kobai-sdk 0.3.0rc2__py3-none-any.whl → 0.3.2__py3-none-any.whl

kobai/ai_query.py

@@ -1,8 +1,6 @@
 from langchain_core.prompts import ChatPromptTemplate, SystemMessagePromptTemplate, HumanMessagePromptTemplate, AIMessagePromptTemplate
 from langchain_core.output_parsers import StrOutputParser
 
-from sentence_transformers import SentenceTransformer, util
-
 from langchain_core.language_models.chat_models import BaseChatModel
 from langchain_core.embeddings import Embeddings
 from langchain_core.documents import Document
@@ -10,8 +8,9 @@ from langchain_core.retrievers import BaseRetriever
 from langchain_core.callbacks import CallbackManagerForRetrieverRun
 from langchain_core.runnables import RunnablePassthrough, RunnableLambda
 from langchain_core.vectorstores import InMemoryVectorStore
+import numpy as np
 
-from typing import Union, List
+from typing import List
 
 
 MESSAGE_SYSTEM_TEMPLATE = """
@@ -73,7 +72,7 @@ def format_docs(docs):
 def input_only(inpt):
     return inpt["question"]
 
-def followup_question(user_question, question_results, question_name, question_def, embedding_model: Union[SentenceTransformer, Embeddings], chat_model: BaseChatModel, use_inmem_vectors=False, k=50):
+def followup_question(user_question, question_results, question_name, question_def, embedding_model: Embeddings, chat_model: BaseChatModel, use_inmem_vectors=False, k=50):
     
     row_texts = process_question_results(question_def, question_results)
     question_documents = [Document(page_content=r, metadata={"source": "kobai"}) for r in row_texts]
@@ -118,22 +117,13 @@ def init_question_search_index(tenant_questions, emb_model):
     
     q_ids = [q["id"] for q in tenant_questions]
     q_descs = [q["description"] for q in tenant_questions]
-
-    if isinstance(emb_model, SentenceTransformer):
-        q_vectors = emb_model.encode(q_descs)
-    else:
-        q_vectors = emb_model.embed_documents(q_descs)
-    
+    q_vectors = emb_model.embed_documents(q_descs)
     return {"ids": q_ids, "descs": q_descs, "vectors": q_vectors}
 
 
 def question_search(search_text: str, search_index, emb_model, k: int):
-    if isinstance(emb_model, SentenceTransformer):
-        search_vec = emb_model.encode(search_text)
-    else:
-        search_vec = emb_model.embed_query(search_text)
+    search_vec = emb_model.embed_query(search_text)
     #search_vec = emb_model.encode(search_text)
-
     matches = __top_vector_matches(search_vec, search_index["vectors"], top=k)
 
     for mi, m in enumerate(matches):
@@ -142,13 +132,25 @@ def question_search(search_text: str, search_index, emb_model, k: int):
     return matches
 
 def __top_vector_matches(test_vec, options_list_vec, top=1):
-    scores_t = util.cos_sim(test_vec, options_list_vec)[0]
-    scores_l = scores_t.tolist()
-    scores_d = [{"index": i, "value": v} for i, v in enumerate(scores_l)]
-    sorted_d = sorted(scores_d, key=lambda i: i["value"], reverse=True)
-    top_d = sorted_d[0:top]
+    # Normalize the test vector
+    test_vec_norm = test_vec / np.linalg.norm(test_vec)
+    # Normalize the option vectors
+    options_norm = options_list_vec / np.linalg.norm(options_list_vec, axis=1, keepdims=True)
+    
+    # Compute cosine similarity (dot product of normalized vectors)
+    cosine_similarities = np.dot(options_norm, test_vec_norm)
+    
+    # Get indexes and similarity scores as dict
+    scores_d = [{"index": i, "value": float(v)} for i, v in enumerate(cosine_similarities)]
+    
+    # Sort dict by similarity score descending
+    sorted_d = sorted(scores_d, key=lambda x: x["value"], reverse=True)
+    
+    # Return top results
+    top_d = sorted_d[:top]
     return top_d
 
+
 def process_question_results(question_def, question_results):
 
     """
@@ -211,8 +213,9 @@ def process_question_results(question_def, question_results):
 
 
     concept_order = [max_src]
-    for t in concept_rels[max_src]["edges"]:
-        concept_order.append(t["dst"])
+    if max_src != "":
+        for t in concept_rels[max_src]["edges"]:
+            concept_order.append(t["dst"])
 
     for c in concept_props:
         if c not in concept_order:

kobai/ai_rag.py

@@ -3,9 +3,7 @@ from pyspark.sql import SparkSession
 
 from pyspark.sql.types import StructType, StructField, StringType, ArrayType, FloatType, IntegerType
 from pyspark.sql import functions as F
-from sentence_transformers import SentenceTransformer
 from delta import DeltaTable
-from typing import Union
 from langchain_core.language_models.chat_models import BaseChatModel
 from langchain_core.embeddings import Embeddings
 from langchain_community.document_loaders import PySparkDataFrameLoader
@@ -145,13 +143,13 @@ def __generate_sentences_from_questions(tc: AIContext, debug):
     ss.sql(full_sql)
 
 
-def encode_to_delta_local(tc: AIContext, st_model: Union[SentenceTransformer, Embeddings], replica_schema=None, batch_size=100000):
+def encode_to_delta_local(tc: AIContext, st_model: Embeddings, replica_schema=None, batch_size=100000):
     """
     Encode Semantic Data to Vectors in Delta Table
 
     Parameters:
     tc (TenantClient): The Kobai tenant_client instance instantiated via the SDK.
-    st_model (SentenceTransformer): A sentence_transformers model to use for encoding.
+    st_model (Embeddings): A langchain embedding model to use for encoding.
     replica_schema (str) OPTIONAL: An alternate schema (catalog.database) to create the Delta table. Useful when the base Kobai schema is not on a Unity Catalog.
     """
 
@@ -174,12 +172,8 @@ def encode_to_delta_local(tc: AIContext, st_model: Union[SentenceTransformer, Em
         content_list = [r["content"] for r in sentences_df.collect()]
         id_list = [r["id"] for r in sentences_df.collect()]
 
-        if isinstance(st_model, SentenceTransformer):
-            vector_list = st_model.encode(
-                content_list, normalize_embeddings=True, show_progress_bar=True).tolist()
-        else:
-            vector_list = st_model.embed_documents(content_list)
-            for i, v in enumerate(vector_list):
+        vector_list = st_model.embed_documents(content_list)
+        for i, v in enumerate(vector_list):
                 vector_list[i] = [float(x) for x in v]
         #vector_list = st_model.encode(
         #    content_list, normalize_embeddings=True, show_progress_bar=True)
@@ -214,13 +208,13 @@ def encode_to_delta_local(tc: AIContext, st_model: Union[SentenceTransformer, Em
     #      """)
 
 
-def rag_delta(tc: AIContext, emb_model: Union[SentenceTransformer, Embeddings], chat_model: BaseChatModel, question, k=5, replica_schema=None):
+def rag_delta(tc: AIContext, emb_model: Embeddings, chat_model: BaseChatModel, question, k=5, replica_schema=None):
     """
     Run a RAG query using vectors in Delta table.
 
     Parameters:
     tc (TenantClient): The Kobai tenant_client instance instantiated via the SDK.
-    emb_model (UNION[SentenceTransformer, Embeddings]): A sentence_transformers or langchain embedding model to use for encoding the query.
+    emb_model (Embeddings): A langchain embedding model to use for encoding the query.
     chat_model (BaseChatModel): A langchain chat model to use in the RAG pipeline.
     question (str): The user's query.
     k (int) OPTIONAL: The number of RAG documents to retrieve.
@@ -233,10 +227,7 @@ def rag_delta(tc: AIContext, emb_model: Union[SentenceTransformer, Embeddings],
 
     ss = tc.spark_session
 
-    if isinstance(emb_model, SentenceTransformer):
-        vector_list = emb_model.encode(
-            question, normalize_embeddings=True).tolist()
-    elif isinstance(emb_model, Embeddings):
+    if isinstance(emb_model, Embeddings):
         vector_list = emb_model.embed_query(question)
     else:
         print("Invalid Embedding Model Type")

kobai/tenant_client.py

@@ -7,13 +7,10 @@ from pyspark.sql import SparkSession
 
 from langchain_community.chat_models import ChatDatabricks
 from databricks_langchain import DatabricksEmbeddings
-from sentence_transformers import SentenceTransformer
 from langchain_core.language_models.chat_models import BaseChatModel
 from langchain_core.embeddings import Embeddings
-from typing import Union
 
-from . import spark_client, databricks_client, ai_query, tenant_api, ai_rag, mobi
-from .mobi_config import MobiSettings
+from . import spark_client, databricks_client, ai_query, tenant_api, ai_rag
 
 class TenantClient:
 
@@ -59,128 +56,12 @@ class TenantClient:
         self.__api_init_session()
 
     
-########################################
-# Mobi
-########################################
-
-    def pull_mobi_to_tenant(self, ontology_name, mobi_config: MobiSettings):
-
-        """
-        Export an ontology from Mobi and import it into a Kobai tenant, replacing the contents of the tenant.
-
-        Requires that the SDK be authenticated against the target Kobai tenant.
-
-        Parameters:
-        ontology_name (str): The name of the ontology to access in Mobi.
-        mobi_config (MobiSettings): Configuration required to access the Mobi service.
-        """
-         
-        _, tenant_json_enc = mobi.get_tenant(ontology_name, mobi_config)
-        self.__set_tenant_import(tenant_json_enc) 
-
-    def pull_mobi_to_file(self, ontology_name, mobi_config: MobiSettings, file_name, human_readable=False):
-
-        """
-        Export an ontology from Mobi and save it in a Kobai json import file.
-
-        Requires that the SDK be authenticated against the target Kobai tenant.
-
-        Parameters:
-        ontology_name (str): The name of the ontology to access in Mobi.
-        mobi_config (MobiSettings): Configuration required to access the Mobi service.
-        file_name (str): File name to give the output (no extension)
-        human_readable (bool) OPTIONAL: generate a second, decoded Kobai file.
-        """
-
-        tenant_json, tenant_json_enc = mobi.get_tenant(ontology_name, mobi_config)
-
-        if ".json" in file_name:
-            file_name = file_name.split(".json")[0]
-
-        with open(f"{file_name}.json", "w") as out_file:
-            json.dump(tenant_json_enc, out_file)
-
-        if human_readable:
-            with open(f"{file_name}_decoded.json", "w") as out_file:
-                json.dump(tenant_json, out_file)
-
-    def push_tenant_update_to_mobi(self, ontology_name, mobi_config: MobiSettings):
-
-        """
-        Compare a (modified) Kobai tenant to a Mobi ontology, and generate a Merge Request for the changes.
-
-        Requires that the SDK be authenticated against the target Kobai tenant.
-
-        Parameters:
-        ontology_name (str): The name of the ontology to access in Mobi.
-        mobi_config (MobiSettings): Configuration required to access the Mobi service.
-        """
-
-        tenant_json_enc = self.__get_tenant_export()
-        mobi.update_tenant(tenant_json_enc, ontology_name, mobi_config)
-
-    def push_whole_tenant_to_mobi(self, ontology_name, mobi_config: MobiSettings):
-
-        """
-        Export a tenant from Kobai, and create an ontology in Mobi.
-
-        Requires that the SDK be authenticated against the target Kobai tenant.
-        Requires that an ontology with the same name does not already exist in Mobi.
-
-        Parameters:
-        ontology_name (str): The name of the ontology to create in Mobi.
-        mobi_config (MobiSettings): Configuration required to access the Mobi service.
-        """
-
-        tenant_json = self.get_tenant_config()
-        mobi.replace_tenant_to_mobi(tenant_json, ontology_name, mobi_config)
-
-    def push_whole_tenant_to_jsonld_file(self, ontology_name, file_name):
-
-        """
-        Export a tenant from Kobai, and create an ontology in Mobi.
-
-        Requires that the SDK be authenticated against the target Kobai tenant.
-
-        Parameters:
-        ontology_name (str): The name of the ontology to create in Mobi.
-        file_name (str): File name to give the output (no extension)
-        """
-
-        tenant_json = self.get_tenant_config()
-        tenant_jsonld = mobi.replace_tenant_to_file(tenant_json, ontology_name)
-
-        if ".json" in file_name:
-            file_name = file_name.split(".json")[0]
-
-        with open(f"{file_name}.json", "w") as out_file:
-            json.dump(tenant_jsonld, out_file)
-
-    def get_default_mobi_config(self):
-
-        """
-        Returns a default MobiSettings configuration object.
-
-        Available Fields to Set:
-        domain_extraction: Mapping of ontology url structures to Kobai domain names.
-        mobi_api_url: url for Mobi service. (ex: https://localhost:8443/mobirest)
-        mobi_username: User name for Mobi service.
-        mobi_password: Password for Mobi service.
-        """
-
-        return MobiSettings()
-
-    def __set_tenant_import(self, tenant_json_enc):
-        self.api_client._TenantAPI__run_post_files(
-            '/data-svcs/solution/snapshot/import/upload',
-            {'file': json.dumps(tenant_json_enc)}
-        )
 
 ########################################
 # MS Entra Auth
 ########################################
 
-    def use_browser_token(self, access_token, run_ai_init: bool = True):
+    def use_browser_token(self, access_token):
 
         """
         Authenticate the TenantClient with the Kobai instance. Returns nothing, but stores bearer token in client.
@@ -189,9 +70,9 @@ class TenantClient:
         Parameters:
         access_token (str): Bearer token for Kobai app session.
         """
-        self._init_post_auth_success(access_token, run_ai_init)
+        self._init_post_auth_success(access_token)
 
-    def use_access_token(self, access_token: str, id_token: str = None,  tenant_id: str = None, run_ai_init: bool = True):
+    def use_access_token(self, access_token: str, id_token: str = None,  tenant_id: str = None):
 
         """
         Authenticate the TenantClient with the Kobai instance. Returns nothing, but stores bearer token in client.
@@ -215,7 +96,7 @@ class TenantClient:
         )
 
         kb_access_token = response.headers.get('Authorization')
-        self.use_browser_token(kb_access_token, run_ai_init)
+        self.use_browser_token(kb_access_token)
 
     def get_tenants(self, id_token: str = None):
 
@@ -242,12 +123,10 @@ class TenantClient:
     def __api_init_session(self):
         self.api_client = tenant_api.TenantAPI(self.token, self.uri, verify=self.ssl_verify, proxies=self.proxies )
 
-    def _init_post_auth_success(self, access_token, run_ai_init: bool = True):
+    def _init_post_auth_success(self, access_token):
         self.token = access_token
         self.__api_init_session()
         self.__set_tenant_solutionid()
-        if run_ai_init:
-            self.init_ai_components()
         print("Authentication Successful.")
 
 ########################################
@@ -560,7 +439,7 @@ class TenantClient:
         """
         ai_rag.generate_sentences(self.get_ai_context(), replica_schema=replica_schema, concept_white_list=concept_white_list, use_questions=use_questions, debug=debug)
 
-    def rag_encode_to_delta_local(self, st_model: Union[SentenceTransformer, Embeddings], replica_schema=None, batch_size=100000):
+    def rag_encode_to_delta_local(self, st_model: Embeddings, replica_schema=None, batch_size=100000):
         """
         Encode Semantic Data to Vectors in Delta Table
 
@@ -570,7 +449,7 @@ class TenantClient:
         """
         ai_rag.encode_to_delta_local(self.get_ai_context(), st_model=st_model, replica_schema=replica_schema, batch_size=batch_size)
 
-    def rag_delta(self, emb_model: Union[SentenceTransformer, Embeddings], chat_model: BaseChatModel, question, k=5, replica_schema=None):
+    def rag_delta(self, emb_model: Embeddings, chat_model: BaseChatModel, question, k=5, replica_schema=None):
         """
         Run a RAG query using vectors in Delta table.
 
@@ -598,9 +477,7 @@ class TenantClient:
         """
 
         if question_id is None:
-
             suggestions = self.question_search(user_question, k=1)
-
             question_id = suggestions[0]["id"]
         
         question_results = self.run_question_remote(question_id, dynamic_filters=dynamic_filters)
@@ -610,26 +487,16 @@ class TenantClient:
 
         return ai_query.followup_question(user_question, question_results, question_name, question_def, self.embedding_model, self.chat_model, use_inmem_vectors=use_inmem_vectors, k=k)
 
-    def init_ai_components(self, embedding_model: Union[SentenceTransformer, Embeddings] = None, chat_model: BaseChatModel = None):
+    def init_ai_components(self, embedding_model: Embeddings, chat_model: BaseChatModel):
         """
         Set Chat and Embedding models for AI functions to use. If no arguments provided, Databricks hosted services are used.
 
         Parameters:
-        embedding_model (Union[SentenceTransformer, Embeddings]) OPTIONAL: A sentence_transformer or Langchain Embedding model.
-        chat_model (BaseChatModel) OPTIONAL: A Langchain BaseChatModel chat model.
+        embedding_model (Embeddings): A Langchain Embedding model.
+        chat_model (BaseChatModel): A Langchain BaseChatModel chat model.
         """
-         
-        if embedding_model is not None:
-            self.embedding_model = embedding_model
-        else:
-            #self.embedding_model = SentenceTransformer("baai/bge-large-en-v1.5")
-            self.embedding_model = DatabricksEmbeddings(endpoint="databricks-bge-large-en")
-        
-        if chat_model is not None:
-            self.chat_model = chat_model
-        else:
-            self.chat_model = ChatDatabricks(endpoint="databricks-dbrx-instruct")
-
+        self.embedding_model = embedding_model
+        self.chat_model = chat_model
         self.question_search_index = ai_query.init_question_search_index(self.list_questions(), self.embedding_model)
 
     def question_search(self, search_text, k: int = 1):

{kobai_sdk-0.3.0rc2.dist-info → kobai_sdk-0.3.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kobai-sdk
-Version: 0.3.0rc2
+Version: 0.3.2
 Summary: A package that enables interaction with a Kobai tenant.
 Author-email: Ryan Oattes <ryan@kobai.io>
 License:                                  Apache License
@@ -223,7 +223,6 @@ Requires-Dist: langchain-core
 Requires-Dist: langchain-community
 Requires-Dist: langchain_openai
 Requires-Dist: databricks_langchain
-Requires-Dist: sentence-transformers
 Provides-Extra: dev
 Requires-Dist: black; extra == "dev"
 Requires-Dist: bumpver; extra == "dev"
@@ -249,38 +248,51 @@ from kobai import tenant_client, spark_client, databricks_client
 
 schema = 'main.demo'
 uri = 'https://demo.kobai.io'
-tenant_id = '1'
 tenant_name = 'My Demo Tenant'
-
-k = tenant_client.TenantClient(tenant_name, tenant_id, uri, schema)
+k = tenant_client.TenantClient(tenant_name, uri, schema)
 ```
 
 2. Authenticate with the Kobai instance:
+Authentication can be performed using different methods, such as device code flow, on-behalf-of flow, or browser-based tokens.
+
+#### Authentication via device code
+Step 1: Obtain the access token from IDM (Identity and Access Management)
 
 ```python
-client_id = 'your_Entra_app_id_here'
+from kobai import ms_authenticate
+
 tenant_id = 'your_Entra_directory_id_here'
+client_id = 'your_Entra_app_id_here'
 
-k.authenticate(client_id, tenant_id)
+access_token = ms_authenticate.device_code(tenant_id, client_id)
 ```
 
-3. Initialize a Spark client using your current `SparkSession`, and generate semantically-rich SQL views describing this Kobai tenant:
+Step 2: Use the token to retrieve the list of Kobai tenants (unless the tenant ID is already known).
 
 ```python
-k.spark_init_session(spark)
-k.spark_generate_genie_views()
+tenants = k.get_tenants(id_token=access_token)
+print(tenants)
 ```
 
-4. Initialize a Databricks API client using your Notebook context, and create a Genie Data Rooms environment for this Kobai tenant.
+Step 3: Authenticate with Kobai for the specific tenant using the IDM access token.
 
 ```python
-notebook_context = dbutils.notebook.entry_point.getDbutils().notebook().getContext()
-sql_warehouse = '8834d98a8agffa76'
+kobai_tenant_id = "5c1ba715-3961-4835-8a10-6f6f963b53ff"
+k.use_access_token(access_token = access_token, tenant_id=kobai_tenant_id)
+```
+
+At this point, authentication to the Kobai tenant is successfully completed.
+
+#### Authentication via browser token
 
-k.databricks_init_notebook(notebook_context, sql_warehouse)
-k.databricks_build_genie()
+```python
+k.use_browser_token(access_token="KOBAI_ACESS_TOKEN_FROM_BROWSER")
 ```
 
+#### Authentication via on-behalf-of flow
+The sample code demonstrating authentication via the on-behalf-of flow will be provided, if requested.
+
+
 ## AI Functionality
 The Kobai SDK enables users to ask follow-up questions based on the results of previous queries. This functionality currently supports models hosted on Databricks and Azure OpenAI. 
 
@@ -305,68 +317,41 @@ kobai_query_name = "Set ownership"
 question_json = k.run_question_remote(k.get_question_id(kobai_query_name)) # By questionName
 ```
 
-3. Ask a Follow-Up Question: Based on the initial results, you can ask a follow-up question using either Azure OpenAI, Databricks or a user-provided chat model.
-
-#### Using Azure OpenAI
-
-###### Authentication Methods:
-
-1. ApiKey
-
-```python
-from kobai import ai_query, llm_config
-import json
-
-followup_question = "Which owner owns the most sets?"
-
-llm_config = llm_config.LLMConfig(endpoint="https://kobaipoc.openai.azure.com/", api_key="YOUR_API_KEY", deployment="gpt-4o-mini", llm_provider="azure_openai")
-
-output = ai_query.followup_question(followup_question, json.dumps(question_json), kobai_query_name, llm_config=llm_config)
-print(output)
-```
-
-2. Azure Active Directory Authentication
+3. Ask a Follow-Up Question: Based on the initial results, you can ask a follow-up question using the user-provided chat and embedding model.
 
-Ensure that the logged-in tenant has access to Azure OpenAI.
-In case of databricks notebook, the logged in service principal should have access to Azure OpenAI.
+#### Using Databricks Embeddings and Chat Models in a Databricks Notebook
+Initialize the AI components by specifying the embedding and chat models, then proceed with follow-up questions for interactive engagement.
 
 ```python
-from kobai import ai_query, llm_config
+from databricks_langchain import DatabricksEmbeddings
+from langchain_community.chat_models import ChatDatabricks
 import json
 
-followup_question = "Which owner owns the most sets?"
-
-llm_config = llm_config.LLMConfig(endpoint="https://kobaipoc.openai.azure.com/", deployment="gpt-4o-mini", llm_provider="azure_openai")
-llm_config.get_azure_ad_token()
-
-output = ai_query.followup_question(followup_question, json.dumps(question_json), kobai_query_name, llm_config=llm_config)
-print(output)
-```
-
-#### Using Databricks (Default Configuration)
-
-```python
-from kobai import ai_query, llm_config
-import json
+# choose the embedding and chat model of your choice from the databricks serving and initialize.
+embedding_model = DatabricksEmbeddings(endpoint="databricks-bge-large-en")
+chat_model = ChatDatabricks(endpoint="databricks-gpt-oss-20b")
+k.init_ai_components(embedding_model=embedding_model, chat_model=chat_model)
 
 followup_question = "Which owner owns the most sets?"
-
-llm_config = llm_config.LLMConfig()
-
-output = ai_query.followup_question(followup_question, json.dumps(question_json), kobai_query_name, llm_config=llm_config)
+output = k.followup_question(followup_question, question_id=k.get_question_id(kobai_query_name))
 print(output)
 ```
 
-#### User Provided Chat Model
+#### Using Azure OpenAI Embeddings and Chat Models
 
 ```python
-from kobai import ai_query, llm_config
-import json
 from langchain_openai import AzureChatOpenAI
+from langchain_openai import AzureOpenAIEmbeddings
+import json
 
 followup_question = "Which owner owns the most sets?"
 
-llm_config = llm_config.LLMConfig(debug=True)
+embedding_model = AzureOpenAIEmbeddings(
+    model="text-embedding-3-small",
+    azure_endpoint="https://kobaipoc.openai.azure.com/",
+    api_key="YOUR_API_KEY",
+    openai_api_version="2023-05-15"
+)
 
 chat_model = AzureChatOpenAI(
 azure_endpoint="https://kobaipoc.openai.azure.com/", azure_deployment="gpt-4o-mini",
@@ -375,7 +360,10 @@ openai_api_version="2024-02-15-preview",
 temperature=0.5, 
 max_tokens=150,)
 
-output = ai_query.followup_question(followup_question, json.dumps(question_json), kobai_query_name, override_model=chat_model, llm_config=llm_config)
+k.init_ai_components(embedding_model=embedding_model, chat_model=chat_model)
+
+followup_question = "Which theme has the most sets?"
+output = k.followup_question(followup_question, question_id=k.get_question_id(kobai_query_name))
 print(output)
 ```
 

kobai_sdk-0.3.2.dist-info/RECORD

@@ -0,0 +1,14 @@
+kobai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kobai/ai_query.py,sha256=FnXn2pabJpXfTUcJvieVkAgMAjSTH9u5SFR9SJUJ-Lk,9556
+kobai/ai_rag.py,sha256=XUq_SnJw17P53Zk75hHJgTryGjHEAyYPwC0r2WtuNp4,14627
+kobai/databricks_client.py,sha256=fyqqMly2Qm0r1AHWsQjkYeNsDdH0G1JSgTkF9KJ55qA,2118
+kobai/demo_tenant_client.py,sha256=wlNc-bdI2wotRXo8ppUOalv4hYdBlek_WzJNARZV-AE,9293
+kobai/ms_authenticate.py,sha256=rlmhtvAaSRBlYmvIBy5epMVa4MBGBLPaMwawu1T_xDQ,2252
+kobai/spark_client.py,sha256=opM_F-4Ut5Hq5zZjWMuLvUps9sDULvyPNZHXGL8dW1k,776
+kobai/tenant_api.py,sha256=Q5yuFd9_V4lo3LWzvYEEO3LpDRWFgQD4TlRPXDTGbiE,4368
+kobai/tenant_client.py,sha256=w83NmLuOEyJjOVUuLva2vbq0zpGFzhi9LdSq1pKClA8,38613
+kobai_sdk-0.3.2.dist-info/licenses/LICENSE,sha256=QwcOLU5TJoTeUhuIXzhdCEEDDvorGiC6-3YTOl4TecE,11356
+kobai_sdk-0.3.2.dist-info/METADATA,sha256=7WIGEJBGHn2QIsYPLdbsnkwvtjqx3RJHZJR3kl0gu_M,19304
+kobai_sdk-0.3.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+kobai_sdk-0.3.2.dist-info/top_level.txt,sha256=ns1El3BrTTHKvoAgU1XtiSaVIudYeCXbEEUVY8HFDZ4,6
+kobai_sdk-0.3.2.dist-info/RECORD,,

kobai/mobi.py

@@ -1,682 +0,0 @@
-import requests
-import urllib.parse
-import json
-import base64
-from random import randrange
-from requests_toolbelt.multipart.encoder import MultipartEncoder
-
-from .mobi_config import MobiSettings
-
-##############################
-# Mobi Pull
-##############################
-
-def get_tenant(top_level_ontology_name, mobi_config: MobiSettings):
-    #Find Ontology Record
-
-    ont_record_id = _get_ont_record_by_name(top_level_ontology_name, mobi_config)
-    print("Mobi Ontology Record ID:", ont_record_id)
-    #Get Deprecated Nodes
-    
-    api_url = mobi_config.mobi_api_url + "/ontologies/" + urllib.parse.quote_plus(ont_record_id) + "/property-ranges"
-    response = requests.get(api_url, verify=False, auth=requests.auth.HTTPBasicAuth(mobi_config.mobi_username, mobi_config.mobi_password))
-
-    prop_ranges = response.json()["propertyToRanges"]
-
-
-    api_url = mobi_config.mobi_api_url + "/ontologies/" + urllib.parse.quote_plus(ont_record_id) + "/ontology-stuff"
-    response = requests.get(api_url, verify=False, timeout=5000, auth=requests.auth.HTTPBasicAuth(mobi_config.mobi_username, mobi_config.mobi_password))
-
-    ########################
-    # Deprecated Classes
-    ########################
-
-    deprecated = []
-
-    try:
-        resp_data = response.json()["iriList"]["deprecatedIris"]
-    except requests.exceptions.JSONDecodeError:
-        resp_data = []
-
-    for iri in resp_data:
-        deprecated.append(iri)
-
-    try:
-        resp_data = response.json()["importedIRIs"]
-    except requests.exceptions.JSONDecodeError:
-        resp_data = []
-
-    for o in resp_data:
-        for iri in o["deprecatedIris"]:
-            deprecated.append(iri)
-
-    ########################
-    # Properties
-    ########################
-
-    data_properties = []
-    object_properties = []
-
-    for p in response.json()["iriList"]["dataProperties"]:
-        data_properties.append(p)
-
-    for p in response.json()["iriList"]["objectProperties"]:
-        object_properties.append(p)
-
-    for o in response.json()["importedIRIs"]:
-        for p in o["dataProperties"]:
-            data_properties.append(p)
-
-    for o in response.json()["importedIRIs"]:
-        for p in o["objectProperties"]:
-            object_properties.append(p)
-
-    all_properties = data_properties + object_properties
-
-    ########################
-    # Classes and Domains
-    ########################
-
-    domains = {}
-    concepts = {}
-    prop_domains = {}
-
-    for ont in _get_classes_by_ont(ont_record_id, mobi_config):
-        for c in ont["classes"]:
-            if c not in deprecated:
-                d = _domain_from_uri(c, mobi_config)
-                c_lu = _fix_uri(c, "concept", mobi_config)
-            
-                if d not in domains:
-                    domains[d] = {"name": d, "concepts": [], "color": ""}
-
-                #Add Leaf Ontology Concepts
-                loc = _parent_uri_from_uri(c)
-                loc_lu = _fix_uri(loc, "concept", mobi_config)
-                if loc_lu not in concepts:
-                    name = _name_from_uri(loc, mobi_config)
-                    concepts[loc_lu] = {"label": name, "domainName": d, "name": name, "uri": loc_lu, "properties": [], "relations": [], "inheritedConcepts": []}
-
-                #Add Class Concepts
-                name = _name_from_uri(c, mobi_config)
-                concepts[c_lu] = {"label": name, "domainName": d, "name": name, "uri": c_lu, "properties": [], "relations": [], "inheritedConcepts": [loc_lu]}
-
-    try:
-        resp_data = response.json()["classToAssociatedProperties"]
-    except requests.exceptions.JSONDecodeError:
-        resp_data = {}
-
-    class_to_props = resp_data
-
-    props_with_domain = []
-    for c in class_to_props:
-        for p in class_to_props[c]:
-            props_with_domain.append(p)
-
-    #for p in resp_data:
-    for p in all_properties:
-        if p not in props_with_domain:
-            leaf_ont_concept = _parent_uri_from_uri(p)
-            if leaf_ont_concept not in class_to_props:
-                class_to_props[leaf_ont_concept] = []
-            class_to_props[leaf_ont_concept].append(p)
-    
-    for c in class_to_props:
-        if c not in deprecated:
-            for p in class_to_props[c]:
-                #loc_lu = _fix_uri(c, "concept", mobi_config)
-
-                if p in prop_ranges:
-                    range = prop_ranges[p][0]
-                    if range not in ["http://www.w3.org/2001/XMLSchema#string", "http://www.w3.org/2001/XMLSchema#number", "http://www.w3.org/2001/XMLSchema#boolean", "http://www.w3.org/2001/XMLSchema#dateTime"]:
-                        range = "http://www.w3.org/2001/XMLSchema#string"
-                else:
-                    range = "http://www.w3.org/2001/XMLSchema#string"
-                
-                #range_lu = _fix_uri(prop_ranges[p][0], "concept", mobi_config)
-
-                #if p in prop_domains:
-                    #for dc in prop_domains[p]:
-                #cp =  dc + "/" + _label_from_uri(p)
-                cp =  c + "/" + _label_from_uri(p)
-                #dc_lu = _fix_uri(dc, "concept", mobi_config)
-                dc_lu = _fix_uri(c, "concept", mobi_config)
-                if p in data_properties:
-                    prop = {"label": _label_from_uri(p), "uri": _fix_uri(cp, "prop", mobi_config), "conceptUri": dc_lu, "propTypeUri": range, "dataClassTags": []}
-                    if dc_lu in concepts:
-                        if prop not in concepts[dc_lu]["properties"]:
-                            concepts[dc_lu]["properties"].append(prop)
-                if p in object_properties:
-                    if p in prop_ranges:
-                        range_lu = _fix_uri(prop_ranges[p][0], "concept", mobi_config)
-                        prop = {"label": _label_from_uri(p), "uri": _fix_uri(cp, "prop", mobi_config), "conceptUri": dc_lu, "relationTypeUri": range_lu, "dataClassTags": []}
-                        if dc_lu in concepts:
-                            if range_lu in concepts:
-                                if prop not in concepts[dc_lu]["relations"]:
-                                    concepts[dc_lu]["relations"].append(prop)
-                    else:
-                        print("PROPERTY RANGE MISSING", p)
-
-    try:
-        resp_data = response.json()["classHierarchy"]["childMap"]
-    except requests.exceptions.JSONDecodeError:
-        resp_data = {}                           
-
-    for c in resp_data:
-        c_lu = _fix_uri(c, "concept", mobi_config)
-        for pc in resp_data[c]:
-            pc_lu = _fix_uri(pc, "concept", mobi_config)
-            if c not in deprecated:
-                if c_lu in concepts:
-                    concepts[c_lu]["inheritedConcepts"].append(pc_lu)
-                else:
-                    print("RELATION TARGET MISSING", c_lu)
-
-    empty_leaf_concepts = []
-    for c in concepts:
-        if c.split("#")[1][0] == "_":
-            if len(concepts[c]["properties"]) == 0 and len(concepts[c]["relations"]) == 0:
-                empty_leaf_concepts.append(c)
-                for cc in concepts:
-                    if c in concepts[cc]["inheritedConcepts"]:
-                        concepts[cc]["inheritedConcepts"].remove(c)
-            else:
-                print("KEEPING LEAF ONTOLOGY", c)
-    for c in empty_leaf_concepts:
-        print("REMOVING LEAF ONTOLOGY", c)
-        del concepts[c]
-
-    tenant = {"solutionId": 0, "model": {"name": "AssetModel", "uri": "http://kobai/" + mobi_config.default_tenant_id + "/AssetModel"}, "tenantId": mobi_config.default_tenant_id, "domains": []}
-    tenant_encoded = {"solutionId": 0, "model": {"name": "AssetModel", "uri": "http://kobai/" + mobi_config.default_tenant_id + "/AssetModel"}, "tenantId": mobi_config.default_tenant_id, "domains": []}
-    _add_empty_tenant_metadata(tenant)
-    _add_empty_tenant_metadata(tenant_encoded)
-
-    di = 0
-    for dk, d in domains.items():
-        d['id'] = di
-        d['color'] = "#" + str(randrange(222222, 888888))
-        d_encoded = {}
-        d_encoded['id'] = di
-        d_encoded['color'] = "#" + str(randrange(222222, 888888))
-        d_encoded['name'] = dk
-
-        for _, c in concepts.items():
-            if dk == c['domainName']:
-                cprime = {"uri": c['uri'], "label": c['label'], "relations": c['relations'], "properties": c['properties'], "inheritedConcepts": c['inheritedConcepts']}
-                d['concepts'].append(cprime)
-        encodedConcepts = base64.b64encode(json.dumps(d['concepts']).encode('ascii')).decode('ascii')
-        d_encoded['concepts'] = encodedConcepts
-        tenant['domains'].append(d)
-        tenant_encoded['domains'].append(d_encoded)
-        di += 1
-
-    return tenant, tenant_encoded
-
-def _get_classes_by_ont(ont_record_id, mobi_config):
-    api_url = mobi_config.mobi_api_url + "/ontologies/" + urllib.parse.quote_plus(ont_record_id) + "/imported-classes"
-    response = requests.get(api_url, verify=False, timeout=5000, auth=requests.auth.HTTPBasicAuth(mobi_config.mobi_username, mobi_config.mobi_password))
-
-    data = []
-    try:
-        resp_data = response.json()
-    except requests.exceptions.JSONDecodeError:
-        resp_data = []
-
-    #for ont in response.json():
-    for ont in resp_data:
-        record = {}
-        record["id"] = _trim_trailing_slash(ont["id"])
-        record["classes"] = []
-        for c in ont["classes"]:
-            record["classes"].append(c)
-        data.append(record)
-
-    api_url = mobi_config.mobi_api_url + "/ontologies/" + urllib.parse.quote_plus(ont_record_id) + "/classes"
-    response = requests.get(api_url, verify=False, timeout=5000, auth=requests.auth.HTTPBasicAuth(mobi_config.mobi_username, mobi_config.mobi_password))
-
-    try:
-        resp_data = response.json()
-    except requests.exceptions.JSONDecodeError:
-        resp_data = []
-
-    record = {}
-    if len(resp_data) == 0:
-        return data
-    record["id"] = _parent_uri_from_uri(_trim_trailing_slash(response.json()[0]["@id"]))
-    record["classes"] = []
-
-    for c in resp_data:
-        record["classes"].append(c["@id"])
-    data.append(record)
-
-    return data
-
-def _get_ont_record_by_name(name, mobi_config):
-    api_url = mobi_config.mobi_api_url + "/catalogs/" + urllib.parse.quote_plus(mobi_config.catalog_name) + "/records"
-    response = requests.get(api_url, verify=False, timeout=5000, auth=requests.auth.HTTPBasicAuth(mobi_config.mobi_username, mobi_config.mobi_password))
-    
-    ont_record_id = ""
-    for r in response.json():
-        if r["http://purl.org/dc/terms/title"][0]["@value"] == name:
-            ont_record_id = r["@id"]
-    return ont_record_id
-
-def _get_ont_record_by_url(url, mobi_config):
-    api_url = mobi_config.mobi_api_url + "/catalogs/" + urllib.parse.quote_plus(mobi_config.catalog_name) + "/records"
-    response = requests.get(api_url, verify=False, timeout=5000, auth=requests.auth.HTTPBasicAuth(mobi_config.mobi_username, mobi_config.mobi_password))
-
-    ont_record_id = ""
-    for r in response.json():
-        for u in r["http://mobi.com/ontologies/ontology-editor#ontologyIRI"]:
-            if url == _trim_trailing_slash(u["@id"]):
-                ont_record_id = r["@id"]
-    return ont_record_id
-
-def _add_empty_tenant_metadata(tenant):
-    tenant["dataAccessTags"] = []
-    tenant["conceptAccessTags"] = []
-    tenant["dataSources"] = []
-    tenant["dataSets"] = []
-    tenant["collections"] = []
-    tenant["visualizations"] = []
-    tenant["queries"] = []
-    tenant["mappingDefs"] = []
-    tenant["dataSourceFileKeys"] = []
-    tenant["apiQueryProfiles"] = []
-    tenant["collectionVizs"] = []
-    tenant["collectionVizOrders"] = []
-    tenant["queryDataTags"] = []
-    tenant["queryCalcs"] = []
-    tenant["dataSourceSettings"] = []
-    tenant["publishedAPIs"] = []
-    tenant["scenarios"] = []
-
-##############################
-# Mobi Replace
-##############################
-
-def replace_tenant_to_mobi(kobai_tenant, top_level_ontology, mobi_config: MobiSettings):
-    json_ld = _create_jsonld(kobai_tenant, top_level_ontology)
-    _post_model(json_ld, top_level_ontology, mobi_config)
-
-def replace_tenant_to_file(kobai_tenant, top_level_ontology):
-    return _create_jsonld(kobai_tenant, top_level_ontology)
-
-def _create_jsonld(kobai_tenant, top_level_ontology):
-    output_json = []
-    uri = kobai_tenant["model"]["uri"]
-    uri = uri.replace("AssetModel", top_level_ontology)
-
-    group = {
-        "@id": uri,
-        "@type": ["http://www.w3.org/2002/07/owl#Ontology"],
-        "http://purl.org/dc/terms/description": [{"@value": "This model was exported from Kobai."}],
-        "http://purl.org/dc/terms/title": [{"@value": top_level_ontology}]
-    }
-    output_json.append(group)
-
-
-    for dom in kobai_tenant["domains"]:
-        for con in dom["concepts"]:
-
-            group = {
-                "@id": con["uri"].replace("AssetModel", top_level_ontology),
-                "@type": ["http://www.w3.org/2002/07/owl#Class"],
-                "http://purl.org/dc/terms/title": [{"@value": con["label"]}]
-            }
-            if len(con["inheritedConcepts"]) > 0:
-                group["http://www.w3.org/2000/01/rdf-schema#subClassOf"] = []
-                for parent in con["inheritedConcepts"]:
-                    group["http://www.w3.org/2000/01/rdf-schema#subClassOf"].append(
-                        {"@id": parent.replace("AssetModel", top_level_ontology)}
-                    )
-            output_json.append(group)
-
-            for prop in con["properties"]:
-                group = {
-                    "@id": prop["uri"].replace("AssetModel", top_level_ontology),
-                    "@type": ["http://www.w3.org/2002/07/owl#DatatypeProperty"],
-                    "http://purl.org/dc/terms/title": [{"@value": prop["label"]}],
-                    "http://www.w3.org/2000/01/rdf-schema#domain": [{"@id": con["uri"].replace("AssetModel", top_level_ontology)}],
-                    "http://www.w3.org/2000/01/rdf-schema#range": [{"@id": prop["propTypeUri"]}]
-                }
-                output_json.append(group)
-
-            for rel in con["relations"]:
-                group = {
-                    "@id": rel["uri"].replace("AssetModel", top_level_ontology),
-                    "@type": ["http://www.w3.org/2002/07/owl#ObjectProperty"],
-                    "http://purl.org/dc/terms/title": [{"@value": rel["label"]}],
-                    "http://www.w3.org/2000/01/rdf-schema#domain": [{"@id": con["uri"].replace("AssetModel", top_level_ontology)}],
-                    "http://www.w3.org/2000/01/rdf-schema#range": [{"@id": rel["relationTypeUri"].replace("AssetModel", top_level_ontology)}]
-                }
-                output_json.append(group)
-    return output_json
-
-def _post_model(tenant_json, top_level_ontology, mobi_config):
-
-    mp = MultipartEncoder(fields={
-            "title": top_level_ontology, 
-            "description": "This model was exported from Kobai.",
-            "json": json.dumps(tenant_json)
-            })
-    h = {"Content-type": mp.content_type}
-
-    api_url = mobi_config.mobi_api_url + "/ontologies"
-    response = requests.post(
-        api_url, 
-        headers = h,
-        data = mp,
-        verify=False, 
-        timeout=5000, 
-        auth=requests.auth.HTTPBasicAuth(mobi_config.mobi_username, mobi_config.mobi_password)
-        )
-    print("Upload Status", response.status_code)
-    if response.status_code != 201:
-        print(response.text)
-
-##############################
-# Mobi Update
-##############################
-
-def update_tenant(kobai_tenant, top_level_ontology_name, mobi_config: MobiSettings):
-    record_id = _get_ont_record_by_name(top_level_ontology_name, mobi_config)
-
-    api_url = mobi_config.mobi_api_url + "/catalogs/" + urllib.parse.quote_plus(mobi_config.catalog_name) + "/records/" + urllib.parse.quote_plus(record_id) + "/branches"
-    response = requests.get(api_url, verify=False, timeout=5000, auth=requests.auth.HTTPBasicAuth(mobi_config.mobi_username, mobi_config.mobi_password))
-
-    classes = _get_classes_by_ont(record_id, mobi_config)
-    ontology_by_class = {}
-    for o in classes:
-        for c in o["classes"]:
-            ontology_by_class[c] = o["id"]
-
-    _, mobi_tenant = get_tenant(top_level_ontology_name, mobi_config)
-
-    change_json = _compare_tenants(kobai_tenant, mobi_tenant, classes, mobi_config)
-
-    #################################
-    # Apply changes with Mobi API calls
-    #################################
-
-    for o in change_json:
-        if not change_json[o]["changed"]:
-            continue
-
-        ont_record_id = _get_ont_record_by_url(o, mobi_config)
-        if ont_record_id == "":
-            continue
-        
-        branch_id = _get_or_create_branch_by_record(ont_record_id, "kobai_dev", mobi_config)
-        master_branch_id = _get_or_create_branch_by_record(ont_record_id, "MASTER", mobi_config)
-        
-        for change in change_json[o]["class"]:
-            _stage_changes([change["mobi"]], ont_record_id, mobi_config)
-            _commit_changes("Kobai added class " + change["mobi"]["http://purl.org/dc/terms/title"][0]["@value"], ont_record_id, branch_id, mobi_config)
-        for change in change_json[o]["property"]:
-            _stage_changes([change["mobi"]], ont_record_id, mobi_config)
-            _commit_changes("Kobai added property " + change["mobi"]["http://purl.org/dc/terms/title"][0]["@value"], ont_record_id, branch_id, mobi_config)
-
-        api_url = mobi_config.mobi_api_url + "/merge-requests"
-        pd = {"title": "Kobai Change from kobai-dev to master", "recordId": ont_record_id, "sourceBranchId": branch_id, "targetBranchId": master_branch_id, "assignees": ["admin"], "removeSource": "true"}
-        response = requests.post(api_url, verify=False, timeout=5000, params=pd, auth=requests.auth.HTTPBasicAuth(mobi_config.mobi_username, mobi_config.mobi_password))
-        #print(response.status_code)
-
-def _compare_tenants(kobai_tenant, mobi_tenant, classes, mobi_config):
-    existing_concepts = []
-    existing_relations = {}
-    existing_properties = {}
-
-    for dom in mobi_tenant["domains"]:
-        conText = base64.b64decode(dom['concepts']).decode('UTF-8')
-        cons = json.loads(conText)
-        for con in cons:
-            existing_concepts.append(con["uri"])
-            existing_properties[con["uri"]] = []
-            for prop in con["properties"]:
-                existing_properties[con["uri"]].append(prop["uri"])
-            existing_relations[con["uri"]] = []
-            for rel in con["relations"]:
-                existing_relations[con["uri"]].append(rel["uri"])
-
-    new_concepts = []
-    new_relations = {}
-    new_properties = {}
-
-    tenantId = kobai_tenant["tenantId"]
-    for dom in kobai_tenant["domains"]:
-        conText = base64.b64decode(dom['concepts']).decode('UTF-8')
-        cons = json.loads(conText)
-        for con in cons:
-            con_d = con["uri"].replace(tenantId, mobi_config.default_tenant_id)
-            if con_d not in existing_concepts:
-                print("New Class Detected")
-                new_concepts.append(con)
-            for prop in con["properties"]:
-                prop_d = prop["uri"].replace(tenantId, mobi_config.default_tenant_id)
-                if con_d in existing_properties:
-                    if prop_d not in existing_properties[con_d]:
-                        print("New Prop Detected")
-                        if con_d not in new_properties:
-                            new_properties[con_d] = []
-                        new_properties[con_d].append(prop)
-                        print(prop)
-                else:
-                    print("New Property due to New Concept")
-            for rel in con["relations"]:
-                rel_d = rel["uri"].replace(tenantId, mobi_config.default_tenant_id)
-                if con_d in existing_relations:
-                    if rel_d not in existing_relations[con_d]:
-                        print("New Rel Detected")
-                        if con_d not in new_relations:
-                            new_relations[con_d] = []
-                            new_relations[con_d].append(rel)
-                else:
-                    print("New Relation due to New Concept")
-    
-    change_json = {}
-    for o in classes:
-        ont_exist = o["id"]
-        change_json[ont_exist] = {}
-        change_json[ont_exist]["exists"] = True
-        change_json[ont_exist]["changed"] = False
-        change_json[ont_exist]["class"] = []
-        change_json[ont_exist]["property"] = []
-        change_json[ont_exist]["relation"] = []
-
-    #################################
-    # Identify and capture changes associated to Mobi ontology
-    #################################
-    for c in new_concepts:
-        c_d = c["uri"].replace(tenantId, mobi_config.default_tenant_id)
-        ont_sig = c_d.replace("http://kobai/" + mobi_config.default_tenant_id + "/AssetModel/", "").replace("#", "/").replace("_", "/")
-        ont_sig = "/".join(ont_sig.split("/")[:-1])
-        ont = ""
-        for o in classes:
-            ont_exist = o["id"]
-            if ont_sig == _get_ont_sig_from_ont(ont_exist, len(ont_sig.split("/"))):
-                change_json[ont_exist]["class"].append({"type": "new", "kobai": c, "mobi": {}})
-
-    for c in new_properties:
-        for p in new_properties[c]:
-            ont_sig = _get_ont_sig_from_concept(tenantId, c, mobi_config)
-            for o in classes:
-                ont_exist = o["id"]
-                if ont_sig == _get_ont_sig_from_ont(ont_exist, len(ont_sig.split("/"))):
-                    change_json[ont_exist]["property"].append({"type": "new", "kobai": p, "mobi": {}})
-
-    for c in new_relations:
-        for r in new_properties[c]:
-            ont_sig = _get_ont_sig_from_concept(tenantId, c, mobi_config)
-            for o in classes:
-                ont_exist = o["id"]
-                if ont_sig == _get_ont_sig_from_ont(ont_exist, len(ont_sig.split("/"))):
-                    change_json[ont_exist]["relation"].append({"type": "new", "kobai": r, "mobi": {}})      
-
-    #################################
-    # Generate Mobi json for every change
-    #################################   
-    for ont in change_json:
-        changed = False
-        for i, change in enumerate(change_json[ont]["class"]):
-            c = change["kobai"]
-            c_json = {}
-            c_json["@id"] = ont + "/" + c["label"].split("_")[-1]
-            c_json["@type"] = [ "http://www.w3.org/2002/07/owl#Class" ]
-            c_json["http://www.w3.org/2000/01/rdf-schema#label"] = [{"@value": c["label"].split("_")[-1]}]
-            c_json["http://purl.org/dc/terms/title"] = [{"@value": c["label"].split("_")[-1]}]
-            c_json["http://www.w3.org/2000/01/rdf-schema#subClassOf"] = []
-            #c_json["http://www.w3.org/2002/07/owl#deprecated"] = [{"@value": "true", "@type": "http://www.w3.org/2001/XMLSchema#boolean"}]
-            for pc in c["inheritedConcepts"]:
-                c_json["http://www.w3.org/2000/01/rdf-schema#subClassOf"].append(pc)
-            change_json[ont]["class"][i]["mobi"] = c_json
-            changed = True
-
-        for i, change in enumerate(change_json[ont]["property"]):
-            p = change["kobai"]
-            p_json = {}
-            p_json["@id"] = ont + "/" + p["label"]
-            p_json["@type"] = [ "http://www.w3.org/2002/07/owl#Class" ]
-            p_json["http://www.w3.org/2000/01/rdf-schema#label"] = [{"@value": p["label"]}]
-            p_json["http://purl.org/dc/terms/title"] = [{"@value": p["label"]}]
-            p_json["http://www.w3.org/2000/01/rdf-schema#domain"] = [{"@id": ont + "/" + _get_concept_name_from_prop_uri(p["uri"])}]
-            p_json["http://www.w3.org/2000/01/rdf-schema#range"] = [{"@id": p["propTypeUri"]}]
-            change_json[ont]["property"][i]["mobi"] = p_json
-            changed = True
-
-        if changed is True:
-            change_json[ont]["changed"] = True
-
-    return change_json
-
-def _stage_changes(changes, ont_record_id, mobi_config):
-    api_url = mobi_config.mobi_api_url + "/catalogs/" + urllib.parse.quote_plus(mobi_config.catalog_name) + "/records/" + urllib.parse.quote_plus(ont_record_id) + "/in-progress-commit"
-    response = requests.delete(api_url, verify=False, timeout=5000, auth=requests.auth.HTTPBasicAuth(mobi_config.mobi_username, mobi_config.mobi_password))
-
-    api_url = mobi_config.mobi_api_url + "/catalogs/" + urllib.parse.quote_plus(mobi_config.catalog_name) + "/records/" + urllib.parse.quote_plus(ont_record_id) + "/in-progress-commit"
-    m = MultipartEncoder(fields={"additions": json.dumps(changes), "deletions": "[]"})
-    h = {"Content-type": m.content_type}
-    response = requests.put(api_url, verify=False, timeout=5000, data=m, headers=h, auth=requests.auth.HTTPBasicAuth(mobi_config.mobi_username, mobi_config.mobi_password))
-
-    api_url = mobi_config.mobi_api_url + "/catalogs/" + urllib.parse.quote_plus(mobi_config.catalog_name) + "/records/" + urllib.parse.quote_plus(ont_record_id) + "/in-progress-commit"
-    response = requests.get(api_url, verify=False, timeout=5000, auth=requests.auth.HTTPBasicAuth(mobi_config.mobi_username, mobi_config.mobi_password))
-
-def _commit_changes(message, ont_record_id, branch_id, mobi_config):
-    api_url = mobi_config.mobi_api_url + "/catalogs/" + urllib.parse.quote_plus(mobi_config.catalog_name) + "/records/" + urllib.parse.quote_plus(ont_record_id) + "/branches/" + urllib.parse.quote_plus(branch_id) + "/commits"
-    pd = {"message": message}
-    response = requests.post(api_url, verify=False, timeout=5000, params=pd, auth=requests.auth.HTTPBasicAuth(mobi_config.mobi_username, mobi_config.mobi_password))
-
-##############################
-# Mobi Branch
-##############################
-
-#def jprint(data):
-#    json_str = json.dumps(data, indent=4)
-
-def _get_branches_by_record(id, mobi_config):
-    api_url = mobi_config.mobi_api_url + "/catalogs/" + urllib.parse.quote_plus(mobi_config.catalog_name) + "/records/" + urllib.parse.quote_plus(id) + "/branches"
-    response = requests.get(api_url, verify=False, timeout=5000, auth=requests.auth.HTTPBasicAuth(mobi_config.mobi_username, mobi_config.mobi_password))
-    return response.json()
-
-def _get_or_create_branch_by_record(id, name, mobi_config):
-    branches = _get_branches_by_record(id, mobi_config)
-    for b in branches:
-        if b["http://purl.org/dc/terms/title"][0]["@value"] == name:
-            return b["@id"]
-
-    commit = ""
-    for b in branches:
-        if b["http://purl.org/dc/terms/title"][0]["@value"] == "MASTER":
-            commit = b["http://mobi.com/ontologies/catalog#head"][0]["@id"]
-        
-    api_url = mobi_config.mobi_api_url + "/catalogs/" + urllib.parse.quote_plus(mobi_config.catalog_name) + "/records/" + urllib.parse.quote_plus(id) + "/branches"
-    pd = {"type": "http://mobi.com/ontologies/catalog#Branch", "title": name, "commitId": commit}
-    requests.post(api_url, verify=False, timeout=5000, params=pd, auth=requests.auth.HTTPBasicAuth(mobi_config.mobi_username, mobi_config.mobi_password))
-    
-    branches = _get_branches_by_record(id, mobi_config)
-    for b in branches:
-        if b["http://purl.org/dc/terms/title"][0]["@value"] == name:
-            return b["@id"]
-    return ""
-
-##############################
-# Mobi Parse
-##############################
-def _get_domain_range(url, mobi_config):
-    for d, r in mobi_config.domain_extraction.items():
-        if d in url:
-            return r
-    return {"min": 0, "max": 0}
-
-def _parent_uri_from_uri(uri):
-    #return "/".join(uri.split("/")[:-1])
-    return "/".join(_uri_split(uri)[:-1])
-
-def _trim_trailing_slash(uri):
-    if uri[-1] == "/":
-        return uri[:-1]
-    else:
-        return uri
-
-def _uri_split(uri):
-    uri = uri.replace("#", "/")
-    return uri.split("/")
-
-
-################################
-# Transform from Kobai to Mobi
-################################
-
-def _get_ont_sig_from_concept(tenantId, uri, mobi_config):
-    uri = uri.replace(tenantId, mobi_config.default_tenant_id)
-    ont_sig = uri.replace("http://kobai/" + mobi_config.default_tenant_id + "/AssetModel/", "").replace("#", "/").replace("_", "/")
-    ont_sig = "/".join(ont_sig.split("/")[:-1])
-    return ont_sig
-
-def _get_ont_sig_from_ont(uri, length):
-    return "/".join(uri.split("/")[-length:])
-
-def _get_concept_name_from_prop_uri(uri):
-    return uri.split("#")[0].split("/")[-1]
-    #return uri.split("#")[0].split("_")[-1]
-
-################################
-# Transform from Mobi to Kobai
-################################
-
-def _domain_from_uri(uri, mobi_config):
-    #domain = "_".join(uri.split("/")[_get_domain_range(uri, mobi_config)['min']:_get_domain_range(uri, mobi_config)['max']+1])
-    domain = "_".join(_uri_split(uri)[_get_domain_range(uri, mobi_config)['min']:_get_domain_range(uri, mobi_config)['max']+1])
-    return domain
-
-def _name_from_uri(uri, mobi_config):
-    #name = "_".join(uri.split("/")[_get_domain_range(uri, mobi_config)['max']+1:])
-    name = "_".join(_uri_split(uri)[_get_domain_range(uri, mobi_config)['max']+1:])
-    if name == "":
-        #name = "_" + "_".join(uri.split("/")[_get_domain_range(uri, mobi_config)['max']:])
-        name = "_" + "_".join(_uri_split(uri)[_get_domain_range(uri, mobi_config)['max']:])
-    return name
-
-def _label_from_uri(uri):
-    #return uri.split("/")[-1]
-    return _uri_split(uri)[-1]
-
-def _fix_uri(uri, type, mobi_config):
-    domain = _domain_from_uri(uri, mobi_config)
-    name = _name_from_uri(uri, mobi_config)
-
-    top = "/".join(uri.split("/")[0:_get_domain_range(uri, mobi_config)['min']])
-    
-    if type == "concept":
-        uri = domain + "#" + name
-    elif type == "prop":
-        uri = domain + "/" + "_".join(name.split("_")[0:-1]) + "#" + name.split("_")[-1]
-
-    for d in mobi_config.domain_extraction:
-        
-        if d in top:
-            uri = "http://kobai/" + mobi_config.default_tenant_id + "/AssetModel/" + uri
-    
-    return uri
-
-

kobai/mobi_config.py

@@ -1,16 +0,0 @@
-from pydantic_settings import BaseSettings
-
-class MobiSettings(BaseSettings):
-
-    #Application Specific Settings
-    domain_extraction: dict = {}
-
-    #Mobi Server Settings
-    mobi_api_url: str = "https://localhost:8443/mobirest"
-    mobi_username: str = "admin"
-    mobi_password: str = "admin"
-    
-    catalog_name: str = "http://mobi.com/catalog-local"
-    default_tenant_id: str = "00000000-0000-0000-0000-000000000000"
-
-#settings = MobiSettings()

kobai_sdk-0.3.0rc2.dist-info/RECORD

@@ -1,16 +0,0 @@
-kobai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-kobai/ai_query.py,sha256=xZh_OyakU01gIrnzaW4v_TdfzG51nPu0ntXJw1WEnvw,9424
-kobai/ai_rag.py,sha256=8B3HM4GoGVrgxJG678NN4vGaDwZRYnQiK5SCGiMIYkM,15186
-kobai/databricks_client.py,sha256=fyqqMly2Qm0r1AHWsQjkYeNsDdH0G1JSgTkF9KJ55qA,2118
-kobai/demo_tenant_client.py,sha256=wlNc-bdI2wotRXo8ppUOalv4hYdBlek_WzJNARZV-AE,9293
-kobai/mobi.py,sha256=FKIyVcmDoQetH00Hg9ajOPmO029IGpL1sttgwvB8-Pc,29862
-kobai/mobi_config.py,sha256=BpW1cn7BgF5iTYz_bB0HMpXflfql0PYlQ61Y_Uh1Vns,454
-kobai/ms_authenticate.py,sha256=rlmhtvAaSRBlYmvIBy5epMVa4MBGBLPaMwawu1T_xDQ,2252
-kobai/spark_client.py,sha256=opM_F-4Ut5Hq5zZjWMuLvUps9sDULvyPNZHXGL8dW1k,776
-kobai/tenant_api.py,sha256=Q5yuFd9_V4lo3LWzvYEEO3LpDRWFgQD4TlRPXDTGbiE,4368
-kobai/tenant_client.py,sha256=Zb9XKOM23u311nbnBaB8JQ72nrPVA7LyOmMn526rC7U,43870
-kobai_sdk-0.3.0rc2.dist-info/licenses/LICENSE,sha256=QwcOLU5TJoTeUhuIXzhdCEEDDvorGiC6-3YTOl4TecE,11356
-kobai_sdk-0.3.0rc2.dist-info/METADATA,sha256=g-g_YgrjB32fVx_gsE9uPpmZXm2B6iBMehsVycgAj7o,19263
-kobai_sdk-0.3.0rc2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-kobai_sdk-0.3.0rc2.dist-info/top_level.txt,sha256=ns1El3BrTTHKvoAgU1XtiSaVIudYeCXbEEUVY8HFDZ4,6
-kobai_sdk-0.3.0rc2.dist-info/RECORD,,