fixing the lynxscribe demo

examples/LynxScribe Image RAG

@@ -1,12 +1,5 @@
 {
   "edges": [
-    {
-      "id": "LynxScribe Image RAG Builder 1 LynxScribe Image RAG Query 1",
-      "source": "LynxScribe Image RAG Builder 1",
-      "sourceHandle": "output",
-      "target": "LynxScribe Image RAG Query 1",
-      "targetHandle": "rag_graph"
-    },
     {
       "id": "Input chat 1 LynxScribe Image RAG Query 1",
       "source": "Input chat 1",
@@ -21,6 +14,13 @@
       "target": "View image 1",
       "targetHandle": "embedding_similarities"
     },
+    {
+      "id": "Cloud-sourced File Loader 1 LynxScribe Image RAG Builder 1",
+      "source": "Cloud-sourced File Loader 1",
+      "sourceHandle": "output",
+      "target": "LynxScribe Image RAG Builder 1",
+      "targetHandle": "file_urls"
+    },
     {
       "id": "LynxScribe Image Describer 1 LynxScribe Image RAG Builder 1",
       "source": "LynxScribe Image Describer 1",
@@ -29,87 +29,22 @@
       "targetHandle": "image_describer"
     },
     {
-      "id": "LynxScribe RAG Vector Store 1 LynxScribe Image RAG Builder 1",
-      "source": "LynxScribe RAG Vector Store 1",
+      "id": "LynxScribe RAG Graph Vector Store 1 LynxScribe Image RAG Builder 1",
+      "source": "LynxScribe RAG Graph Vector Store 1",
       "sourceHandle": "output",
       "target": "LynxScribe Image RAG Builder 1",
       "targetHandle": "rag_graph"
     },
     {
-      "id": "Cloud-sourced Image Loader 1 LynxScribe Image RAG Builder 1",
-      "source": "Cloud-sourced Image Loader 1",
+      "id": "LynxScribe Image RAG Builder 1 LynxScribe Image RAG Query 1",
+      "source": "LynxScribe Image RAG Builder 1",
       "sourceHandle": "output",
-      "target": "LynxScribe Image RAG Builder 1",
-      "targetHandle": "image_urls"
+      "target": "LynxScribe Image RAG Query 1",
+      "targetHandle": "rag_graph"
     }
   ],
   "env": "LynxScribe",
   "nodes": [
-    {
-      "data": {
-        "__execution_delay": 0.0,
-        "collapsed": false,
-        "display": null,
-        "error": null,
-        "meta": {
-          "inputs": {
-            "image_describer": {
-              "name": "image_describer",
-              "position": "bottom",
-              "type": {
-                "type": "<class 'inspect._empty'>"
-              }
-            },
-            "image_urls": {
-              "name": "image_urls",
-              "position": "left",
-              "type": {
-                "type": "<class 'inspect._empty'>"
-              }
-            },
-            "rag_graph": {
-              "name": "rag_graph",
-              "position": "bottom",
-              "type": {
-                "type": "<class 'inspect._empty'>"
-              }
-            }
-          },
-          "name": "LynxScribe Image RAG Builder",
-          "outputs": {
-            "output": {
-              "name": "output",
-              "position": "right",
-              "type": {
-                "type": "None"
-              }
-            }
-          },
-          "params": {
-            "image_rag_out_path": {
-              "default": "image_test_rag_graph.pickle",
-              "name": "image_rag_out_path",
-              "type": {
-                "type": "<class 'str'>"
-              }
-            }
-          },
-          "type": "basic"
-        },
-        "params": {},
-        "status": "done",
-        "title": "LynxScribe Image RAG Builder"
-      },
-      "dragHandle": ".bg-primary",
-      "height": 298.0,
-      "id": "LynxScribe Image RAG Builder 1",
-      "position": {
-        "x": 202.17177613422314,
-        "y": 209.6180585281515
-      },
-      "type": "basic",
-      "width": 479.0
-    },
     {
       "data": {
         "__execution_delay": 0.0,
@@ -140,7 +75,7 @@
           "type": "basic"
         },
         "params": {
-          "chat": "Show me a picture about meditation"
+          "chat": "Show me a picture about pills!"
         },
         "status": "done",
         "title": "Input chat"
@@ -219,7 +154,7 @@
       "data": {
         "__execution_delay": null,
         "collapsed": false,
-        "display": "https://storage.googleapis.com/lynxkite_public_data/lynxscribe-images/image-rag-test/yoga-3053487_1280.jpg",
+        "display": "https://storage.googleapis.com/lynxkite_public_data/lynxscribe-images/image-rag-test/capsules-1079838_1280.jpg",
         "error": null,
         "meta": {
           "inputs": {
@@ -315,8 +250,8 @@
       "height": 363.0,
       "id": "LynxScribe Image Describer 1",
       "position": {
-        "x": 16.941021961247145,
-        "y": 664.8693601063997
+        "x": 127.85361236096924,
+        "y": 687.0518781863441
       },
       "type": "basic",
       "width": 401.0
@@ -327,7 +262,7 @@
         "error": null,
         "meta": {
           "inputs": {},
-          "name": "LynxScribe RAG Vector Store",
+          "name": "LynxScribe RAG Graph Vector Store",
           "outputs": {
             "output": {
               "name": "output",
@@ -375,8 +310,8 @@
             }
           },
           "position": {
-            "x": 831.0,
-            "y": 734.0
+            "x": 790.0,
+            "y": 633.0
           },
           "type": "basic"
         },
@@ -388,25 +323,27 @@
           "text_embedder_model_name_or_path": "text-embedding-3-large"
         },
         "status": "done",
-        "title": "LynxScribe RAG Vector Store"
+        "title": "LynxScribe RAG Graph Vector Store"
       },
       "dragHandle": ".bg-primary",
-      "height": 445.0,
-      "id": "LynxScribe RAG Vector Store 1",
+      "height": 436.0,
+      "id": "LynxScribe RAG Graph Vector Store 1",
       "position": {
-        "x": 485.48864677068343,
-        "y": 669.7387202127995
+        "x": 595.4558693958389,
+        "y": 688.0989202130276
       },
       "type": "basic",
-      "width": 442.0
+      "width": 339.0
     },
     {
       "data": {
+        "__execution_delay": 0.0,
+        "collapsed": null,
         "display": null,
         "error": null,
         "meta": {
           "inputs": {},
-          "name": "Cloud-sourced Image Loader",
+          "name": "Cloud-sourced File Loader",
           "outputs": {
             "output": {
               "name": "output",
@@ -417,6 +354,13 @@
             }
           },
           "params": {
+            "accepted_file_types": {
+              "default": ".jpg, .jpeg, .png",
+              "name": "accepted_file_types",
+              "type": {
+                "type": "<class 'str'>"
+              }
+            },
             "cloud_provider": {
               "default": "gcp",
               "name": "cloud_provider",
@@ -433,27 +377,87 @@
             }
           },
           "position": {
-            "x": 141.0,
-            "y": 421.0
+            "x": 248.0,
+            "y": 419.0
           },
           "type": "basic"
         },
         "params": {
+          "accepted_file_types": ".jpg, .jpeg, .png",
           "cloud_provider": "gcp",
           "folder_URL": "https://storage.googleapis.com/lynxkite_public_data/lynxscribe-images/image-rag-test"
         },
         "status": "done",
-        "title": "Cloud-sourced Image Loader"
+        "title": "Cloud-sourced File Loader"
+      },
+      "dragHandle": ".bg-primary",
+      "height": 291.0,
+      "id": "Cloud-sourced File Loader 1",
+      "position": {
+        "x": -479.7367372966062,
+        "y": 213.81581567584843
+      },
+      "type": "basic",
+      "width": 512.0
+    },
+    {
+      "data": {
+        "display": null,
+        "error": null,
+        "meta": {
+          "inputs": {
+            "file_urls": {
+              "name": "file_urls",
+              "position": "left",
+              "type": {
+                "type": "<class 'inspect._empty'>"
+              }
+            },
+            "image_describer": {
+              "name": "image_describer",
+              "position": "bottom",
+              "type": {
+                "type": "<class 'inspect._empty'>"
+              }
+            },
+            "rag_graph": {
+              "name": "rag_graph",
+              "position": "bottom",
+              "type": {
+                "type": "<class 'inspect._empty'>"
+              }
+            }
+          },
+          "name": "LynxScribe Image RAG Builder",
+          "outputs": {
+            "output": {
+              "name": "output",
+              "position": "right",
+              "type": {
+                "type": "None"
+              }
+            }
+          },
+          "params": {},
+          "position": {
+            "x": 480.0,
+            "y": 388.0
+          },
+          "type": "basic"
+        },
+        "params": {},
+        "status": "done",
+        "title": "LynxScribe Image RAG Builder"
       },
       "dragHandle": ".bg-primary",
-      "height": 267.0,
-      "id": "Cloud-sourced Image Loader 1",
+      "height": 313.0,
+      "id": "LynxScribe Image RAG Builder 1",
       "position": {
-        "x": -451.2626989986675,
-        "y": 225.06333310959974
+        "x": 243.62049392420903,
+        "y": 215.6136303371116
       },
       "type": "basic",
-      "width": 437.0
+      "width": 526.0
     }
   ]
 }

examples/LynxScribe demo

@@ -1,56 +1,126 @@
 {
+  "edges": [
+    {
+      "id": "xy-edge__Truncate history 1output-Chat processor 1processor",
+      "source": "Truncate history 1",
+      "sourceHandle": "output",
+      "target": "Chat processor 1",
+      "targetHandle": "processor"
+    },
+    {
+      "id": "xy-edge__Mask 1output-Chat processor 1processor",
+      "source": "Mask 1",
+      "sourceHandle": "output",
+      "target": "Chat processor 1",
+      "targetHandle": "processor"
+    },
+    {
+      "id": "xy-edge__Mask 2output-Chat processor 1processor",
+      "source": "Mask 2",
+      "sourceHandle": "output",
+      "target": "Chat processor 1",
+      "targetHandle": "processor"
+    },
+    {
+      "id": "xy-edge__Input chat 1output-Test Chat API 2message",
+      "source": "Input chat 1",
+      "sourceHandle": "output",
+      "target": "Test Chat API 2",
+      "targetHandle": "message"
+    },
+    {
+      "id": "xy-edge__Test Chat API 2output-View 1input",
+      "source": "Test Chat API 2",
+      "sourceHandle": "output",
+      "target": "View 1",
+      "targetHandle": "input"
+    },
+    {
+      "id": "LynxScribe RAG Graph Chatbot Backend 1 Test Chat API 2",
+      "source": "LynxScribe RAG Graph Chatbot Backend 1",
+      "sourceHandle": "output",
+      "target": "Test Chat API 2",
+      "targetHandle": "chat_api"
+    },
+    {
+      "id": "Chat processor 1 LynxScribe RAG Graph Chatbot Backend 1",
+      "source": "Chat processor 1",
+      "sourceHandle": "output",
+      "target": "LynxScribe RAG Graph Chatbot Backend 1",
+      "targetHandle": "chat_processor"
+    },
+    {
+      "id": "Cloud-sourced File Loader 1 LynxScribe RAG Graph Chatbot Builder 1",
+      "source": "Cloud-sourced File Loader 1",
+      "sourceHandle": "output",
+      "target": "LynxScribe RAG Graph Chatbot Builder 1",
+      "targetHandle": "file_urls"
+    },
+    {
+      "id": "LynxScribe RAG Graph Chatbot Builder 1 LynxScribe RAG Graph Chatbot Backend 1",
+      "source": "LynxScribe RAG Graph Chatbot Builder 1",
+      "sourceHandle": "output",
+      "target": "LynxScribe RAG Graph Chatbot Backend 1",
+      "targetHandle": "knowledge_base"
+    },
+    {
+      "id": "LynxScribe RAG Graph Vector Store 1 LynxScribe RAG Graph Chatbot Builder 1",
+      "source": "LynxScribe RAG Graph Vector Store 1",
+      "sourceHandle": "output",
+      "target": "LynxScribe RAG Graph Chatbot Builder 1",
+      "targetHandle": "rag_graph"
+    }
+  ],
   "env": "LynxScribe",
   "nodes": [
     {
-      "id": "Input chat 1",
-      "type": "basic",
       "data": {
-        "title": "Input chat",
-        "params": {
-          "chat": "who is the CTO of Lynx?"
-        },
+        "__execution_delay": 0.0,
+        "collapsed": null,
         "display": null,
         "error": null,
-        "collapsed": null,
         "meta": {
           "inputs": {},
-          "params": {
-            "chat": {
-              "default": null,
-              "type": {
-                "type": "<class 'str'>"
-              },
-              "name": "chat"
-            }
-          },
+          "name": "Input chat",
           "outputs": {
             "output": {
               "name": "output",
+              "position": "right",
               "type": {
                 "type": "None"
-              },
-              "position": "right"
+              }
+            }
+          },
+          "params": {
+            "chat": {
+              "default": null,
+              "name": "chat",
+              "type": {
+                "type": "<class 'str'>"
+              }
             }
           },
-          "name": "Input chat",
           "type": "basic"
         },
-        "__execution_delay": 0.0
+        "params": {
+          "chat": "What products does Lynx have?"
+        },
+        "status": "done",
+        "title": "Input chat"
       },
+      "dragHandle": ".bg-primary",
+      "height": 186.0,
+      "id": "Input chat 1",
+      "parentId": null,
       "position": {
-        "x": -493.5496596237119,
-        "y": 20.90123252513356
+        "x": -2606.8829929570456,
+        "y": -648.2654341415332
       },
-      "height": 186.0,
-      "width": 259.0,
-      "parentId": null
+      "type": "basic",
+      "width": 259.0
     },
     {
-      "id": "View 1",
-      "type": "table_view",
       "data": {
-        "title": "View",
-        "params": {},
         "display": {
           "dataframes": {
             "df": {
@@ -59,7 +129,7 @@
               ],
               "data": [
                 [
-                  "TheThe Chief Technology Officer (CTO) of Lynx Analytics is Chema Lizano. He leads the technology strategy and roadmap at the company, overseeing the vision, development, and implementation of solutions across various clients and environments. If you have any more questions regarding our team or services, feel free to ask!\n\nPlease visit https://www.lynxanalytics.com/board for further information."
+                  "Lynx Analytics offers a range of data analytics products and solutions tailored for various industries. Here are some of our key offerings:\n\n- **Generative AI**: We provide innovative solutions such as chatbots specifically designed for the pharmaceutical and service provider sectors.\n  \n- **Graph AI**: Our advanced graph reasoning tools help in areas like transport scenario planning and predicting patient outcomes with graph representation learning.\n\n- **Pharma and Life Sciences**: We focus on marketing support, including Next Best Action predictions and Brand Adoption Ladder analysis, as well as supporting drug discovery and medical analytics.\n\n- **Retail Solutions**: Our products include Price AI, Assort AI, and Promo AI to optimize pricing, assortment, and promotion strategies for retailers.\n\n- **Financial Services**: We offer digital banking analytics solutions and a Customer Happiness Index to enhance customer experience and retention.\n\n- **Telecommunications**: While briefly mentioned, our telecom solutions help optimize operations, including fibre CAPEX optimization and churn prevention management.\n\nThese products are complemented by consulting services to help businesses make data-driven decisions. If you need more specific information or a demo, feel free to get in touch.\n\nCould you share what prompted your visit to our website today? Or may I know which specific domain or industry you are interested in or work in?"
                 ]
               ]
             }
@@ -67,686 +137,488 @@
         },
         "error": null,
         "meta": {
-          "type": "table_view",
-          "name": "View",
           "inputs": {
             "input": {
               "name": "input",
+              "position": "left",
               "type": {
                 "type": "<class 'inspect._empty'>"
-              },
-              "position": "left"
+              }
             }
           },
+          "name": "View",
           "outputs": {},
-          "params": {}
-        }
+          "params": {},
+          "type": "table_view"
+        },
+        "params": {},
+        "status": "done",
+        "title": "View"
       },
+      "dragHandle": ".bg-primary",
+      "height": 950.0,
+      "id": "View 1",
+      "parentId": null,
       "position": {
-        "x": 731.7440706129762,
-        "y": -716.4943976910913
+        "x": -754.9225960536905,
+        "y": -643.161064357758
       },
-      "width": 1256.0,
-      "parentId": null,
-      "height": 950.0
+      "type": "table_view",
+      "width": 1256.0
     },
     {
-      "id": "LLM 1",
-      "type": "basic",
       "data": {
-        "title": "LLM",
-        "params": {
-          "name": "openai"
-        },
         "display": null,
         "error": null,
         "meta": {
           "inputs": {},
+          "name": "Truncate history",
           "outputs": {
             "output": {
+              "name": "output",
+              "position": "top",
               "type": {
                 "type": "None"
-              },
-              "name": "output",
-              "position": "top"
+              }
             }
           },
-          "type": "basic",
           "params": {
-            "name": {
-              "default": "openai",
-              "name": "name",
+            "max_tokens": {
+              "default": 10000.0,
+              "name": "max_tokens",
               "type": {
-                "type": "<class 'str'>"
+                "type": "<class 'int'>"
               }
             }
           },
-          "name": "LLM"
-        }
+          "type": "basic"
+        },
+        "params": {
+          "max_tokens": 10000.0
+        },
+        "status": "done",
+        "title": "Truncate history"
       },
+      "dragHandle": ".bg-primary",
+      "height": 200.0,
+      "id": "Truncate history 1",
+      "parentId": null,
       "position": {
-        "x": -312.5774211084781,
-        "y": 1093.4019527511366
+        "x": -1536.508533731351,
+        "y": 728.1204075546109
       },
-      "parentId": null,
-      "width": 200.0,
-      "height": 200.0
+      "type": "basic",
+      "width": 200.0
     },
     {
-      "id": "Scenario selector 1",
-      "type": "basic",
       "data": {
-        "title": "Scenario selector",
-        "params": {
-          "scenario_file": "uploads/chat_api/scenarios.yaml",
-          "node_types": "intent_cluster"
-        },
+        "__execution_delay": null,
+        "collapsed": false,
         "display": null,
         "error": null,
         "meta": {
-          "params": {
-            "scenario_file": {
-              "type": {
-                "type": "<class 'str'>"
-              },
-              "name": "scenario_file",
-              "default": null
-            },
-            "node_types": {
-              "default": "intent_cluster",
+          "inputs": {
+            "processor": {
+              "name": "processor",
+              "position": "bottom",
               "type": {
-                "type": "<class 'str'>"
-              },
-              "name": "node_types"
+                "type": "<class 'inspect._empty'>"
+              }
             }
           },
-          "inputs": {},
+          "name": "Chat processor",
           "outputs": {
             "output": {
-              "position": "top",
               "name": "output",
+              "position": "top",
               "type": {
                 "type": "None"
               }
             }
           },
-          "type": "basic",
-          "name": "Scenario selector"
-        }
+          "params": {},
+          "type": "basic"
+        },
+        "params": {},
+        "status": "done",
+        "title": "Chat processor"
       },
+      "dragHandle": ".bg-primary",
+      "height": 89.0,
+      "id": "Chat processor 1",
+      "parentId": null,
       "position": {
-        "x": -549.1300345090008,
-        "y": 1086.4852248156676
+        "x": -1527.1027075359414,
+        "y": 605.2129408898476
       },
-      "parentId": null,
-      "height": 200.0,
-      "width": 200.0
+      "type": "basic",
+      "width": 416.0
     },
     {
-      "id": "Chat API 1",
-      "type": "basic",
       "data": {
-        "title": "Chat API",
-        "params": {
-          "model": "gpt-4o-mini"
-        },
         "display": null,
         "error": null,
         "meta": {
-          "name": "Chat API",
-          "type": "basic",
+          "inputs": {},
+          "name": "Mask",
           "outputs": {
             "output": {
-              "type": {
-                "type": "None"
-              },
+              "name": "output",
               "position": "top",
-              "name": "output"
-            }
-          },
-          "inputs": {
-            "chatbot": {
-              "name": "chatbot",
-              "type": {
-                "type": "<class 'inspect._empty'>"
-              },
-              "position": "bottom"
-            },
-            "chat_processor": {
-              "name": "chat_processor",
-              "position": "bottom",
               "type": {
-                "type": "<class 'inspect._empty'>"
+                "type": "None"
               }
-            },
-            "knowledge_base": {
-              "type": {
-                "type": "<class 'inspect._empty'>"
-              },
-              "position": "bottom",
-              "name": "knowledge_base"
             }
           },
           "params": {
-            "model": {
-              "default": "gpt-4o-mini",
+            "exceptions": {
+              "default": "",
+              "name": "exceptions",
               "type": {
                 "type": "<class 'str'>"
-              },
-              "name": "model"
-            }
-          }
-        }
-      },
-      "position": {
-        "x": -22.866663363810787,
-        "y": 258.20943122219336
-      },
-      "parentId": null,
-      "width": 200.0,
-      "height": 200.0
-    },
-    {
-      "id": "Knowledge base 1",
-      "type": "basic",
-      "data": {
-        "title": "Knowledge base",
-        "params": {
-          "template_cluster_path": "uploads/chat_api/data/lynx/tempclusters.pickle",
-          "edges_path": "uploads/chat_api/data/lynx/edges.pickle",
-          "nodes_path": "uploads/chat_api/data/lynx/nodes.pickle"
-        },
-        "display": null,
-        "error": null,
-        "meta": {
-          "name": "Knowledge base",
-          "type": "basic",
-          "params": {
-            "nodes_path": {
-              "name": "nodes_path",
-              "default": "nodes.pickle",
+              }
+            },
+            "mask_pattern": {
+              "default": "",
+              "name": "mask_pattern",
               "type": {
                 "type": "<class 'str'>"
               }
             },
-            "template_cluster_path": {
+            "name": {
+              "default": "",
+              "name": "name",
               "type": {
                 "type": "<class 'str'>"
-              },
-              "name": "template_cluster_path",
-              "default": "tempclusters.pickle"
+              }
             },
-            "edges_path": {
-              "name": "edges_path",
-              "default": "edges.pickle",
+            "regex": {
+              "default": "",
+              "name": "regex",
               "type": {
                 "type": "<class 'str'>"
               }
             }
           },
-          "inputs": {},
-          "outputs": {
-            "output": {
-              "position": "top",
-              "name": "output",
-              "type": {
-                "type": "None"
-              }
-            }
-          }
-        }
+          "type": "basic"
+        },
+        "params": {
+          "exceptions": "[email protected],[email protected],[email protected],[email protected]",
+          "mask_pattern": "masked_email_address_{}",
+          "name": "email",
+          "regex": "([a-z0-9!#$%&'*+\\/=?^_`{|.}~-]+@(?:[a-z0-9](?:[a-z0-9-]*[a-z0-9])?\\.)+[a-z0-9](?:[a-z0-9-]*[a-z0-9])?)"
+        },
+        "status": "done",
+        "title": "Mask"
       },
+      "dragHandle": ".bg-primary",
+      "height": 358.0,
+      "id": "Mask 1",
+      "parentId": null,
       "position": {
-        "x": 598.8683124946176,
-        "y": 609.9499973808545
+        "x": -1309.5065330408577,
+        "y": 731.6791509394458
       },
-      "width": 336.0,
-      "height": 320.0,
-      "parentId": null
+      "type": "basic",
+      "width": 313.0
     },
     {
-      "id": "RAG chatbot 1",
-      "type": "basic",
       "data": {
-        "title": "RAG chatbot",
-        "params": {
-          "limits_by_type": "{\"information\": [2, 3], \"summary\": [2, 3]}",
-          "max_results": "5",
-          "negative_answer": "I'm sorry, but the data I've been trained on does not contain any information related to your question.",
-          "strict_limits": true
-        },
         "display": null,
         "error": null,
         "meta": {
+          "inputs": {},
+          "name": "Mask",
           "outputs": {
             "output": {
-              "position": "top",
               "name": "output",
+              "position": "top",
               "type": {
                 "type": "None"
               }
             }
           },
           "params": {
-            "max_results": {
-              "default": 5.0,
+            "exceptions": {
+              "default": "",
+              "name": "exceptions",
               "type": {
-                "type": "<class 'int'>"
-              },
-              "name": "max_results"
+                "type": "<class 'str'>"
+              }
             },
-            "strict_limits": {
-              "name": "strict_limits",
-              "default": true,
+            "mask_pattern": {
+              "default": "",
+              "name": "mask_pattern",
               "type": {
-                "type": "<class 'bool'>"
+                "type": "<class 'str'>"
               }
             },
-            "negative_answer": {
-              "default": "I'm sorry, but the data I've been trained on does not contain any information related to your question.",
-              "name": "negative_answer",
+            "name": {
+              "default": "",
+              "name": "name",
               "type": {
                 "type": "<class 'str'>"
               }
             },
-            "limits_by_type": {
-              "default": "{}",
-              "name": "limits_by_type",
+            "regex": {
+              "default": "",
+              "name": "regex",
               "type": {
                 "type": "<class 'str'>"
               }
             }
           },
-          "name": "RAG chatbot",
-          "type": "basic",
-          "inputs": {
-            "rag_graph": {
-              "type": {
-                "type": "<class 'inspect._empty'>"
-              },
-              "name": "rag_graph",
-              "position": "bottom"
-            },
-            "llm": {
-              "name": "llm",
-              "position": "bottom",
-              "type": {
-                "type": "<class 'inspect._empty'>"
-              }
-            },
-            "scenario_selector": {
-              "type": {
-                "type": "<class 'inspect._empty'>"
-              },
-              "name": "scenario_selector",
-              "position": "bottom"
-            }
-          }
+          "type": "basic"
+        },
+        "params": {
+          "exceptions": "",
+          "mask_pattern": "masked_credit_card_number_{}",
+          "name": "credit_card",
+          "regex": "((?:(?:\\\\d{4}[- ]?){3}\\\\d{4}|\\\\d{15,16}))(?![\\\\d])"
         },
-        "beingResized": false
+        "status": "done",
+        "title": "Mask"
       },
+      "dragHandle": ".bg-primary",
+      "height": 358.0,
+      "id": "Mask 2",
+      "parentId": null,
       "position": {
-        "x": -533.1301830766971,
-        "y": 547.294980747757
+        "x": -983.2612912523697,
+        "y": 731.5859900002104
       },
-      "parentId": null,
-      "height": 399.0,
-      "width": 339.0
+      "type": "basic",
+      "width": 315.0
     },
     {
-      "id": "RAG graph 1",
-      "type": "basic",
       "data": {
-        "title": "RAG graph",
-        "params": {},
+        "__execution_delay": 0.0,
+        "collapsed": false,
         "display": null,
         "error": null,
         "meta": {
-          "type": "basic",
           "inputs": {
-            "text_embedder": {
-              "type": {
-                "type": "<class 'inspect._empty'>"
-              },
-              "position": "bottom",
-              "name": "text_embedder"
-            },
-            "vector_store": {
+            "chat_api": {
+              "name": "chat_api",
               "position": "bottom",
               "type": {
                 "type": "<class 'inspect._empty'>"
-              },
-              "name": "vector_store"
-            }
-          },
-          "name": "RAG graph",
-          "params": {},
-          "outputs": {
-            "output": {
-              "position": "top",
-              "type": {
-                "type": "None"
-              },
-              "name": "output"
-            }
-          }
-        }
-      },
-      "position": {
-        "x": -817.8208895639339,
-        "y": 1014.836542916127
-      },
-      "parentId": null,
-      "width": 200.0,
-      "height": 200.0
-    },
-    {
-      "id": "Vector store 1",
-      "type": "basic",
-      "data": {
-        "title": "Vector store",
-        "params": {
-          "name": "chromadb",
-          "collection_name": "lynx"
-        },
-        "display": null,
-        "error": null,
-        "beingResized": false,
-        "meta": {
-          "params": {
-            "collection_name": {
-              "type": {
-                "type": "<class 'str'>"
-              },
-              "default": "lynx",
-              "name": "collection_name"
+              }
             },
-            "name": {
-              "default": "chromadb",
+            "message": {
+              "name": "message",
+              "position": "left",
               "type": {
-                "type": "<class 'str'>"
-              },
-              "name": "name"
+                "type": "<class 'inspect._empty'>"
+              }
             }
           },
-          "type": "basic",
-          "name": "Vector store",
+          "name": "Test Chat API",
           "outputs": {
             "output": {
+              "name": "output",
+              "position": "right",
               "type": {
                 "type": "None"
-              },
-              "position": "top",
-              "name": "output"
+              }
             }
           },
-          "inputs": {}
-        }
-      },
-      "position": {
-        "x": -1053.794625339574,
-        "y": 1347.7711940497127
-      },
-      "height": 227.0,
-      "parentId": null,
-      "width": 275.0
-    },
-    {
-      "id": "Text embedder 2",
-      "type": "basic",
-      "data": {
-        "title": "Text embedder",
-        "params": {
-          "model": "text-embedding-ada-002"
-        },
-        "display": null,
-        "error": null,
-        "meta": {
           "params": {
-            "model": {
-              "default": "text-embedding-ada-002",
-              "type": {
-                "type": "<class 'str'>"
-              },
-              "name": "model"
-            }
-          },
-          "name": "Text embedder",
-          "outputs": {
-            "output": {
+            "show_details": {
+              "default": false,
+              "name": "show_details",
               "type": {
-                "type": "None"
-              },
-              "position": "top",
-              "name": "output"
+                "type": "<class 'bool'>"
+              }
             }
           },
-          "type": "basic",
-          "inputs": {
-            "llm": {
-              "type": {
-                "type": "<class 'inspect._empty'>"
-              },
-              "name": "llm",
-              "position": "bottom"
-            }
-          }
-        }
+          "type": "basic"
+        },
+        "params": {},
+        "status": "done",
+        "title": "Test Chat API"
       },
+      "dragHandle": ".bg-primary",
+      "height": 201.0,
+      "id": "Test Chat API 2",
+      "parentId": null,
       "position": {
-        "x": -719.98604638686,
-        "y": 1343.5978526690794
+        "x": -2024.044443214723,
+        "y": -654.8412606520155
       },
-      "width": 200.0,
-      "height": 200.0,
-      "parentId": null
+      "type": "basic",
+      "width": 906.0
     },
     {
-      "id": "LLM 2",
-      "type": "basic",
       "data": {
-        "title": "LLM",
-        "params": {
-          "name": "openai"
-        },
+        "__execution_delay": 0.0,
+        "collapsed": null,
         "display": null,
         "error": null,
         "meta": {
+          "inputs": {},
+          "name": "LynxScribe RAG Graph Vector Store",
           "outputs": {
             "output": {
-              "position": "top",
               "name": "output",
+              "position": "top",
               "type": {
                 "type": "None"
               }
             }
           },
-          "name": "LLM",
-          "type": "basic",
-          "inputs": {},
           "params": {
+            "collection_name": {
+              "default": "lynx",
+              "name": "collection_name",
+              "type": {
+                "type": "<class 'str'>"
+              }
+            },
             "name": {
-              "default": "openai",
+              "default": "faiss",
               "name": "name",
               "type": {
                 "type": "<class 'str'>"
               }
-            }
-          }
-        }
-      },
-      "position": {
-        "x": -727.6171373682814,
-        "y": 1649.7242636905507
-      },
-      "width": 200.0,
-      "parentId": null,
-      "height": 200.0
-    },
-    {
-      "id": "Truncate history 1",
-      "type": "basic",
-      "data": {
-        "title": "Truncate history",
-        "params": {
-          "max_tokens": 10000.0
-        },
-        "display": null,
-        "error": null,
-        "meta": {
-          "outputs": {
-            "output": {
-              "type": {
-                "type": "None"
-              },
-              "name": "output",
-              "position": "top"
-            }
-          },
-          "type": "basic",
-          "params": {
-            "max_tokens": {
-              "default": 10000.0,
-              "name": "max_tokens",
+            },
+            "num_dimensions": {
+              "default": 3072.0,
+              "name": "num_dimensions",
               "type": {
                 "type": "<class 'int'>"
               }
-            }
-          },
-          "name": "Truncate history",
-          "inputs": {}
-        }
-      },
-      "position": {
-        "x": 0.08889822620079713,
-        "y": 1044.7639853229612
-      },
-      "height": 200.0,
-      "width": 200.0,
-      "parentId": null
-    },
-    {
-      "id": "Chat processor 1",
-      "type": "basic",
-      "data": {
-        "title": "Chat processor",
-        "params": {},
-        "display": null,
-        "error": null,
-        "__execution_delay": null,
-        "collapsed": true,
-        "meta": {
-          "name": "Chat processor",
-          "inputs": {
-            "processor": {
-              "name": "processor",
-              "position": "bottom",
+            },
+            "text_embedder_interface": {
+              "default": "openai",
+              "name": "text_embedder_interface",
               "type": {
-                "type": "<class 'inspect._empty'>"
+                "type": "<class 'str'>"
               }
-            }
-          },
-          "params": {},
-          "type": "basic",
-          "outputs": {
-            "output": {
+            },
+            "text_embedder_model_name_or_path": {
+              "default": "text-embedding-3-large",
+              "name": "text_embedder_model_name_or_path",
               "type": {
-                "type": "None"
-              },
-              "position": "top",
-              "name": "output"
+                "type": "<class 'str'>"
+              }
             }
-          }
-        }
+          },
+          "position": {
+            "x": 189.0,
+            "y": 489.0
+          },
+          "type": "basic"
+        },
+        "params": {
+          "collection_name": "lynx",
+          "name": "faiss",
+          "num_dimensions": "1536",
+          "text_embedder_interface": "openai",
+          "text_embedder_model_name_or_path": "text-embedding-ada-002"
+        },
+        "status": "done",
+        "title": "LynxScribe RAG Graph Vector Store"
       },
+      "dragHandle": ".bg-primary",
+      "height": 443.0,
+      "id": "LynxScribe RAG Graph Vector Store 1",
       "position": {
-        "x": 182.89729246405872,
-        "y": 778.546274223181
+        "x": -2019.279230344727,
+        "y": 1080.1955856484205
       },
-      "parentId": null,
-      "width": 200.0,
-      "height": 200.0
+      "type": "basic",
+      "width": 336.0
     },
     {
-      "id": "Mask 1",
-      "type": "basic",
       "data": {
-        "title": "Mask",
-        "params": {
-          "mask_pattern": "masked_email_address_{}",
-          "name": "email",
-          "exceptions": "[email protected],[email protected],[email protected],[email protected]",
-          "regex": "([a-z0-9!#$%&'*+\\/=?^_`{|.}~-]+@(?:[a-z0-9](?:[a-z0-9-]*[a-z0-9])?\\.)+[a-z0-9](?:[a-z0-9-]*[a-z0-9])?)"
-        },
+        "__execution_delay": 0.0,
+        "collapsed": null,
         "display": null,
         "error": null,
         "meta": {
           "inputs": {},
+          "name": "Cloud-sourced File Loader",
           "outputs": {
             "output": {
-              "position": "top",
               "name": "output",
+              "position": "right",
               "type": {
                 "type": "None"
               }
             }
           },
-          "type": "basic",
-          "name": "Mask",
           "params": {
-            "name": {
-              "default": "",
-              "name": "name",
+            "accepted_file_types": {
+              "default": ".jpg, .jpeg, .png",
+              "name": "accepted_file_types",
               "type": {
                 "type": "<class 'str'>"
               }
             },
-            "exceptions": {
-              "name": "exceptions",
-              "type": {
-                "type": "<class 'str'>"
-              },
-              "default": ""
-            },
-            "regex": {
+            "cloud_provider": {
+              "default": "gcp",
+              "name": "cloud_provider",
               "type": {
                 "type": "<class 'str'>"
-              },
-              "name": "regex",
-              "default": ""
+              }
             },
-            "mask_pattern": {
-              "default": "",
+            "folder_URL": {
+              "default": "https://storage.googleapis.com/lynxkite_public_data/lynxscribe-images/image-rag-test",
+              "name": "folder_URL",
               "type": {
                 "type": "<class 'str'>"
-              },
-              "name": "mask_pattern"
+              }
             }
-          }
-        }
+          },
+          "position": {
+            "x": 189.0,
+            "y": 412.0
+          },
+          "type": "basic"
+        },
+        "params": {
+          "accepted_file_types": ".pickle",
+          "cloud_provider": "gcp",
+          "folder_URL": "https://storage.googleapis.com/lynxkite_public_data/lynxscribe-knowledge-graphs/lynx-chatbot"
+        },
+        "status": "done",
+        "title": "Cloud-sourced File Loader"
       },
+      "dragHandle": ".bg-primary",
+      "height": 325.0,
+      "id": "Cloud-sourced File Loader 1",
       "position": {
-        "x": 233.69759202223884,
-        "y": 1041.6145468043276
+        "x": -2884.195823214815,
+        "y": 630.6408986626046
       },
-      "height": 200.0,
-      "parentId": null,
-      "width": 200.0
+      "type": "basic",
+      "width": 622.0
     },
     {
-      "id": "Mask 2",
-      "type": "basic",
       "data": {
-        "title": "Mask",
-        "params": {
-          "regex": "((?:(?:\\\\d{4}[- ]?){3}\\\\d{4}|\\\\d{15,16}))(?![\\\\d])",
-          "exceptions": "",
-          "name": "credit_card",
-          "mask_pattern": "masked_credit_card_number_{}"
-        },
+        "__execution_delay": 0.0,
+        "collapsed": null,
         "display": null,
         "error": null,
         "meta": {
+          "inputs": {
+            "chat_processor": {
+              "name": "chat_processor",
+              "position": "bottom",
+              "type": {
+                "type": "<class 'inspect._empty'>"
+              }
+            },
+            "knowledge_base": {
+              "name": "knowledge_base",
+              "position": "bottom",
+              "type": {
+                "type": "<class 'inspect._empty'>"
+              }
+            }
+          },
+          "name": "LynxScribe RAG Graph Chatbot Backend",
           "outputs": {
             "output": {
               "name": "output",
@@ -756,214 +628,170 @@
               }
             }
           },
-          "inputs": {},
-          "name": "Mask",
-          "type": "basic",
           "params": {
-            "exceptions": {
+            "llm_interface": {
+              "default": "openai",
+              "name": "llm_interface",
               "type": {
                 "type": "<class 'str'>"
-              },
-              "default": "",
-              "name": "exceptions"
+              }
             },
-            "regex": {
-              "default": "",
+            "llm_model_name": {
+              "default": "gpt-4o",
+              "name": "llm_model_name",
               "type": {
                 "type": "<class 'str'>"
-              },
-              "name": "regex"
+              }
             },
-            "mask_pattern": {
-              "name": "mask_pattern",
+            "negative_answer": {
+              "default": "I'm sorry, but the data I've been trained on does not contain any information related to your question.",
+              "name": "negative_answer",
               "type": {
                 "type": "<class 'str'>"
-              },
-              "default": ""
+              }
             },
-            "name": {
-              "name": "name",
-              "default": "",
+            "retriever_limits_by_type": {
+              "default": "{}",
+              "name": "retriever_limits_by_type",
               "type": {
                 "type": "<class 'str'>"
               }
+            },
+            "retriever_max_iterations": {
+              "default": 3.0,
+              "name": "retriever_max_iterations",
+              "type": {
+                "type": "<class 'int'>"
+              }
+            },
+            "retriever_overall_chunk_limit": {
+              "default": 20.0,
+              "name": "retriever_overall_chunk_limit",
+              "type": {
+                "type": "<class 'int'>"
+              }
+            },
+            "retriever_overall_token_limit": {
+              "default": 3000.0,
+              "name": "retriever_overall_token_limit",
+              "type": {
+                "type": "<class 'int'>"
+              }
+            },
+            "retriever_strict_limits": {
+              "default": true,
+              "name": "retriever_strict_limits",
+              "type": {
+                "type": "<class 'bool'>"
+              }
             }
-          }
-        }
+          },
+          "position": {
+            "x": 543.0,
+            "y": 256.0
+          },
+          "type": "basic"
+        },
+        "params": {
+          "llm_interface": "openai",
+          "llm_model_name": "gpt-4o",
+          "negative_answer": "I'm sorry, but the data I've been trained on does not contain any information related to your question.",
+          "retriever_limits_by_type": "{\"information\": [1, 5], \"summary\": [0, 2], \"template_qna\": [1, 3], \"QnA question\": [0, 0]}",
+          "retriever_max_iterations": 3.0,
+          "retriever_overall_chunk_limit": "20",
+          "retriever_overall_token_limit": 3000.0,
+          "retriever_strict_limits": true
+        },
+        "status": "done",
+        "title": "LynxScribe RAG Graph Chatbot Backend"
       },
+      "dragHandle": ".bg-primary",
+      "height": 556.0,
+      "id": "LynxScribe RAG Graph Chatbot Backend 1",
       "position": {
-        "x": 513.2761671440603,
-        "y": 1034.8547191984255
+        "x": -2020.0,
+        "y": -188.33333333333334
       },
-      "width": 200.0,
-      "parentId": null,
-      "height": 200.0
+      "type": "basic",
+      "width": 903.0
     },
     {
-      "id": "Test Chat API 2",
-      "type": "basic",
       "data": {
-        "title": "Test Chat API",
-        "params": {
-          "show_details": false
-        },
         "display": null,
         "error": null,
-        "collapsed": false,
-        "__execution_delay": 0.0,
         "meta": {
-          "params": {
-            "show_details": {
-              "default": false,
-              "type": {
-                "type": "<class 'bool'>"
-              },
-              "name": "show_details"
-            }
-          },
           "inputs": {
-            "message": {
-              "name": "message",
+            "file_urls": {
+              "name": "file_urls",
               "position": "left",
               "type": {
                 "type": "<class 'inspect._empty'>"
               }
             },
-            "chat_api": {
+            "rag_graph": {
+              "name": "rag_graph",
               "position": "bottom",
               "type": {
                 "type": "<class 'inspect._empty'>"
-              },
-              "name": "chat_api"
+              }
             }
           },
+          "name": "LynxScribe RAG Graph Chatbot Builder",
           "outputs": {
             "output": {
-              "position": "right",
+              "name": "output",
+              "position": "top",
               "type": {
                 "type": "None"
-              },
-              "name": "output"
+              }
             }
           },
-          "name": "Test Chat API",
+          "params": {
+            "input_type": {
+              "default": "v1",
+              "name": "input_type",
+              "type": {
+                "type": "<class 'str'>"
+              }
+            },
+            "node_types": {
+              "default": "intent_cluster",
+              "name": "node_types",
+              "type": {
+                "type": "<class 'str'>"
+              }
+            },
+            "scenario_file": {
+              "default": "uploads/lynx_chatbot_scenario_selector.yaml",
+              "name": "scenario_file",
+              "type": {
+                "type": "<class 'str'>"
+              }
+            }
+          },
+          "position": {
+            "x": 466.0,
+            "y": 478.0
+          },
           "type": "basic"
-        }
+        },
+        "params": {
+          "input_type": "v1",
+          "node_types": "intent_cluster",
+          "scenario_file": "uploads/lynx_chatbot_scenario_selector.yaml"
+        },
+        "status": "done",
+        "title": "LynxScribe RAG Graph Chatbot Builder"
       },
+      "dragHandle": ".bg-primary",
+      "height": 364.0,
+      "id": "LynxScribe RAG Graph Chatbot Builder 1",
       "position": {
-        "x": -57.377776548056346,
-        "y": -16.924593985348814
+        "x": -2101.666666666667,
+        "y": 611.6666666666666
       },
-      "width": 376.0,
-      "parentId": null,
-      "height": 225.0
-    }
-  ],
-  "edges": [
-    {
-      "id": "xy-edge__Knowledge base 1output-Chat API 1knowledge_base",
-      "source": "Knowledge base 1",
-      "target": "Chat API 1",
-      "sourceHandle": "output",
-      "targetHandle": "knowledge_base"
-    },
-    {
-      "id": "xy-edge__RAG chatbot 1output-Chat API 1chatbot",
-      "source": "RAG chatbot 1",
-      "target": "Chat API 1",
-      "sourceHandle": "output",
-      "targetHandle": "chatbot"
-    },
-    {
-      "id": "xy-edge__LLM 1output-RAG chatbot 1llm",
-      "source": "LLM 1",
-      "target": "RAG chatbot 1",
-      "sourceHandle": "output",
-      "targetHandle": "llm"
-    },
-    {
-      "id": "xy-edge__Scenario selector 1output-RAG chatbot 1scenario_selector",
-      "source": "Scenario selector 1",
-      "target": "RAG chatbot 1",
-      "sourceHandle": "output",
-      "targetHandle": "scenario_selector"
-    },
-    {
-      "id": "xy-edge__RAG graph 1output-RAG chatbot 1rag_graph",
-      "source": "RAG graph 1",
-      "target": "RAG chatbot 1",
-      "sourceHandle": "output",
-      "targetHandle": "rag_graph"
-    },
-    {
-      "id": "xy-edge__Vector store 1output-RAG graph 1vector_store",
-      "source": "Vector store 1",
-      "target": "RAG graph 1",
-      "sourceHandle": "output",
-      "targetHandle": "vector_store"
-    },
-    {
-      "id": "xy-edge__Text embedder 2output-RAG graph 1text_embedder",
-      "source": "Text embedder 2",
-      "target": "RAG graph 1",
-      "sourceHandle": "output",
-      "targetHandle": "text_embedder"
-    },
-    {
-      "id": "xy-edge__LLM 2output-Text embedder 2llm",
-      "source": "LLM 2",
-      "target": "Text embedder 2",
-      "sourceHandle": "output",
-      "targetHandle": "llm"
-    },
-    {
-      "id": "xy-edge__Truncate history 1output-Chat processor 1processor",
-      "source": "Truncate history 1",
-      "target": "Chat processor 1",
-      "sourceHandle": "output",
-      "targetHandle": "processor"
-    },
-    {
-      "id": "xy-edge__Chat processor 1output-Chat API 1chat_processor",
-      "source": "Chat processor 1",
-      "target": "Chat API 1",
-      "sourceHandle": "output",
-      "targetHandle": "chat_processor"
-    },
-    {
-      "id": "xy-edge__Mask 1output-Chat processor 1processor",
-      "source": "Mask 1",
-      "target": "Chat processor 1",
-      "sourceHandle": "output",
-      "targetHandle": "processor"
-    },
-    {
-      "id": "xy-edge__Mask 2output-Chat processor 1processor",
-      "source": "Mask 2",
-      "target": "Chat processor 1",
-      "sourceHandle": "output",
-      "targetHandle": "processor"
-    },
-    {
-      "id": "xy-edge__Input chat 1output-Test Chat API 2message",
-      "source": "Input chat 1",
-      "target": "Test Chat API 2",
-      "sourceHandle": "output",
-      "targetHandle": "message"
-    },
-    {
-      "id": "xy-edge__Test Chat API 2output-View 1input",
-      "source": "Test Chat API 2",
-      "target": "View 1",
-      "sourceHandle": "output",
-      "targetHandle": "input"
-    },
-    {
-      "id": "xy-edge__Chat API 1output-Test Chat API 2chat_api",
-      "source": "Chat API 1",
-      "target": "Test Chat API 2",
-      "sourceHandle": "output",
-      "targetHandle": "chat_api"
+      "type": "basic",
+      "width": 500.0
     }
   ]
 }

examples/uploads/lynx_chatbot_scenario_selector.yaml

@@ -0,0 +1,302 @@
+- name: general_interest
+  mode: retrieve_llm  # Literal[retrieve_llm, retrieve_only, llm_only, fixed_answer, sticky_answer]
+  prompt_messages:  # Answer prompts in [role, content] format, should contain {context}
+    - role: system  # Literal[system, assistant, user, tool]
+      content: &role >
+        You are LynxScribe, a chatbot representing Lynx Analytics, a leading Singaporean analytics
+        company specializing in pharma, life sciences, generative AI, and graph AI. Your role is to
+        respond to inquiries on the Lynx Analytics website. To better understand the visitors'
+        needs, you may ask follow-up questions as detailed in subsequent instructions.
+    - role: system
+      content: &preferences >
+        Lynx Analytics specializes in a range of areas including pharma (with a focus on marketing
+        support), life sciences, graph AI, and generative AI solutions. When responding to inquiries
+        about our solutions or products, give priority to those related to generative AI (chatbots
+        for pharma and service providers), graph AI (graph reasoning), and pharma (research, key
+        opinion leaders, brand adoption ladder). Also, briefly touch upon our offerings in retail
+        (price AI, assort AI, promo AI) and finance (digital banking, Customer Happiness Index), as
+        these are areas of secondary priority. Additionally, although telecommunication is worth
+        mentioning briefly to highlight our comprehensive range of expertise and solutions.
+    - role: system
+      content: &context >
+        Respond to questions solely based on the context outlined below:\n\n{context}
+    - role: system
+      content: &instr_prices >
+        If inquiries about pricing arise, suggest contacting Lynx Analytics for detailed
+        information. Additionally, emphasize that Lynx Analytics offers solutions at competitive
+        prices without compromising on quality.
+    - role: system
+      content: &ask_industry >
+        If it's not mentioned in the chat history, include a question at the end of your response
+        to inquire about their industry interest or employment. For example: 'May I know which
+        specific domain or industry you are interested in or work in?'
+    - role: system
+      content: &ask_visit_reason >
+        If the chat history does not reveal it, ask about their reason for visiting the website. For
+        instance, you might say: 'Could you share what prompted your visit to our website today?'
+    - role: system
+      content: &final_instr >
+        Carefully answer questions based on the provided context. Refrain from introducing new
+        names; use only those within your context. Respond in the language of the question. If
+        necessary, ask follow-up questions. Ensure your answers are clear, utilizing bullet points
+        where appropriate. Avoid phrases like 'According to this article' to maintain a natural
+        tone.
+  link_answer: &link # When present, formatted node link appends to answer, should contain {link}
+        "\n\nPlease visit <a href='{link}' target='_blank'>{link}</a> for further information."
+  min_similarity_score: -1  # Only need to specify if > -1 and in RETRIEVE_LLM or RETRIEVE_ONLY mode
+- name: life_sciences_interest
+  mode: retrieve_llm
+  prompt_messages:
+    - role: system
+      content: *role
+    - role: system
+      content: *preferences
+    - role: system
+      content: *context
+    - role: system
+      content: *instr_prices
+    - role: system
+      content: &ask_profession >
+        If their job is not mentioned in the chat history, add a question at the end of your answer
+        about their profession. For example: 'Could you please tell me about your current profession
+        or occupation?'
+    - role: system
+      content: *ask_visit_reason
+    - role: system
+      content: &ask_email >
+        If their email is not already in the chat history, suggest that they can provide their email
+        address for further contact. For instance: 'Should you wish for further communication
+        regarding your queries, feel free to provide your email address.'
+    - role: system
+      content: *final_instr
+  link_answer: *link
+  min_similarity_score: -1
+- name: finance_interest
+  mode: retrieve_llm
+  prompt_messages:
+    - role: system
+      content: *role
+    - role: system
+      content: *context
+    - role: system
+      content: *instr_prices
+    - role: system
+      content: &ask_responsibilities >
+        If their job or responsibilities are not detailed in the chat history, include a question
+        at the end of your response. For example: 'Would you mind sharing some details about the
+        specific responsibilities you manage in your role?'
+    - role: system
+      content: *ask_visit_reason
+    - role: system
+      content: *ask_email
+    - role: system
+      content: *final_instr
+  link_answer: *link
+  min_similarity_score: -1
+- name: telco_interest
+  mode: retrieve_llm
+  prompt_messages:
+    - role: system
+      content: *role
+    - role: system
+      content: *context
+    - role: system
+      content: *instr_prices
+    - role: system
+      content: *ask_responsibilities
+    - role: system
+      content: *ask_visit_reason
+    - role: system
+      content: *ask_email
+    - role: system
+      content: *final_instr
+  link_answer: *link
+  min_similarity_score: -1
+- name: retail_interest
+  mode: retrieve_llm
+  prompt_messages:
+    - role: system
+      content: *role
+    - role: system
+      content: *context
+    - role: system
+      content: *instr_prices
+    - role: system
+      content: *ask_responsibilities
+    - role: system
+      content: *ask_visit_reason
+    - role: system
+      content: *ask_email
+    - role: system
+      content: *final_instr
+  link_answer: *link
+  min_similarity_score: -1
+- name: lynx_kite
+  mode: retrieve_llm
+  prompt_messages:
+    - role: system
+      content: *role
+    - role: system
+      content: *preferences
+    - role: system
+      content: *context
+    - role: system
+      content: *instr_prices
+    - role: system
+      content: *ask_industry
+    - role: system
+      content: &ask_graph >
+        If it's not mentioned in the chat history, include a question at the end of your response to
+        inquire about their specific needs related to graph analytics. For example: 'May I know
+        which particular graph-related problem you are looking to solve with graph analytics?'
+    - role: system
+      content: *ask_email
+    - role: system
+      content: *final_instr
+  link_answer: *link
+  min_similarity_score: -1
+- name: lynx_team
+  mode: retrieve_llm
+  prompt_messages:
+    - role: system
+      content: *role
+    - role: system
+      content: *context
+    - role: system
+      content: *instr_prices
+    - role: system
+      content: *ask_visit_reason
+    - role: system
+      content: >
+        When they inquire about names that could refer to multiple individuals, provide the names
+        along with a brief description of each. Then, ask for clarification on which specific
+        individual they are referring to.
+    - role: system
+      content: *final_instr
+  link_answer: *link
+  min_similarity_score: -1
+- name: lynx_career
+  mode: retrieve_llm
+  prompt_messages:
+    - role: system
+      content: *role
+    - role: system
+      content: *context
+    - role: system
+      content: *instr_prices
+    - role: system
+      content: *ask_responsibilities
+    - role: system
+      content: >
+        If it's not already mentioned in the chat history, include a question at the end of your
+        response to inquire about their motivation for wanting to work with us. For example: 'Could
+        you share what motivates you to seek a position with our team?'
+    - role: system
+      content: *ask_email
+    - role: system
+      content: *final_instr
+  link_answer: *link
+  min_similarity_score: -1
+- name: lynxscribe
+  mode: retrieve_llm
+  prompt_messages:
+    - role: system
+      content: *role
+    - role: system
+      content: *preferences
+    - role: system
+      content: *context
+    - role: system
+      content: *instr_prices
+    - role: system
+      content: *ask_industry
+    - role: system
+      content: >
+        If the chat history does not already include this information, add a question at the end of
+        your response to identify their specific needs in generative AI. For example: 'Could you
+        please specify the problem you are aiming to address using generative AI?'
+    - role: system
+      content: *ask_email
+    - role: system
+      content: *final_instr
+  link_answer: *link
+  min_similarity_score: -1
+- name: general_ds
+  mode: retrieve_llm
+  prompt_messages:
+    - role: system
+      content: *role
+    - role: system
+      content: *context
+    - role: system
+      content: *instr_prices
+    - role: system
+      content: *ask_industry
+    - role: system
+      content: *ask_visit_reason
+    - role: system
+      content: *ask_email
+    - role: system
+      content: *final_instr
+  link_answer: *link
+  min_similarity_score: -1
+- name: general_graph
+  mode: retrieve_llm
+  prompt_messages:
+    - role: system
+      content: *role
+    - role: system
+      content: *preferences
+    - role: system
+      content: *context
+    - role: system
+      content: *instr_prices
+    - role: system
+      content: *ask_graph
+    - role: system
+      content: *ask_industry
+    - role: system
+      content: *ask_email
+    - role: system
+      content: *final_instr
+  link_answer: *link
+  min_similarity_score: -1
+- name: other_okay
+  mode: retrieve_llm
+  prompt_messages:
+    - role: system
+      content: *role
+    - role: system
+      content: *preferences
+    - role: system
+      content: *context
+    - role: system
+      content: *instr_prices
+    - role: system
+      content: *ask_industry
+    - role: system
+      content: *ask_visit_reason
+    - role: system
+      content: *final_instr
+  link_answer: *link
+  min_similarity_score: -1
+- name: contact_us
+  mode: retrieve_llm
+  prompt_messages:
+    - role: system
+      content: *role
+    - role: system
+      content: *context
+    - role: system
+      content: *instr_prices
+    - role: system
+      content: *ask_email
+    - role: system
+      content: *final_instr
+  link_answer: *link
+  min_similarity_score: -1
+- name: malicious
+  mode: fixed_answer  # Could be sticky, but if we want the user to rephrase, let's give 2nd chance
+  fixed_answer: >
+    I am sorry, but I feel you want me use in a wrong way. If I feel it wrong, please try to
+    rephrase your question.

lynxkite-lynxscribe/src/lynxkite_lynxscribe/lynxscribe_ops.py

@@ -30,6 +30,8 @@ from lynxkite.core import ops
 import json
 from lynxkite.core.executors import one_by_one
 
+DEFAULT_NEGATIVE_ANSWER = "I'm sorry, but the data I've been trained on does not contain any information related to your question."
+
 # logger
 # import logging
 # logging.basicConfig(level=logging.INFO)
@@ -42,11 +44,12 @@ op = ops.op_registration(ENV)
 output_on_top = ops.output_position(output="top")
 
 
-@op("Cloud-sourced Image Loader")
-def cloud_image_loader(
+@op("Cloud-sourced File Loader")
+def cloud_file_loader(
     *,
     cloud_provider: str = "gcp",
     folder_URL: str = "https://storage.googleapis.com/lynxkite_public_data/lynxscribe-images/image-rag-test",
+    accepted_file_types: str = ".jpg, .jpeg, .png",
 ):
     """
     Gives back the list of URLs of all the images from a cloud-based folder.
@@ -55,6 +58,8 @@ def cloud_image_loader(
     if folder_URL[-1].endswith("/"):
         folder_URL = folder_URL[:-1]
 
+    accepted_file_types = tuple([t.strip() for t in accepted_file_types.split(",")])
+
     if cloud_provider == "gcp":
         client = storage.Client()
         url_useful_part = folder_URL.split(".com/")[-1]
@@ -66,18 +71,16 @@ def cloud_image_loader(
 
         bucket = client.bucket(bucket_name)
         blobs = bucket.list_blobs(prefix=prefix)
-        image_urls = [
-            blob.public_url
-            for blob in blobs
-            if blob.name.endswith((".jpg", ".jpeg", ".png"))
+        file_urls = [
+            blob.public_url for blob in blobs if blob.name.endswith(accepted_file_types)
         ]
-        return {"image_urls": image_urls}
+        return {"file_urls": file_urls}
     else:
         raise ValueError(f"Cloud provider '{cloud_provider}' is not supported.")
 
 
 @output_on_top
-@op("LynxScribe RAG Vector Store")
+@op("LynxScribe RAG Graph Vector Store")
 @mem.cache
 def ls_rag_graph(
     *,
@@ -151,7 +154,7 @@ def ls_image_describer(
 @op("LynxScribe Image RAG Builder")
 @mem.cache
 async def ls_image_rag_builder(
-    image_urls,
+    file_urls,
     image_describer,
     rag_graph,
 ):
@@ -166,7 +169,7 @@ async def ls_image_rag_builder(
 
     # handling inputs
     image_describer = image_describer[0]["image_describer"]
-    image_urls = image_urls["image_urls"]
+    image_urls = file_urls["file_urls"]
     rag_graph = rag_graph[0]["rag_graph"]
 
     # generate prompts from inputs
@@ -300,83 +303,207 @@ def view_image(embedding_similarities):
     return embedding_similarities[0]["image_url"]
 
 
-@output_on_top
-@op("Vector store")
-def vector_store(*, name="chromadb", collection_name="lynx"):
-    vector_store = get_vector_store(name=name, collection_name=collection_name)
-    return {"vector_store": vector_store}
+# @output_on_top
+# @op("Vector store")
+# def vector_store(*, name="chromadb", collection_name="lynx"):
+#     vector_store = get_vector_store(name=name, collection_name=collection_name)
+#     return {"vector_store": vector_store}
 
 
-@output_on_top
-@op("LLM")
-def llm(*, name="openai"):
-    llm = get_llm_engine(name=name)
-    return {"llm": llm}
+# @output_on_top
+# @op("LLM")
+# def llm(*, name="openai"):
+#     llm = get_llm_engine(name=name)
+#     return {"llm": llm}
 
 
-@output_on_top
-@ops.input_position(llm="bottom")
-@op("Text embedder")
-def text_embedder(llm, *, model="text-embedding-ada-002"):
-    llm = llm[0]["llm"]
-    text_embedder = TextEmbedder(llm=llm, model=model)
-    return {"text_embedder": text_embedder}
+# @output_on_top
+# @ops.input_position(llm="bottom")
+# @op("Text embedder")
+# def text_embedder(llm, *, model="text-embedding-ada-002"):
+#     llm = llm[0]["llm"]
+#     text_embedder = TextEmbedder(llm=llm, model=model)
+#     return {"text_embedder": text_embedder}
 
 
-@output_on_top
-@ops.input_position(vector_store="bottom", text_embedder="bottom")
-@op("RAG graph")
-def rag_graph(vector_store, text_embedder):
-    vector_store = vector_store[0]["vector_store"]
-    text_embedder = text_embedder[0]["text_embedder"]
-    rag_graph = RAGGraph(
-        PandasKnowledgeBaseGraph(vector_store=vector_store, text_embedder=text_embedder)
-    )
-    return {"rag_graph": rag_graph}
+# @output_on_top
+# @ops.input_position(vector_store="bottom", text_embedder="bottom")
+# @op("RAG graph")
+# def rag_graph(vector_store, text_embedder):
+#     vector_store = vector_store[0]["vector_store"]
+#     text_embedder = text_embedder[0]["text_embedder"]
+#     rag_graph = RAGGraph(
+#         PandasKnowledgeBaseGraph(vector_store=vector_store, text_embedder=text_embedder)
+#     )
+#     return {"rag_graph": rag_graph}
 
 
 @output_on_top
-@op("Scenario selector")
-def scenario_selector(*, scenario_file: str, node_types="intent_cluster"):
+@ops.input_position(rag_graph="bottom")
+@op("LynxScribe RAG Graph Chatbot Builder")
+@mem.cache
+def ls_rag_chatbot_builder(
+    file_urls,
+    rag_graph,
+    *,
+    scenario_file: str = "uploads/lynx_chatbot_scenario_selector.yaml",
+    node_types: str = "intent_cluster",
+    input_type: str = "v1",
+):
+    """
+    Builds up a RAG Graph-based chatbot. It could load the chatbot from
+    an existing folder (v1 or v2).
+
+    TODO: Later, we should not use these saved files, but we should build
+    up the chatbot from scratch - will be added soon). That time we will
+    add the summarizer-related parameters (LLM interface and model).
+
+    TODO: Later, the scenario selector can be built up synthetically from
+    the input documents - or semi-automated.
+
+    TODO: Currently, we do not affected by the embedder, as the files are
+    pre-loaded, so the text embedder should have the same model as the
+    one used in the files...
+    """
+
     scenarios = load_config(scenario_file)
     node_types = [t.strip() for t in node_types.split(",")]
+
+    # handling inputs
+    file_urls = file_urls["file_urls"]
+    rag_graph = rag_graph[0]["rag_graph"]
+
+    # loading v1 knowledge base (shitty solution, but temporary)
+    if input_type == "v1":
+        node_file = [f for f in file_urls if "nodes.p" in f][0]
+        edge_file = [f for f in file_urls if "edges.p" in f][0]
+        tempcluster_file = [f for f in file_urls if "clusters.p" in f][0]
+        rag_graph.kg_base.load_v1_knowledge_base(
+            nodes_path=node_file,
+            edges_path=edge_file,
+            template_cluster_path=tempcluster_file,
+        )
+    elif input_type == "v2":
+        raise ValueError("Currently only v1 input type is supported.")
+    else:
+        raise ValueError(f"Input type '{input_type}' is not supported.")
+
+    # loading the scenarios
     scenario_selector = ScenarioSelector(
         scenarios=[Scenario(**scenario) for scenario in scenarios],
         node_types=node_types,
     )
-    return {"scenario_selector": scenario_selector}
 
+    # TODO: later we should unify this "knowledge base" object across the functions
+    # this could be always an input of a RAG Chatbot, but also for other apps.
+    return {
+        "knowledge_base": {
+            "rag_graph": rag_graph,
+            "scenario_selector": scenario_selector,
+        }
+    }
 
-DEFAULT_NEGATIVE_ANSWER = "I'm sorry, but the data I've been trained on does not contain any information related to your question."
+
+# @output_on_top
+# @op("Scenario selector")
+# def scenario_selector(*, scenario_file: str, node_types="intent_cluster"):
+#     scenarios = load_config(scenario_file)
+#     node_types = [t.strip() for t in node_types.split(",")]
+#     scenario_selector = ScenarioSelector(
+#         scenarios=[Scenario(**scenario) for scenario in scenarios],
+#         node_types=node_types,
+#     )
+#     return {"scenario_selector": scenario_selector}
 
 
 @output_on_top
-@ops.input_position(rag_graph="bottom", scenario_selector="bottom", llm="bottom")
-@op("RAG chatbot")
-def rag_chatbot(
-    rag_graph,
-    scenario_selector,
-    llm,
+@ops.input_position(knowledge_base="bottom", chat_processor="bottom")
+@op("LynxScribe RAG Graph Chatbot Backend")
+def ls_rag_chatbot_backend(
+    knowledge_base,
+    chat_processor,
     *,
     negative_answer=DEFAULT_NEGATIVE_ANSWER,
-    limits_by_type="{}",
-    strict_limits=True,
-    max_results=5,
+    retriever_limits_by_type="{}",
+    retriever_strict_limits=True,
+    retriever_overall_chunk_limit=20,
+    retriever_overall_token_limit=3000,
+    retriever_max_iterations=3,
+    llm_interface: str = "openai",
+    llm_model_name: str = "gpt-4o",
+    # api_key_name: str = "OPENAI_API_KEY",
 ):
-    rag_graph = rag_graph[0]["rag_graph"]
-    scenario_selector = scenario_selector[0]["scenario_selector"]
-    llm = llm[0]["llm"]
-    limits_by_type = json.loads(limits_by_type)
+    """
+    Returns with a chatbot instance.
+    """
+
+    # handling_inputs
+    rag_graph = knowledge_base[0]["knowledge_base"]["rag_graph"]
+    scenario_selector = knowledge_base[0]["knowledge_base"]["scenario_selector"]
+    chat_processor = chat_processor[0]["chat_processor"]
+    limits_by_type = json.loads(retriever_limits_by_type)
+
+    # connecting to the LLM
+    llm_params = {"name": llm_interface}
+    # if api_key_name:
+    #     llm_params["api_key"] = os.getenv(api_key_name)
+    llm = get_llm_engine(**llm_params)
+
+    # setting the parameters
+    params = {
+        "limits_by_type": limits_by_type,
+        "strict_limits": retriever_strict_limits,
+        "max_results": retriever_overall_chunk_limit,
+        "token_limit": retriever_overall_token_limit,
+        "max_iterations": retriever_max_iterations,
+    }
+
+    # generating the RAG Chatbot
     rag_chatbot = RAGChatbot(
         rag_graph=rag_graph,
         scenario_selector=scenario_selector,
         llm=llm,
         negative_answer=negative_answer,
-        limits_by_type=limits_by_type,
-        strict_limits=strict_limits,
-        max_results=max_results,
+        **params,
+    )
+
+    # generating the chatbot back-end
+    c = ChatAPI(
+        chatbot=rag_chatbot,
+        chat_processor=chat_processor,
+        model=llm_model_name,
     )
-    return {"chatbot": rag_chatbot}
+
+    return {"chat_api": c}
+
+
+# @output_on_top
+# @ops.input_position(rag_graph="bottom", scenario_selector="bottom", llm="bottom")
+# @op("RAG chatbot")
+# def rag_chatbot(
+#     rag_graph,
+#     scenario_selector,
+#     llm,
+#     *,
+#     negative_answer=DEFAULT_NEGATIVE_ANSWER,
+#     limits_by_type="{}",
+#     strict_limits=True,
+#     max_results=5,
+# ):
+#     rag_graph = rag_graph[0]["rag_graph"]
+#     scenario_selector = scenario_selector[0]["scenario_selector"]
+#     llm = llm[0]["llm"]
+#     limits_by_type = json.loads(limits_by_type)
+#     rag_chatbot = RAGChatbot(
+#         rag_graph=rag_graph,
+#         scenario_selector=scenario_selector,
+#         llm=llm,
+#         negative_answer=negative_answer,
+#         limits_by_type=limits_by_type,
+#         strict_limits=strict_limits,
+#         max_results=max_results,
+#     )
+#     return {"chatbot": rag_chatbot}
 
 
 @output_on_top
@@ -446,37 +573,37 @@ def input_chat(*, chat: str):
     return {"text": chat}
 
 
-@output_on_top
-@ops.input_position(chatbot="bottom", chat_processor="bottom", knowledge_base="bottom")
-@op("Chat API")
-def chat_api(chatbot, chat_processor, knowledge_base, *, model="gpt-4o-mini"):
-    chatbot = chatbot[0]["chatbot"]
-    chat_processor = chat_processor[0]["chat_processor"]
-    knowledge_base = knowledge_base[0]
-    c = ChatAPI(
-        chatbot=chatbot,
-        chat_processor=chat_processor,
-        model=model,
-    )
-    if knowledge_base:
-        c.chatbot.rag_graph.kg_base.load_v1_knowledge_base(**knowledge_base)
-        c.chatbot.scenario_selector.check_compatibility(c.chatbot.rag_graph)
-    return {"chat_api": c}
-
-
-@output_on_top
-@op("Knowledge base")
-def knowledge_base(
-    *,
-    nodes_path="nodes.pickle",
-    edges_path="edges.pickle",
-    template_cluster_path="tempclusters.pickle",
-):
-    return {
-        "nodes_path": nodes_path,
-        "edges_path": edges_path,
-        "template_cluster_path": template_cluster_path,
-    }
+# @output_on_top
+# @ops.input_position(chatbot="bottom", chat_processor="bottom", knowledge_base="bottom")
+# @op("Chat API")
+# def chat_api(chatbot, chat_processor, knowledge_base, *, model="gpt-4o-mini"):
+#     chatbot = chatbot[0]["chatbot"]
+#     chat_processor = chat_processor[0]["chat_processor"]
+#     knowledge_base = knowledge_base[0]
+#     c = ChatAPI(
+#         chatbot=chatbot,
+#         chat_processor=chat_processor,
+#         model=model,
+#     )
+#     if knowledge_base:
+#         c.chatbot.rag_graph.kg_base.load_v1_knowledge_base(**knowledge_base)
+#         c.chatbot.scenario_selector.check_compatibility(c.chatbot.rag_graph)
+#     return {"chat_api": c}
+
+
+# @output_on_top
+# @op("Knowledge base")
+# def knowledge_base(
+#     *,
+#     nodes_path="nodes.pickle",
+#     edges_path="edges.pickle",
+#     template_cluster_path="tempclusters.pickle",
+# ):
+#     return {
+#         "nodes_path": nodes_path,
+#         "edges_path": edges_path,
+#         "template_cluster_path": template_cluster_path,
+#     }
 
 
 @op("View", view="table_view")