and so it begins

app.py

@@ -0,0 +1,126 @@
+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
+
+
+import ibis
+from ibis import _
+geoparquet = "https://data.source.coop/fiboa/be-vlg/be_vlg.parquet"
+con = ibis.duckdb.connect("duck.db", extensions = ["spatial"])
+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_icon="🦜",
+)
+st.title("🚧 Early prototype 🚧")
+
+# +
+# from langchain.chains.sql_database.prompt import PROMPT # peek at the default
+from langchain_core.prompts.prompt import PromptTemplate
+
+new_prompt = PromptTemplate(input_variables=['dialect', 'input', 'table_info', 'top_k'], 
+                        template=
+'''
+Given an input question, first create a syntactically correct {dialect} query to run, then look at the results of the query
+and return the answer. Never use limit for {top_k}. You can order the results by a relevant column to return the most interesting
+examples in the database. This duckdb database includes full support for spatial queries, so it will understand most PostGIS-type
+queries as well.
+
+If you are asked to "map" or "show on a map", be sure to alway select the "geometry" column in your query.
+In the response, return only the SQLQuery to run.
+
+Pay attention to use only the column names that you can see in the schema description. Be careful to
+not query for columns that do not exist. Also, pay attention to which column is in which table.
+
+Use the following format:
+Question: Question here
+SQLQuery: SQL Query to run
+SQLResult: Result of the SQLQuery
+Answer: Final answer here
+
+Only use the following tables:
+{table_info}
+
+Question: {input}
+'''
+)
+# -
+
+llm = ChatOpenAI(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)
+# 
+
+
+
+
+# +
+import lonboard
+
+def map_layer(gdf):
+    layer = lonboard.PolygonLayer.from_geopandas(
+        gdf,
+        get_line_width=20,  # width in default units (meters)
+        line_width_min_pixels=0.2,  # minimum width when zoomed out
+        get_fill_color=[204, 251, 254],  # light blue
+        get_line_color=[37, 36, 34],  # dark border color
+    )
+    m = lonboard.Map(layer)
+    return m
+
+
+# -
+
+import geopandas as gpd
+from ibis import _
+def as_geopandas(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())
+        gdf.set_crs(epsg=4326, inplace=True) 
+        return map_layer(gdf)
+    return gdf
+
+
+# +
+#response = "SELECT * FROM crops LIMIT 100"
+#fields = as_geopandas(response)
+#fields
+# -
+
+example = "Which are the 10 largest fields?"
+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)
+            result = as_geopandas(response)
+            result
+
+st.divider()

requirements.txt

@@ -0,0 +1,9 @@
+streamlit
+langchain
+langchain_community
+langchain_openai
+duckdb_engine
+duckdb
+altair
+ibis-framework[duckdb]
+lonboard