kobai-sdk 0.2.8rc10__tar.gz → 0.2.8rc12__tar.gz

{kobai_sdk-0.2.8rc10 → kobai_sdk-0.2.8rc12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: kobai-sdk
-Version: 0.2.8rc10
+Version: 0.2.8rc12
 Summary: A package that enables interaction with a Kobai tenant.
 Author-email: Ryan Oattes <ryan@kobai.io>
 License:                                  Apache License

{kobai_sdk-0.2.8rc10 → kobai_sdk-0.2.8rc12}/kobai/ai_rag.py

@@ -143,7 +143,7 @@ def __generate_sentences_from_questions(tc: AIContext, debug):
     ss.sql(full_sql)
 
 
-def encode_to_delta_local(tc: AIContext, st_model: SentenceTransformer, replica_schema=None):
+def encode_to_delta_local(tc: AIContext, st_model: Union[SentenceTransformer, Embeddings], replica_schema=None, batch_size=100000):
     """
     Encode Semantic Data to Vectors in Delta Table
 
@@ -163,7 +163,7 @@ def encode_to_delta_local(tc: AIContext, st_model: SentenceTransformer, replica_
     sentences_df = ss.sql(sentences_sql)
 
     num_records = sentences_df.count()
-    query_batch_size = 100000
+    query_batch_size = batch_size
 
     for x in range(0, num_records, query_batch_size):
         print(f"Running Batch Starting at {x}")
@@ -172,15 +172,22 @@ def encode_to_delta_local(tc: AIContext, st_model: SentenceTransformer, replica_
         content_list = [r["content"] for r in sentences_df.collect()]
         id_list = [r["id"] for r in sentences_df.collect()]
 
-        vector_list = st_model.encode(
-            content_list, normalize_embeddings=True, show_progress_bar=True)
+        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[i] = [float(x) for x in v]
+        #vector_list = st_model.encode(
+        #    content_list, normalize_embeddings=True, show_progress_bar=True)
 
         schema_v = StructType([
             StructField("id", IntegerType(), True),
             StructField("vector", ArrayType(FloatType()), False)
         ])
 
-        updated_list = [[r[0], r[1].tolist()]
+        updated_list = [[r[0], r[1]]
                         for r in zip(id_list, vector_list)]
         updated_df = ss.createDataFrame(updated_list, schema_v)
 

{kobai_sdk-0.2.8rc10 → kobai_sdk-0.2.8rc12}/kobai/tenant_client.py

@@ -451,7 +451,7 @@ 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: SentenceTransformer, replica_schema=None):
+    def rag_encode_to_delta_local(self, st_model: Union[SentenceTransformer, Embeddings], replica_schema=None, batch_size=100000):
         """
         Encode Semantic Data to Vectors in Delta Table
 
@@ -459,7 +459,7 @@ class TenantClient:
         st_model (SentenceTransformer): A sentence_transformers 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.
         """
-        ai_rag.encode_to_delta_local(self.get_ai_context(), st_model=st_model, replica_schema=replica_schema)
+        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):
         """

{kobai_sdk-0.2.8rc10 → kobai_sdk-0.2.8rc12}/kobai_sdk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: kobai-sdk
-Version: 0.2.8rc10
+Version: 0.2.8rc12
 Summary: A package that enables interaction with a Kobai tenant.
 Author-email: Ryan Oattes <ryan@kobai.io>
 License:                                  Apache License

{kobai_sdk-0.2.8rc10 → kobai_sdk-0.2.8rc12}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "kobai-sdk"
-version = "0.2.8rc10"
+version = "0.2.8rc12"
 description = "A package that enables interaction with a Kobai tenant."
 readme = "README.md"
 authors = [{ name = "Ryan Oattes", email = "ryan@kobai.io" }]