+
+def execute_prompt(con, chain, prompt):
+    response = chain.invoke({"question": prompt})
+    st.write(response)
+    gdf = as_geopandas(con, response)
+
+    if 'geometry' in gdf.columns:
+        m = leafmap.Map()
+        m.add_gdf(gdf)
+        m.to_streamlit()
+    else:
+        gdf.drop(columns=['geometry', 'bbox', 'bbox.minx', 'bbox.maxx', 'bbox.miny', 'bbox.maxy'], errors='ignore', inplace=True)
+        st.dataframe(pd.DataFrame(gdf), column_config={
+            "area": st.column_config.NumberColumn("Area (ha)", format="%.5f"),
+            "perimeter": st.column_config.NumberColumn("Perimeter (m)", format="%.3f"),
+            "determination_datetime": st.column_config.DatetimeColumn("Determination Date"),
+        })
+
+def as_geopandas(con, response):
+    response = re.sub(";$", "", response)
+    sql_query = f"CREATE OR REPLACE VIEW testing AS ({response})"
+    con.raw_sql(sql_query)
+    gdf = con.table("testing")
+
+    if 'geometry' in gdf.columns:
+        gdf = (gdf
+               .cast({"geometry": "geometry"})
+               .mutate(geometry = _.geometry.convert("EPSG:31370", "EPSG:4326"))
+               .to_pandas()
+              ).set_crs(epsg=4326, inplace=True) 
+    else:
+        gdf = gdf.to_pandas()
+
+    for col in gdf.columns:
+        dtype = str(gdf[col].dtype)
+        if dtype.startswith("datetime64"):
+            gdf[col] = gdf[col].astype(str)
+    
+    return gdf

requirements.txt

@@ -1,6 +1,5 @@
-duckdb==1.0.0
+duckdb==1.1.0
 pandas==2.2.2
-#git+https://github.com/eodaGmbH/py-maplibregl@feature/color-utils
 git+https://github.com/eodaGmbH/py-maplibregl
 leafmap[maplibre]
 ibis-framework[duckdb]==9.1.0