TriCacheLLM-MMA 0.1.4__tar.gz → 0.1.5__tar.gz

{tricachellm_mma-0.1.4 → tricachellm_mma-0.1.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: TriCacheLLM_MMA
-Version: 0.1.4
+Version: 0.1.5
 Summary: A robust three-tier LLM-aware caching SDK using Redis, ChromaDB, and automatic SQLite bootstrap.
 Author-email: Mohib Ashfaq Butt <inboxmohib@gmail.com>
 License-Expression: LGPL-3.0-only
@@ -511,18 +511,31 @@ from TriCacheLLM_MMA import (
     check_tenant_creation_status,
 )
 
-app = FastAPI()
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    yield
+    await close_cache_system()
+
+
+app = FastAPI(
+    title="TriCacheLLM_MMA V1 Route Test",
+    lifespan=lifespan,
+)
+
 
 # 1. ADMIN SETUP (Run once on startup / first deploy with user_id=0)
-@app.on_event("startup")
-async def startup_event():
-    await create_cache_system(
+@app.post("/api/consumer/init")
+async def initialize_consumer():
+    user_id: int = 0
+    result = await create_cache_system(
         redis_url="redis://localhost:6379/0",
-        cohere_api_key="YOUR_COHERE_API_KEY",
+        cohere_api_key="KEY_HERE",
         chroma_db_dir="./chroma_db",
         db_path="./cache.db",
-        user_id=0,
+        user_id=user_id, 
     )
+    return {"status": "success", "details": result}
 
 
 # 2. TENANT ENDPOINT (Zero boilerplate for subsequent users)
@@ -552,12 +565,13 @@ async def ask_question(
     )
 
     return {"source": "ai", "response": llm_response}
+
 ```
 The core cache operations are asynchronous Python APIs and are not inherently tied to FastAPI.
 The included integration example uses FastAPI because it provides a convenient demonstration of multi-user request handling.
 
 V1 is primarily demonstrated in a web-service architecture, while future versions aim to make standalone application integration equally straightforward.
-***NOTE: When you import files they'll send request to hugging face to get embedding model weights but only once! untill you reload server***
+***NOTE: On first initialization, the embedding model may contact Hugging Face to obtain the model if it is not already available in the local cache. Subsequent process reloads and reuse the locally cached model files Blazing fast.***
 
 ---
 

{tricachellm_mma-0.1.4 → tricachellm_mma-0.1.5}/README.md

@@ -469,18 +469,31 @@ from TriCacheLLM_MMA import (
     check_tenant_creation_status,
 )
 
-app = FastAPI()
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    yield
+    await close_cache_system()
+
+
+app = FastAPI(
+    title="TriCacheLLM_MMA V1 Route Test",
+    lifespan=lifespan,
+)
+
 
 # 1. ADMIN SETUP (Run once on startup / first deploy with user_id=0)
-@app.on_event("startup")
-async def startup_event():
-    await create_cache_system(
+@app.post("/api/consumer/init")
+async def initialize_consumer():
+    user_id: int = 0
+    result = await create_cache_system(
         redis_url="redis://localhost:6379/0",
-        cohere_api_key="YOUR_COHERE_API_KEY",
+        cohere_api_key="KEY_HERE",
         chroma_db_dir="./chroma_db",
         db_path="./cache.db",
-        user_id=0,
+        user_id=user_id, 
     )
+    return {"status": "success", "details": result}
 
 
 # 2. TENANT ENDPOINT (Zero boilerplate for subsequent users)
@@ -510,12 +523,13 @@ async def ask_question(
     )
 
     return {"source": "ai", "response": llm_response}
+
 ```
 The core cache operations are asynchronous Python APIs and are not inherently tied to FastAPI.
 The included integration example uses FastAPI because it provides a convenient demonstration of multi-user request handling.
 
 V1 is primarily demonstrated in a web-service architecture, while future versions aim to make standalone application integration equally straightforward.
-***NOTE: When you import files they'll send request to hugging face to get embedding model weights but only once! untill you reload server***
+***NOTE: On first initialization, the embedding model may contact Hugging Face to obtain the model if it is not already available in the local cache. Subsequent process reloads and reuse the locally cached model files Blazing fast.***
 
 ---
 

{tricachellm_mma-0.1.4 → tricachellm_mma-0.1.5}/TriCacheLLM_MMA/portable_cache_utils/portable_cache_embedding_model.py

@@ -3,5 +3,6 @@ from langchain_huggingface import HuggingFaceEmbeddings
 from ..portable_cache_utils.protable_cache_DynamicEnv_maker import get_settings
 
 embedding_model = HuggingFaceEmbeddings(
-    model_name=get_settings().portable_cache_cache_proj_embedding_model
+    model_name=get_settings().portable_cache_cache_proj_embedding_model,
+    cache_folder=get_settings().portable_cache_chroma_db_dir
 )

{tricachellm_mma-0.1.4 → tricachellm_mma-0.1.5}/TriCacheLLM_MMA.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: TriCacheLLM_MMA
-Version: 0.1.4
+Version: 0.1.5
 Summary: A robust three-tier LLM-aware caching SDK using Redis, ChromaDB, and automatic SQLite bootstrap.
 Author-email: Mohib Ashfaq Butt <inboxmohib@gmail.com>
 License-Expression: LGPL-3.0-only
@@ -511,18 +511,31 @@ from TriCacheLLM_MMA import (
     check_tenant_creation_status,
 )
 
-app = FastAPI()
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    yield
+    await close_cache_system()
+
+
+app = FastAPI(
+    title="TriCacheLLM_MMA V1 Route Test",
+    lifespan=lifespan,
+)
+
 
 # 1. ADMIN SETUP (Run once on startup / first deploy with user_id=0)
-@app.on_event("startup")
-async def startup_event():
-    await create_cache_system(
+@app.post("/api/consumer/init")
+async def initialize_consumer():
+    user_id: int = 0
+    result = await create_cache_system(
         redis_url="redis://localhost:6379/0",
-        cohere_api_key="YOUR_COHERE_API_KEY",
+        cohere_api_key="KEY_HERE",
         chroma_db_dir="./chroma_db",
         db_path="./cache.db",
-        user_id=0,
+        user_id=user_id, 
     )
+    return {"status": "success", "details": result}
 
 
 # 2. TENANT ENDPOINT (Zero boilerplate for subsequent users)
@@ -552,12 +565,13 @@ async def ask_question(
     )
 
     return {"source": "ai", "response": llm_response}
+
 ```
 The core cache operations are asynchronous Python APIs and are not inherently tied to FastAPI.
 The included integration example uses FastAPI because it provides a convenient demonstration of multi-user request handling.
 
 V1 is primarily demonstrated in a web-service architecture, while future versions aim to make standalone application integration equally straightforward.
-***NOTE: When you import files they'll send request to hugging face to get embedding model weights but only once! untill you reload server***
+***NOTE: On first initialization, the embedding model may contact Hugging Face to obtain the model if it is not already available in the local cache. Subsequent process reloads and reuse the locally cached model files Blazing fast.***
 
 ---
 

{tricachellm_mma-0.1.4 → tricachellm_mma-0.1.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "TriCacheLLM_MMA"
-version = "0.1.4"
+version = "0.1.5"
 description = "A robust three-tier LLM-aware caching SDK using Redis, ChromaDB, and automatic SQLite bootstrap."
 readme = "README.md"
 requires-python = ">=3.11"