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

Remove hardcoded API keys and finalize Colab badges in notebooks

Browse Source
This commit is contained in:
KaifAhmad1
2025-12-22 22:11:08 +05:30
parent e92bf0e872
commit 323a788288
2 changed files with 57 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cookbook/use_cases/advanced_rag/01_GraphRAG_Complete.ipynb
+53 -49
View File
@@ -5,6 +5,8 @@
"id": "9570d208",
"metadata": {},
"source": [
"[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Hawksight-AI/semantica/blob/main/cookbook/use_cases/advanced_rag/01_GraphRAG_Complete.ipynb)\n",
"\n",
"# 🧪 GraphRAG: Skincare Intelligence System\n",
"## 📖 Overview\n",
"\n",
@@ -27,55 +29,57 @@
"metadata": {},
"outputs": [],
"source": [
"# Install dependencies\n",
"!pip install -qU semantica networkx matplotlib plotly pandas faiss-cpu beautifulsoup4 groq"
]
},
{
"cell_type": "markdown",
"id": "b7a767b5",
"metadata": {},
"source": [
"## 🛠️ Phase 0: Environment & Foundation\n",
"We configure **Groq** as our primary LLM provider and seed the system with verified \"Ground Truth\" data."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6840539f",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import json\n",
"import pandas as pd\n",
"from semantica.core import Semantica, ConfigManager\n",
"from semantica.seed import SeedDataManager\n",
"from semantica.vector_store import VectorStore\n",
"\n",
"# 1. Groq Configuration\n",
"os.environ[\"GROQ_API_KEY\"] = \"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\"\n",
"\n",
"config_dict = {\n",
" \"project_name\": \"Skincare_Intelligence\",\n",
" \"embedding\": {\"provider\": \"openai\", \"model\": \"text-embedding-3-small\"}, \n",
" \"extraction\": {\n",
" \"provider\": \"groq\", \n",
" \"model\": \"llama-3.1-8b-instant\", \n",
" \"temperature\": 0.0\n",
" },\n",
" \"inference\": {\n",
" \"provider\": \"groq\",\n",
" \"model\": \"llama-3.1-70b-versatile\"\n",
" },\n",
" \"vector_store\": {\"provider\": \"faiss\", \"dimension\": 1536},\n",
" \"knowledge_graph\": {\"backend\": \"networkx\", \"merge_entities\": True}\n",
"}\n",
"\n",
"config = ConfigManager().load_from_dict(config_dict)\n",
"core = Semantica(config=config)\n",
"vs = VectorStore(backend=\"faiss\", dimension=1536)\n",
"# Install dependencies\n",
"!pip install -qU semantica networkx matplotlib plotly pandas faiss-cpu beautifulsoup4 groq sentence-transformers"
]
},
{
"cell_type": "markdown",
"id": "b7a767b5",
"metadata": {},
"source": [
"## 🛠️ Phase 0: Environment & Foundation\n",
"We configure **Groq** as our primary LLM provider and use **Sentence-Transformers** for local embeddings to avoid API dependencies."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6840539f",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import json\n",
"import pandas as pd\n",
"from semantica.core import Semantica, ConfigManager\n",
"from semantica.seed import SeedDataManager\n",
"from semantica.vector_store import VectorStore\n",
"\n",
"# 1. Groq Configuration\n",
"import getpass\n",
"if \"GROQ_API_KEY\" not in os.environ:\n",
" os.environ[\"GROQ_API_KEY\"] = getpass.getpass(\"Enter your Groq API Key: \")\n",
"\n",
"config_dict = {\n",
" \"project_name\": \"Skincare_Intelligence\",\n",
" \"embedding\": {\"provider\": \"sentence_transformers\", \"model\": \"all-MiniLM-L6-v2\"}, \n",
" \"extraction\": {\n",
" \"provider\": \"groq\", \n",
" \"model\": \"llama-3.1-8b-instant\", \n",
" \"temperature\": 0.0\n",
" },\n",
" \"inference\": {\n",
" \"provider\": \"groq\",\n",
" \"model\": \"llama-3.1-70b-versatile\"\n",
" },\n",
" \"vector_store\": {\"provider\": \"faiss\", \"dimension\": 384},\n",
" \"knowledge_graph\": {\"backend\": \"networkx\", \"merge_entities\": True}\n",
"}\n",
"\n",
"config = ConfigManager().load_from_dict(config_dict)\n",
"core = Semantica(config=config)\n",
"vs = VectorStore(backend=\"faiss\", dimension=384)\n",
"\n",
"# 2. Seeding Ground Truth\n",
"foundation_data = {\n",
cookbook/use_cases/advanced_rag/02_RAG_vs_GraphRAG_Comparison.ipynb
+4 -3
View File
@@ -5,10 +5,9 @@
"id": "de0a7591",
"metadata": {},
"source": [
"# RAG vs. GraphRAG: Final Answer Comparison\n",
"\n",
"[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Hawksight-AI/semantica/blob/main/cookbook/use_cases/advanced_rag/02_RAG_vs_GraphRAG_Comparison.ipynb)\n",
"\n",
"# RAG vs. GraphRAG: Final Answer Comparison\n",
"This notebook demonstrates the difference in final answers generated by **Standard Vector RAG** and **Semantica GraphRAG** for a complex multi-hop query. We use **FalkorDB** as our high-performance graph backend.\n",
"\n",
"### FalkorDB Setup\n",
@@ -53,7 +52,9 @@
"import os\n",
"\n",
"# 1. Core Semantica & Vector Store\n",
"os.environ[\"GROQ_API_KEY\"] = \"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\"\n",
"import getpass\n",
"if \"GROQ_API_KEY\" not in os.environ:\n",
" os.environ[\"GROQ_API_KEY\"] = getpass.getpass(\"Enter your Groq API Key: \")\n",
"\n",
"config_dict = {\n",
" \"embedding\": {\"provider\": \"sentence_transformers\", \"model\": \"all-MiniLM-L6-v2\"},\n",