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

chore: resolve dependencies, migrate Gemini SDK, and sanitize notebooks

Browse Source
This commit is contained in:
KaifAhmad1
2026-01-14 12:37:29 +05:30
parent be8856cfcf
commit a5da533d55
10 changed files with 70 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cookbook/use_cases/advanced_rag/01_GraphRAG_Complete.ipynb
+1 -1
View File
@@ -110,7 +110,7 @@
"source": [
"# Set up API keys\n",
"# Note: In production, use environment variables: export GROQ_API_KEY=\"your-key\"\n",
"os.environ[\"GROQ_API_KEY\"] = os.getenv(\"GROQ_API_KEY\", \"Your Groq API\")\n"
"os.environ[\"GROQ_API_KEY\"] = os.getenv(\"GROQ_API_KEY\", \"\")\n"
]
},
{
cookbook/use_cases/advanced_rag/02_RAG_vs_GraphRAG_Comparison.ipynb
+2 -2
View File
@@ -30,7 +30,7 @@
"# Environment Setup\n",
"import os\n",
"\n",
"os.environ['GROQ_API_KEY'] = os.getenv('GROQ_API_KEY', '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')\n",
"os.environ['GROQ_API_KEY'] = os.getenv('GROQ_API_KEY', '')\n",
"\n",
"# Install Semantica and all required dependencies\n",
"%pip install -qU semantica networkx matplotlib plotly pandas faiss-cpu beautifulsoup4 groq sentence-transformers\n"
@@ -84,7 +84,7 @@
"source": [
"# Set up API keys\n",
"# Note: In production, use environment variables: export GROQ_API_KEY=\"your-key\"\n",
"os.environ[\"GROQ_API_KEY\"] = os.getenv(\"GROQ_API_KEY\", \"your-groq-api-key-here\")\n",
"os.environ[\"GROQ_API_KEY\"] = os.getenv(\"GROQ_API_KEY\", \"\")\n",
"\n",
"print(\"API keys configured.\")\n"
]
cookbook/use_cases/biomedical/01_Drug_Discovery_Pipeline.ipynb
+1 -1
View File
@@ -109,7 +109,7 @@
"source": [
"import os\n",
"\n",
"os.environ[\"GROQ_API_KEY\"] = os.getenv(\"GROQ_API_KEY\", \"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\")\n"
"os.environ[\"GROQ_API_KEY\"] = os.getenv(\"GROQ_API_KEY\", \"\")\n"
]
},
{
cookbook/use_cases/biomedical/02_Genomic_Variant_Analysis.ipynb
+1 -1
View File
@@ -85,7 +85,7 @@
"source": [
"import os\n",
"\n",
"os.environ[\"GROQ_API_KEY\"] = os.getenv(\"GROQ_API_KEY\", \"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\")\n"
"os.environ[\"GROQ_API_KEY\"] = os.getenv(\"GROQ_API_KEY\", \"\")\n"
]
},
{
cookbook/use_cases/blockchain/01_DeFi_Protocol_Intelligence.ipynb
+1 -1
View File
@@ -81,7 +81,7 @@
"source": [
"import os\n",
"\n",
"os.environ[\"GROQ_API_KEY\"] = os.getenv(\"GROQ_API_KEY\", \"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\")\n",
"os.environ[\"GROQ_API_KEY\"] = os.getenv(\"GROQ_API_KEY\", \"\")\n",
"\n",
"# Configuration constants\n",
"EMBEDDING_DIMENSION = 384\n",
cookbook/use_cases/finance/02_Fraud_Detection.ipynb
+1 -1
View File
@@ -98,7 +98,7 @@
"source": [
"import os\n",
"\n",
"os.environ[\"GROQ_API_KEY\"] = os.getenv(\"GROQ_API_KEY\", \"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\")\n",
"os.environ[\"GROQ_API_KEY\"] = os.getenv(\"GROQ_API_KEY\", \"\")\n",
"\n",
"# Configuration constants\n",
"EMBEDDING_DIMENSION = 384\n",
cookbook/use_cases/intelligence/02_Intelligence_Analysis_Orchestrator_Worker.ipynb
+1 -1
View File
@@ -83,7 +83,7 @@
"source": [
"import os\n",
"\n",
"os.environ[\"GROQ_API_KEY\"] = os.getenv(\"GROQ_API_KEY\", \"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\")\n",
"os.environ[\"GROQ_API_KEY\"] = os.getenv(\"GROQ_API_KEY\", \"\")\n",
"\n",
"# Configuration constants\n",
"EMBEDDING_DIMENSION = 384\n",
cookbook/use_cases/renewable_energy/01_Energy_Market_Analysis.ipynb
+1 -1
View File
@@ -80,7 +80,7 @@
"source": [
"import os\n",
"\n",
"os.environ[\"GROQ_API_KEY\"] = os.getenv(\"GROQ_API_KEY\", \"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\")\n",
"os.environ[\"GROQ_API_KEY\"] = os.getenv(\"GROQ_API_KEY\", \"\")\n",
"\n",
"# Configuration constants\n",
"EMBEDDING_DIMENSION = 384\n",
pyproject.toml
+5 -5
View File
@@ -56,8 +56,8 @@ dependencies = [
"requests>=2.28.0",
"GitPython>=3.1.30",
"chardet>=5.1.0",
"protobuf==4.25.8",
"grpcio==1.67.1",
"protobuf>=5.29.1,<7.0",
"grpcio>=1.71.2",
"beautifulsoup4>=4.11.0",
"lxml>=4.9.0",
"pypdf2>=2.10.0",
@@ -102,8 +102,8 @@ dependencies = [
"loguru>=0.6.0",
"structlog>=22.1.0",
"prometheus-client>=0.14.0",
"opentelemetry-api>=1.12.0",
"opentelemetry-sdk>=1.12.0",
"opentelemetry-api==1.37.0",
"opentelemetry-sdk==1.37.0",
"opentelemetry-instrumentation",
"fastapi>=0.78.0",
"uvicorn>=0.18.0",
@@ -166,7 +166,7 @@ llm-openai = [
"openai>=1.0.0"
]
llm-gemini = [
"google-generativeai>=0.3.0"
"google-genai>=0.1.0"
]
llm-groq = [
"groq>=0.4.0"
semantica/semantic_extract/providers.py
+56 -28
View File
@@ -530,26 +530,40 @@ class GeminiProvider(BaseProvider):
self.api_key = api_key or config.get_api_key("gemini")
self.model = model
self.client = None
self._use_new_genai = False
self._init_client()
def _init_client(self):
"""Initialize Gemini client."""
try:
import google.generativeai as genai
from google import genai as new_genai
if self.api_key:
genai.configure(api_key=self.api_key)
self.client = genai.GenerativeModel(self.model)
except (ImportError, OSError):
self.client = new_genai.Client(api_key=self.api_key)
self._use_new_genai = True
return
except Exception:
pass
try:
import google.generativeai as old_genai
if self.api_key:
old_genai.configure(api_key=self.api_key)
self.client = old_genai.GenerativeModel(self.model)
self._use_new_genai = False
except Exception:
self.client = None
self.logger.warning(
"google-generativeai library not installed. Install with: pip install semantica[llm-gemini]"
)
self.logger.warning("Gemini SDK not installed. Install with: pip install semantica[llm-gemini]")
def is_available(self) -> bool:
"""Check if provider is available."""
return self.client is not None
def _resp_text(self, resp: Any) -> str:
if hasattr(resp, "text"):
return getattr(resp, "text")
try:
return resp.candidates[0].content.parts[0].text
except Exception:
return str(resp)
def generate(self, prompt: str, **kwargs) -> str:
"""Generate text from prompt."""
if not self.client:
@@ -557,32 +571,46 @@ class GeminiProvider(BaseProvider):
"Gemini client not initialized. Set GEMINI_API_KEY or pass api_key."
)
generation_config = {"temperature": kwargs.get("temperature", 0.3)}
if "max_tokens" in kwargs:
generation_config["max_output_tokens"] = kwargs["max_tokens"]
# Pass through other common parameters
for param in ["top_p", "top_k", "stop_sequences", "candidate_count"]:
if param in kwargs:
generation_config[param] = kwargs[param]
response = self.client.generate_content(
prompt, generation_config=generation_config
)
return response.text
if self._use_new_genai:
model = kwargs.get("model", self.model)
temperature = kwargs.get("temperature", 0.3)
create_kwargs = {"model": model, "contents": prompt, "config": {"temperature": temperature}}
if "max_tokens" in kwargs:
create_kwargs["config"]["max_output_tokens"] = kwargs["max_tokens"]
for p in ["top_p", "top_k", "stop_sequences", "candidate_count"]:
if p in kwargs:
create_kwargs["config"][p] = kwargs[p]
resp = self.client.models.generate_content(**create_kwargs)
return self._resp_text(resp)
else:
generation_config = {"temperature": kwargs.get("temperature", 0.3)}
if "max_tokens" in kwargs:
generation_config["max_output_tokens"] = kwargs["max_tokens"]
for param in ["top_p", "top_k", "stop_sequences", "candidate_count"]:
if param in kwargs:
generation_config[param] = kwargs[param]
response = self.client.generate_content(prompt, generation_config=generation_config)
return self._resp_text(response)
def generate_structured(self, prompt: str, **kwargs) -> dict:
"""Generate structured output."""
if not self.client:
raise ProcessingError("Gemini client not initialized.")
# Add JSON format instruction to prompt
json_prompt = f"{prompt}\n\nReturn the response as valid JSON only."
response = self.client.generate_content(json_prompt)
try:
return self._parse_json(response.text)
except Exception as e:
raise ProcessingError(f"Failed to parse JSON from Gemini response: {e}")
if self._use_new_genai:
model = kwargs.get("model", self.model)
resp = self.client.models.generate_content(model=model, contents=json_prompt)
try:
return self._parse_json(self._resp_text(resp))
except Exception as e:
raise ProcessingError(f"Failed to parse JSON from Gemini response: {e}")
else:
response = self.client.generate_content(json_prompt)
try:
return self._parse_json(self._resp_text(response))
except Exception as e:
raise ProcessingError(f"Failed to parse JSON from Gemini response: {e}")
class GroqProvider(BaseProvider):