ai-microcore 4.0.0.dev1__tar.gz → 4.0.0.dev2__tar.gz

{ai_microcore-4.0.0.dev1 → ai_microcore-4.0.0.dev2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ai-microcore
-Version: 4.0.0.dev1
+Version: 4.0.0.dev2
 Summary: # Minimalistic Foundation for AI Applications
 Keywords: llm,large language models,ai,similarity search,ai search,gpt,openai
 Author-email: Vitalii Stepanenko <mail@vitalii.in>
@@ -132,6 +132,24 @@ See [transformers installation](https://huggingface.co/docs/transformers/install
     <br>💡 <small>Setting `USE_DOT_ENV` to `false` disables reading configuration files.</small>
 3.  OS environment variables have the lowest priority.
 
+### Vector Databases
+
+Vector database functions are available via `microcore.texts`.
+Default vector database is [Chroma](https://www.trychroma.com/).
+In order to use vector database functions, you need to install the `chromadb` package:
+```bash
+pip install chromadb
+```
+By default, MicroCore will use ChromaDB PersistentClient (if corresponding package is installed).
+Alternatively, you can run Chroma as separate service and configure MicroCore to use HttpClient:
+
+```python
+from microcore import configure
+configure(
+    EMBEDDING_DB_HOST = 'localhost',
+    EMBEDDING_DB_PORT = 8000,
+)
+```
 
 ## 🌟 Core Functions
 

{ai_microcore-4.0.0.dev1 → ai_microcore-4.0.0.dev2}/README.md

@@ -107,6 +107,24 @@ See [transformers installation](https://huggingface.co/docs/transformers/install
     <br>💡 <small>Setting `USE_DOT_ENV` to `false` disables reading configuration files.</small>
 3.  OS environment variables have the lowest priority.
 
+### Vector Databases
+
+Vector database functions are available via `microcore.texts`.
+Default vector database is [Chroma](https://www.trychroma.com/).
+In order to use vector database functions, you need to install the `chromadb` package:
+```bash
+pip install chromadb
+```
+By default, MicroCore will use ChromaDB PersistentClient (if corresponding package is installed).
+Alternatively, you can run Chroma as separate service and configure MicroCore to use HttpClient:
+
+```python
+from microcore import configure
+configure(
+    EMBEDDING_DB_HOST = 'localhost',
+    EMBEDDING_DB_PORT = 8000,
+)
+```
 
 ## 🌟 Core Functions
 

{ai_microcore-4.0.0.dev1 → ai_microcore-4.0.0.dev2}/microcore/__init__.py

@@ -161,4 +161,4 @@ __all__ = [
     # "wrappers",
 ]
 
-__version__ = "4.0.0-dev1"
+__version__ = "4.0.0-dev2"

{ai_microcore-4.0.0.dev1 → ai_microcore-4.0.0.dev2}/microcore/embedding_db/chromadb.py

@@ -1,3 +1,4 @@
+import logging
 from dataclasses import dataclass
 import uuid
 
@@ -17,6 +18,11 @@ class ChromaEmbeddingDB(AbstractEmbeddingDB):
 
     def __post_init__(self):
         if self.config.EMBEDDING_DB_HOST:
+            logging.info(
+                "Connecting to ChromaDB at %s:%s",
+                self.config.EMBEDDING_DB_HOST,
+                self.config.EMBEDDING_DB_PORT
+            )
             self.client = chromadb.HttpClient(
                 host=self.config.EMBEDDING_DB_HOST,
                 port=self.config.EMBEDDING_DB_PORT or 8000,

{ai_microcore-4.0.0.dev1 → ai_microcore-4.0.0.dev2}/microcore/logging.py

@@ -41,6 +41,20 @@ def _format_request_log_str(prompt, **kwargs) -> str:
         )
         if out.endswith("\n"):
             out = out[:-1]
+    if LoggingConfig.STRIP_REQUEST_LINES:
+        start_lines, end_lines = LoggingConfig.STRIP_REQUEST_LINES
+        max_lines = start_lines + end_lines
+        lines = out.split("\n")
+        if len(lines) > max_lines:
+            out = "\n".join(
+                lines[:start_lines]
+                + [
+                    f"{LoggingConfig.INDENT}{Fore.YELLOW}"
+                    f"...(output was truncated)..."
+                    f"{LoggingConfig.PROMPT_COLOR}"
+                ]
+                + (lines[-end_lines:] if end_lines else [])
+            )
     return out
 
 
@@ -72,6 +86,7 @@ class LoggingConfig:
     OUTPUT_METHOD: callable = print
     REQUEST_FORMATTER: callable = _format_request_log_str
     RESPONSE_FORMATTER: callable = _format_response_log_str
+    STRIP_REQUEST_LINES: tuple[int, int] | None = [40, 15]
 
 
 def _log_request(prompt, **kwargs):