mengzhx/semantica
1
0
Fork 0
mirror of https://github.com/semantica-agi/semantica.git synced 2026-08-29 04:26:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add high-performance VectorStore ingestion and docs

Browse Source
This commit is contained in:
KaifAhmad1
2026-01-19 13:32:16 +05:30
parent f6c9d50e03
commit 1568237ce7
6 changed files with 429 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cookbook/use_cases/finance/03_Earnings_Call_Analysis.ipynb
+9 -11
View File
@@ -915,23 +915,21 @@
"metadata": {},
"outputs": [],
"source": [
"from semantica.vector_store import VectorStore \n",
"from semantica.context import ContextRetriever \n",
"import numpy as np\n",
"from semantica.vector_store import VectorStore\n",
"from semantica.context import ContextRetriever\n",
"\n",
"# Initialize vector store (dimension should match your embedder; default is 768)\n",
"vector_store = VectorStore(backend=\"faiss\", dimension=768)\n",
"\n",
"# 1) Embed the full transcript\n",
"embedding = vector_store.embed(parsed_doc[\"full_text\"])\n",
"documents = [parsed_doc[\"full_text\"]]\n",
"metadata = [{\"source\": \"earnings_call\", \"type\": \"transcript\"}]\n",
"\n",
"# 2) Store the embedding + metadata\n",
"vector_store.store(\n",
" vectors=[embedding],\n",
" metadata=[{\"source\": \"earnings_call\", \"type\": \"transcript\"}],\n",
"vector_ids = vector_store.add_documents(\n",
" documents=documents,\n",
" metadata=metadata,\n",
" batch_size=32,\n",
" parallel=True,\n",
")\n",
"\n",
"# 3) Configure the context retriever as before\n",
"context_retriever = ContextRetriever(\n",
" knowledge_graph=knowledge_graph,\n",
" vector_store=vector_store,\n",