feat: added streamlit platform prototype

platform/agentbase.db

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55ff49e995742f88b3efa6d0736a58bcf47b987dbfa91a228f5ad1c64a8a03db
+size 6701056

platform/database.py

@@ -0,0 +1,124 @@
+"""
+AgentBase SQLite3 Database Connector.
+
+This module implements general-purpose functions to access, manipulate and query the AgentBase
+database platform.
+1. Schema Initialisation
+2. Database Connection and Query Execution
+3. Data Insertion (e.g., from temporary CSV files, TODO: updates through web scraping)
+
+Author: Arastun Mammadli
+Date: [Current Date]
+"""
+
+import json
+import pandas as pd
+import numpy as np
+import sqlite3
+from sentence_transformers import SentenceTransformer
+
+
+class SQLiteConnector:
+    """
+    A class to handle SQLite database connections and operations.
+    """
+
+    def __init__(self, database_file):
+        self.conn = sqlite3.connect(database_file)
+        self.cursor = self.conn.cursor()
+        self.init_schema()
+
+    def init_schema(self):
+        """
+        Initialise the datbase schema (run once).
+        (1) Platform Entity, (2) Agent Entity, (3) Embeddings Table (optional)
+        """
+        self.conn.execute("""
+        CREATE TABLE IF NOT EXISTS platforms (
+            platform_id TEXT PRIMARY KEY,
+            platform_name TEXT,
+            platform_url TEXT
+        )
+        """)
+        self.conn.execute("""
+        CREATE TABLE IF NOT EXISTS agents (
+            agent_id TEXT PRIMARY KEY,
+            platform_id INTEGER,
+            agent_name TEXT,
+            platform_name TEXT,
+            agent_description TEXT,
+            agent_category TEXT,
+            agent_usage TEXT,  -- JSON string
+            usage_example TEXT,  -- JSON string
+            agent_url TEXT,
+            agent_accessibility TEXT,
+            update_time TEXT,
+            misc TEXT,
+            FOREIGN KEY (platform_id) REFERENCES platforms(platform_id)
+        )
+        """)
+        self.conn.execute("""
+        CREATE TABLE IF NOT EXISTS embeddings (
+            agent_id TEXT,
+            embedding_model TEXT,  -- e.g., 'all-MiniLM-L6-v2'
+            field TEXT,  -- 'description', 'combined', etc.
+            embedding BLOB,  -- numpy array as bytes
+            PRIMARY KEY (agent_id, embedding_model, field),
+            FOREIGN KEY (agent_id) REFERENCES agents(agent_id)
+        )
+        """)
+        self.conn.commit()
+
+    def insert_platform(self, platform_csv):
+        """
+        Insert a mock platform from a CSV file
+        """
+
+        df = pd.read_csv(platform_csv)
+        df.to_sql('platforms', self.conn, if_exists='replace', index=False)
+        self.conn.commit()
+    
+    def insert_agent(self, agent_csv):
+        """
+        Insert mock agents from a CSV file
+        """
+
+        df = pd.read_csv(agent_csv)
+        df.to_sql('agents', self.conn, if_exists='replace', index=False)
+        self.conn.commit()
+
+    def execute_query(self, query, params=None):
+        if params:
+            self.cursor.execute(query, params)
+        else:
+            self.cursor.execute(query)
+        self.conn.commit()
+        return self.cursor.fetchall()
+    
+    def load_all_as_df(self):
+        """
+        Loads all platforms and agents from database as a pandas dataframe.
+        """
+
+        platforms_df = pd.read_sql_query("SELECT * FROM platforms", self.conn)
+        agents_df = pd.read_sql_query("SELECT * FROM agents", self.conn)
+        return platforms_df, agents_df
+
+    def close(self):
+        self.conn.close()
+
+
+if __name__ == "__main__":
+    db_file = "agentbase.db"
+    platforms_csv = f"../data_collection/extracted_data/platforms.csv"
+    agents_csv = f"../data_collection/extracted_data/cleaned/agentbase_cleaned.csv"
+
+    # connect & insert
+    db_connector = SQLiteConnector(db_file)
+    db_connector.insert_platform(platforms_csv)
+    db_connector.insert_agent(agents_csv)
+
+    # test
+    # platforms, agents = db_connector.load_all_as_df()
+    # print(platforms)
+    db_connector.close()

platform/interface.py

@@ -0,0 +1,116 @@
+"""
+AgentBase Visualisation Demo.
+
+Author: Arastun Mammadli
+Date: [Current Date]
+"""
+
+import streamlit as st
+import pandas as pd
+import numpy as np
+
+from database import SQLiteConnector
+
+
+def retrieve_data(df, search_term, search_columns, method='baseline'):
+    """
+    Retrieve data from the loaded DataFrame based on the specified method.
+    """
+
+    if method == 'baseline': return keyword_filter(df, search_term, search_columns)
+
+def keyword_filter(df, keyword, columns):
+    """
+    Simple keyword-based boolean filter across specified columns.
+    """
+
+    if not keyword: return df
+
+    mask = df[columns].astype(str).apply(
+        lambda col: col.str.contains(keyword, case=False, na=False)
+    ).any(axis=1)
+    return df[mask]
+
+
+class AgentBaseUI:
+    """
+    AgentBase Streamlit-based UI Components.
+    """
+
+    def __init__(self, db_path):
+        # loading the data
+        self.db_connector = SQLiteConnector(db_path)
+        self.platforms_df, self.agents_df = self.db_connector.load_all_as_df()
+
+    def show_header(self):
+        st.set_page_config(page_title="AgentBase", layout="wide")
+        st.title("AgentBase Platform Demo")
+        st.write("A Large-Scale Agent Collection for Automated Agent Recommendation.")
+        st.subheader("🔍 Retrieval")
+        self.search_term = st.text_input("Test our retrieval models", placeholder="Type to search...")
+
+    def show_platforms(self):
+        st.header("Platforms")
+        platforms_filtered = retrieve_data(
+            self.platforms_df, 
+            self.search_term, 
+            ['platform_id', 'platform_name', 'platform_url']
+        )
+        
+        if len(platforms_filtered) > 0:
+            st.write(f"Showing {len(platforms_filtered)} of {len(self.platforms_df)} platforms")
+            # cropped display
+            platform_config = {
+                "platform_url": st.column_config.LinkColumn("platform_url", display_text="Visit →"),
+            }
+            st.dataframe(
+                platforms_filtered,
+                column_config=platform_config,
+                use_container_width=True,
+                hide_index=True
+            )
+        else:
+            st.info("No platforms match your search.")
+
+    def show_agents(self):
+        st.header("Agents")
+        agents_filtered = retrieve_data(
+            self.agents_df,
+            self.search_term,
+            ['agent_id', 'agent_name', 'agent_description', 'agent_category']
+        )
+        
+        if len(agents_filtered) > 0:
+            st.write(f"Showing {len(agents_filtered)} of {len(self.agents_df)} agents")
+            # cropped display
+            agent_config = {
+                "agent_url": st.column_config.LinkColumn("agent_url", display_text="Visit →"),
+                "agent_description": st.column_config.TextColumn("agent_description", width="large"),
+                "agent_accessibility": st.column_config.TextColumn("agent_accessibility", width="small"),
+            }
+            
+            # option to show details
+            if st.toggle("Show detailed view"):
+                st.dataframe(
+                    agents_filtered,
+                    column_config=agent_config,
+                    use_container_width=True,
+                    hide_index=True
+                )
+            else:
+                key_columns = ['agent_name', 'platform_id', 'agent_category', 'agent_accessibility', 'agent_url']
+                st.dataframe(
+                    agents_filtered[key_columns],
+                    column_config=agent_config,
+                    use_container_width=True,
+                    hide_index=True
+                )
+        else:
+            st.info("No agents match your search.")
+
+
+if __name__ == "__main__":
+    agentbaseui = AgentBaseUI(db_path="agentbase.db")
+    agentbaseui.show_header()
+    agentbaseui.show_agents()
+    agentbaseui.show_platforms()