Develop

.env.template

@@ -0,0 +1,25 @@
+OPENAI_API_KEY="sk-proj-XXXXX"
+ANTHROPIC_API_KEY="sk-XXXXX"
+COHERE_API_KEY="XXXX"
+GOOGLE_API_KEY="XXXX"
+DECART_API_KEY="XXXX"
+AI71_API_KEY="XXXX"
+AI21_API_KEY="XXXX"
+BEDROCK_ACCESS_KEY="XXXX"
+BEDROCK_SECRET_KEY="r+"XXXX""
+BEDROCK_REGION="us-west-2"
+HUGGING_FACE_API_KEY="hf_"XXXX""
+AZURE_API_KEY=""XXXX""
+AZURE_API_ENDPOINT="https://XXXXX.openai.azure.com/"
+AZURE_API_VERSION="2023-07-01-preview"
+ENGINE_HOST="localhost"
+ENGINE_PORT=8000
+UI_HOST="localhost"
+UI_PORT=3000
+LOG_LEVEL="info"
+
+#LLMSTUDIO_TRACKING_URI="postgresql://postgres:postgres@localhost:5433/tracker_db"
+LLMSTUDIO_TRACKING_URI="sqlite:///./llmstudio_mgmt.db"
+LLMSTUDIO_TRACKING_HOST="127.0.0.1"
+LLMSTUDIO_TRACKING_PORT="50002"
+LLMSTUDIO_ALEMBIC_TABLE_NAME="llmstudio_alembic_version"

.github/workflows/tests.yml

@@ -82,19 +82,32 @@ jobs:
         uses: actions/cache@v3
         with:
           path: ~/.cache/pypoetry
-          key: poetry-integration-${{ runner.os }}-${{ hashFiles('libs/llmstudio/poetry.lock') }}
+          key: poetry-integration-${{ runner.os }}-${{ hashFiles('libs/llmstudio/poetry.lock', 'libs/llmstudio/pyproject.toml') }}
           restore-keys: |
             poetry-integration-${{ runner.os }}-
 
       # Install llmstudio
       - name: Install llmstudio
         working-directory: ./libs/llmstudio
         run: |
-          poetry install
+          poetry install --extras tracker
           INTEGRATION_ENV=$(poetry env info --path)
           echo $INTEGRATION_ENV
           echo "INTEGRATION_ENV=$INTEGRATION_ENV" >> $GITHUB_ENV
 
+      # Set Env vars for sqlite db
+      - name: Set hardcoded DB URI, HOST and PORT
+        run: |
+          echo "LLMSTUDIO_TRACKING_URI=sqlite:///./test_tracker.db" >> $GITHUB_ENV
+          echo "LLMSTUDIO_TRACKING_HOST=127.0.0.1" >> $GITHUB_ENV
+          echo "LLMSTUDIO_TRACKING_PORT=50002" >> $GITHUB_ENV
+
+      # Run Alembic migrations
+      - name: Run Alembic migrations
+        run: |
+          source ${{ env.INTEGRATION_ENV }}/bin/activate
+          poetry run alembic upgrade head
+
       # Run Integration Tests
       - name: Run Integration Tests
         run: |

.gitignore

@@ -78,4 +78,4 @@ bun.lockb
 llmstudio/llm_engine/logs/execution_logs.jsonl
 *.db
 .prettierignore
-db
+

.pre-commit-config.yaml

@@ -30,7 +30,7 @@ repos:
     hooks:
       - id: autoflake
         files: libs/
-        exclude: 'libs/core/llmstudio_core/providers/__init__.py|libs/llmstudio/llmstudio/providers/__init__.py'
+        exclude: 'libs/core/llmstudio_core/providers/__init__.py|libs/llmstudio/llmstudio/providers/__init__.py|libs/tracker/llmstudio_tracker/db/migrations/env.py|libs/tracker/llmstudio_tracker/base.py'
         args:
         - --remove-all-unused-imports
         - --recursive

Makefile

@@ -3,3 +3,6 @@ format:
 
 unit-tests:
 	pytest libs/core/tests/unit_tests
+
+integration-tests:
+	pytest libs/llmstudio/tests/integration_tests

alembic.ini

@@ -0,0 +1,118 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+# Use forward slashes (/) also on windows to provide an os agnostic path
+script_location = libs/tracker/llmstudio_tracker/db/migrations
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.
+prepend_sys_path = .
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the python>=3.9 or backports.zoneinfo library and tzdata library.
+# Any required deps can installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to ZoneInfo()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to alembic/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "version_path_separator" below.
+# version_locations = %(here)s/bar:%(here)s/bat:alembic/versions
+
+# version path separator; As mentioned above, this is the character used to split
+# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
+# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or commas.
+# Valid values for version_path_separator are:
+#
+# version_path_separator = :
+# version_path_separator = ;
+# version_path_separator = space
+# version_path_separator = newline
+#
+# Use os.pathsep. Default configuration used for new projects.
+version_path_separator = os
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+sqlalchemy.url = placeholder
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# lint with attempts to fix using "ruff" - use the exec runner, execute a binary
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = %(here)s/.venv/bin/ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARNING
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARNING
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

examples/core.py

@@ -1,16 +1,35 @@
 
 from llmstudio_core.providers import LLMCore
-
+from llmstudio.providers import LLM
+from llmstudio_tracker.tracker import TrackingConfig
+from llmstudio.server import start_servers
 
 from pprint import pprint
 import os
 import asyncio
 from dotenv import load_dotenv
+import uuid
 load_dotenv()
 
+start_servers(proxy=False, tracker=True)
+
+tracking_config = TrackingConfig(
+            host=os.environ["LLMSTUDIO_TRACKING_HOST"],
+            port=os.environ["LLMSTUDIO_TRACKING_PORT"]
+        )
+
+session_id = str(uuid.uuid4())
+
+use_logging = True
+
+
 def run_provider(provider, model, api_key=None, **kwargs):
     print(f"\n\n###RUNNING for <{provider}>, <{model}> ###")
-    llm = LLMCore(provider=provider, api_key=api_key, **kwargs)
+
+    if use_logging:
+        llm = LLM(provider=provider, api_key=api_key, session_id=session_id, tracking_config=tracking_config, **kwargs)
+    else:
+        llm = LLMCore(provider=provider, api_key=api_key, **kwargs)
 
     latencies = {}
     print("\nAsync Non-Stream")
@@ -94,7 +113,7 @@ async def async_stream():
     return latencies
 
 def build_chat_request(model: str, chat_input: str, is_stream: bool, max_tokens: int=1000):
-    if model.startswith(('o1', 'o3')):
+    if model.startswith(('o1', 'o3', 'o4')):
         chat_request = {
             "chat_input": chat_input,
             "model": model,
@@ -137,7 +156,7 @@ def multiple_provider_runs(provider:str, model:str, num_runs:int, api_key:str, *
 def run_chat_all_providers():    
     # OpenAI
     multiple_provider_runs(provider="openai", model="gpt-4o-mini", api_key=os.environ["OPENAI_API_KEY"], num_runs=1)
-    multiple_provider_runs(provider="openai", model="o3-mini", api_key=os.environ["OPENAI_API_KEY"], num_runs=1)
+    multiple_provider_runs(provider="openai", model="o4-mini", api_key=os.environ["OPENAI_API_KEY"], num_runs=1)
     #multiple_provider_runs(provider="openai", model="o1-preview", api_key=os.environ["OPENAI_API_KEY"], num_runs=1)
 
 

libs/core/llmstudio_core/config.yaml

@@ -42,6 +42,26 @@ providers:
         max_tokens: 100000
         input_token_cost: 0.00000163
         output_token_cost: 0.00000551
+      claude-opus-4-6:
+        mode: chat
+        max_tokens: 1000000
+        input_token_cost: 0.000005
+        output_token_cost: 0.000025
+      claude-opus-4-7:
+        mode: chat
+        max_tokens: 1000000
+        input_token_cost: 0.000005
+        output_token_cost: 0.000025
+      claude-sonnet-4-6:
+        mode: chat
+        max_tokens: 1000000
+        input_token_cost: 0.000003
+        output_token_cost: 0.000015
+      claude-haiku-4-5-20251001:
+        mode: chat
+        max_tokens: 200000
+        input_token_cost: 0.000001
+        output_token_cost: 0.000005
     parameters:
       temperature:
         name: "Temperature"
@@ -126,6 +146,26 @@ providers:
         max_tokens: 100000
         input_token_cost: 0.000008
         output_token_cost: 0.000024
+      anthropic.claude-opus-4-6:
+        mode: chat
+        max_tokens: 1000000
+        input_token_cost: 0.000005
+        output_token_cost: 0.000025
+      anthropic.claude-opus-4-7:
+        mode: chat
+        max_tokens: 1000000
+        input_token_cost: 0.000005
+        output_token_cost: 0.000025
+      anthropic.claude-sonnet-4-6:
+        mode: chat
+        max_tokens: 1000000
+        input_token_cost: 0.000003
+        output_token_cost: 0.000015
+      anthropic.claude-haiku-4-5-20251001-v1:0:
+        mode: chat
+        max_tokens: 200000
+        input_token_cost: 0.000001
+        output_token_cost: 0.000005
       us.amazon.nova-pro-v1:0:
         mode: chat
         max_tokens: 300000

libs/core/llmstudio_core/providers/bedrock_converse.py

@@ -335,17 +335,22 @@ def _process_messages(
             return messages, system_prompt
 
     @staticmethod
-    def _base64_to_bytes(image_url: str) -> bytes:
+    def _b64_data_url_to_bytes(b64_data_url: str) -> bytes:
         """
-        Extracts and decodes Base64 image data from a 'data:image/...;base64,...' URL.
+        Extracts and decodes Base64 image data from a 'data:image/...;base64,...' data URL.
         Returns the raw image bytes.
         """
-        if not image_url.startswith("data:image/"):
+        if not b64_data_url.startswith("data:image/"):
             raise ValueError("Invalid Base64 image URL")
 
-        base64_data = re.sub(r"^data:image/[^;]+;base64,", "", image_url)
+        base64_data = re.sub(r"^data:image/[^;]+;base64,", "", b64_data_url)
 
-        return base64.b64decode(base64_data)
+        try:
+            return base64.b64decode(base64_data)
+        except Exception as e:
+            raise ValueError(
+                f"Failed to decode Base64: {e} ; For Base64 Data Url: {b64_data_url}"
+            )
 
     @staticmethod
     def _get_img_format_from_bytes(image_bytes: bytes) -> str:
@@ -377,7 +382,7 @@ def _get_image_bytes(image_url: str) -> bytes:
         - If it's a normal URL, downloads and encodes the image in Base64.
         """
         if image_url.startswith("data:image/"):
-            return BedrockConverseProvider._base64_to_bytes(image_url)
+            return BedrockConverseProvider._b64_data_url_to_bytes(image_url)
 
         elif image_url.startswith(("http://", "https://")):
             response = requests.get(image_url)