llama-stack 0.3.4__tar.gz → 0.3.5__tar.gz

{llama_stack-0.3.4/llama_stack.egg-info → llama_stack-0.3.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: llama_stack
-Version: 0.3.4
+Version: 0.3.5
 Summary: Llama Stack
 Author-email: Meta Llama <llama-oss@meta.com>
 License: MIT
@@ -22,7 +22,7 @@ Requires-Dist: fire
 Requires-Dist: httpx
 Requires-Dist: jinja2>=3.1.6
 Requires-Dist: jsonschema
-Requires-Dist: llama-stack-client>=0.3.4
+Requires-Dist: llama-stack-client==0.3.5
 Requires-Dist: openai>=1.107
 Requires-Dist: prompt-toolkit
 Requires-Dist: python-dotenv
@@ -45,7 +45,7 @@ Requires-Dist: starlette>=0.49.1
 Provides-Extra: ui
 Requires-Dist: streamlit; extra == "ui"
 Requires-Dist: pandas; extra == "ui"
-Requires-Dist: llama-stack-client>=0.3.4; extra == "ui"
+Requires-Dist: llama-stack-client==0.3.5; extra == "ui"
 Requires-Dist: streamlit-option-menu; extra == "ui"
 Dynamic: license-file
 
@@ -61,83 +61,6 @@ Dynamic: license-file
 [**Quick Start**](https://llamastack.github.io/docs/getting_started/quickstart) | [**Documentation**](https://llamastack.github.io/docs) | [**Colab Notebook**](./docs/getting_started.ipynb) | [**Discord**](https://discord.gg/llama-stack)
 
 
-### ✨🎉 Llama 4 Support  🎉✨
-We released [Version 0.2.0](https://github.com/meta-llama/llama-stack/releases/tag/v0.2.0) with support for the Llama 4 herd of models released by Meta.
-
-<details>
-
-<summary>👋 Click here to see how to run Llama 4 models on Llama Stack </summary>
-
-\
-*Note you need 8xH100 GPU-host to run these models*
-
-```bash
-pip install -U llama_stack
-
-MODEL="Llama-4-Scout-17B-16E-Instruct"
-# get meta url from llama.com
-huggingface-cli download meta-llama/$MODEL --local-dir ~/.llama/$MODEL
-
-# install dependencies for the distribution
-llama stack list-deps meta-reference-gpu | xargs -L1 uv pip install
-
-# start a llama stack server
-INFERENCE_MODEL=meta-llama/$MODEL llama stack run meta-reference-gpu
-
-# install client to interact with the server
-pip install llama-stack-client
-```
-### CLI
-```bash
-# Run a chat completion
-MODEL="Llama-4-Scout-17B-16E-Instruct"
-
-llama-stack-client --endpoint http://localhost:8321 \
-inference chat-completion \
---model-id meta-llama/$MODEL \
---message "write a haiku for meta's llama 4 models"
-
-OpenAIChatCompletion(
-    ...
-    choices=[
-        OpenAIChatCompletionChoice(
-            finish_reason='stop',
-            index=0,
-            message=OpenAIChatCompletionChoiceMessageOpenAIAssistantMessageParam(
-                role='assistant',
-                content='...**Silent minds awaken,**  \n**Whispers of billions of words,**  \n**Reasoning breaks the night.**  \n\n—  \n*This haiku blends the essence of LLaMA 4\'s capabilities with nature-inspired metaphor, evoking its vast training data and transformative potential.*',
-                ...
-            ),
-            ...
-        )
-    ],
-    ...
-)
-```
-### Python SDK
-```python
-from llama_stack_client import LlamaStackClient
-
-client = LlamaStackClient(base_url=f"http://localhost:8321")
-
-model_id = "meta-llama/Llama-4-Scout-17B-16E-Instruct"
-prompt = "Write a haiku about coding"
-
-print(f"User> {prompt}")
-response = client.chat.completions.create(
-    model=model_id,
-    messages=[
-        {"role": "system", "content": "You are a helpful assistant."},
-        {"role": "user", "content": prompt},
-    ],
-)
-print(f"Assistant> {response.choices[0].message.content}")
-```
-As more providers start supporting Llama 4, you can use them in Llama Stack as well. We are adding to the list. Stay tuned!
-
-
-</details>
-
 ### 🚀 One-Line Installer 🚀
 
 To try Llama Stack locally, run:

{llama_stack-0.3.4 → llama_stack-0.3.5}/README.md

@@ -10,83 +10,6 @@
 [**Quick Start**](https://llamastack.github.io/docs/getting_started/quickstart) | [**Documentation**](https://llamastack.github.io/docs) | [**Colab Notebook**](./docs/getting_started.ipynb) | [**Discord**](https://discord.gg/llama-stack)
 
 
-### ✨🎉 Llama 4 Support  🎉✨
-We released [Version 0.2.0](https://github.com/meta-llama/llama-stack/releases/tag/v0.2.0) with support for the Llama 4 herd of models released by Meta.
-
-<details>
-
-<summary>👋 Click here to see how to run Llama 4 models on Llama Stack </summary>
-
-\
-*Note you need 8xH100 GPU-host to run these models*
-
-```bash
-pip install -U llama_stack
-
-MODEL="Llama-4-Scout-17B-16E-Instruct"
-# get meta url from llama.com
-huggingface-cli download meta-llama/$MODEL --local-dir ~/.llama/$MODEL
-
-# install dependencies for the distribution
-llama stack list-deps meta-reference-gpu | xargs -L1 uv pip install
-
-# start a llama stack server
-INFERENCE_MODEL=meta-llama/$MODEL llama stack run meta-reference-gpu
-
-# install client to interact with the server
-pip install llama-stack-client
-```
-### CLI
-```bash
-# Run a chat completion
-MODEL="Llama-4-Scout-17B-16E-Instruct"
-
-llama-stack-client --endpoint http://localhost:8321 \
-inference chat-completion \
---model-id meta-llama/$MODEL \
---message "write a haiku for meta's llama 4 models"
-
-OpenAIChatCompletion(
-    ...
-    choices=[
-        OpenAIChatCompletionChoice(
-            finish_reason='stop',
-            index=0,
-            message=OpenAIChatCompletionChoiceMessageOpenAIAssistantMessageParam(
-                role='assistant',
-                content='...**Silent minds awaken,**  \n**Whispers of billions of words,**  \n**Reasoning breaks the night.**  \n\n—  \n*This haiku blends the essence of LLaMA 4\'s capabilities with nature-inspired metaphor, evoking its vast training data and transformative potential.*',
-                ...
-            ),
-            ...
-        )
-    ],
-    ...
-)
-```
-### Python SDK
-```python
-from llama_stack_client import LlamaStackClient
-
-client = LlamaStackClient(base_url=f"http://localhost:8321")
-
-model_id = "meta-llama/Llama-4-Scout-17B-16E-Instruct"
-prompt = "Write a haiku about coding"
-
-print(f"User> {prompt}")
-response = client.chat.completions.create(
-    model=model_id,
-    messages=[
-        {"role": "system", "content": "You are a helpful assistant."},
-        {"role": "user", "content": prompt},
-    ],
-)
-print(f"Assistant> {response.choices[0].message.content}")
-```
-As more providers start supporting Llama 4, you can use them in Llama Stack as well. We are adding to the list. Stay tuned!
-
-
-</details>
-
 ### 🚀 One-Line Installer 🚀
 
 To try Llama Stack locally, run:

{llama_stack-0.3.4 → llama_stack-0.3.5}/llama_stack/providers/utils/inference/inference_store.py

@@ -56,7 +56,7 @@ class InferenceStore:
             logger.debug("Write queue disabled for SQLite (WAL mode handles concurrency)")
 
         await self.sql_store.create_table(
-            "chat_completions",
+            self.reference.table_name,
             {
                 "id": ColumnDefinition(type=ColumnType.STRING, primary_key=True),
                 "created": ColumnType.INTEGER,
@@ -66,14 +66,6 @@ class InferenceStore:
             },
         )
 
-        if self.enable_write_queue:
-            self._queue = asyncio.Queue(maxsize=self._max_write_queue_size)
-            for _ in range(self._num_writers):
-                self._worker_tasks.append(asyncio.create_task(self._worker_loop()))
-            logger.debug(
-                f"Inference store write queue enabled with {self._num_writers} writers, max queue size {self._max_write_queue_size}"
-            )
-
     async def shutdown(self) -> None:
         if not self._worker_tasks:
             return
@@ -161,7 +153,7 @@ class InferenceStore:
 
         try:
             await self.sql_store.insert(
-                table="chat_completions",
+                table=self.reference.table_name,
                 data=record_data,
             )
         except IntegrityError as e:
@@ -173,7 +165,7 @@ class InferenceStore:
             error_message = str(e.orig) if e.orig else str(e)
             if self._is_unique_constraint_error(error_message):
                 # Update the existing record instead
-                await self.sql_store.update(table="chat_completions", data=record_data, where={"id": data["id"]})
+                await self.sql_store.update(table=self.reference.table_name, data=record_data, where={"id": data["id"]})
             else:
                 # Re-raise if it's not a unique constraint error
                 raise
@@ -217,7 +209,7 @@ class InferenceStore:
             where_conditions["model"] = model
 
         paginated_result = await self.sql_store.fetch_all(
-            table="chat_completions",
+            table=self.reference.table_name,
             where=where_conditions if where_conditions else None,
             order_by=[("created", order.value)],
             cursor=("id", after) if after else None,
@@ -246,7 +238,7 @@ class InferenceStore:
             raise ValueError("Inference store is not initialized")
 
         row = await self.sql_store.fetch_one(
-            table="chat_completions",
+            table=self.reference.table_name,
             where={"id": completion_id},
         )
 

{llama_stack-0.3.4 → llama_stack-0.3.5/llama_stack.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: llama_stack
-Version: 0.3.4
+Version: 0.3.5
 Summary: Llama Stack
 Author-email: Meta Llama <llama-oss@meta.com>
 License: MIT
@@ -22,7 +22,7 @@ Requires-Dist: fire
 Requires-Dist: httpx
 Requires-Dist: jinja2>=3.1.6
 Requires-Dist: jsonschema
-Requires-Dist: llama-stack-client>=0.3.4
+Requires-Dist: llama-stack-client==0.3.5
 Requires-Dist: openai>=1.107
 Requires-Dist: prompt-toolkit
 Requires-Dist: python-dotenv
@@ -45,7 +45,7 @@ Requires-Dist: starlette>=0.49.1
 Provides-Extra: ui
 Requires-Dist: streamlit; extra == "ui"
 Requires-Dist: pandas; extra == "ui"
-Requires-Dist: llama-stack-client>=0.3.4; extra == "ui"
+Requires-Dist: llama-stack-client==0.3.5; extra == "ui"
 Requires-Dist: streamlit-option-menu; extra == "ui"
 Dynamic: license-file
 
@@ -61,83 +61,6 @@ Dynamic: license-file
 [**Quick Start**](https://llamastack.github.io/docs/getting_started/quickstart) | [**Documentation**](https://llamastack.github.io/docs) | [**Colab Notebook**](./docs/getting_started.ipynb) | [**Discord**](https://discord.gg/llama-stack)
 
 
-### ✨🎉 Llama 4 Support  🎉✨
-We released [Version 0.2.0](https://github.com/meta-llama/llama-stack/releases/tag/v0.2.0) with support for the Llama 4 herd of models released by Meta.
-
-<details>
-
-<summary>👋 Click here to see how to run Llama 4 models on Llama Stack </summary>
-
-\
-*Note you need 8xH100 GPU-host to run these models*
-
-```bash
-pip install -U llama_stack
-
-MODEL="Llama-4-Scout-17B-16E-Instruct"
-# get meta url from llama.com
-huggingface-cli download meta-llama/$MODEL --local-dir ~/.llama/$MODEL
-
-# install dependencies for the distribution
-llama stack list-deps meta-reference-gpu | xargs -L1 uv pip install
-
-# start a llama stack server
-INFERENCE_MODEL=meta-llama/$MODEL llama stack run meta-reference-gpu
-
-# install client to interact with the server
-pip install llama-stack-client
-```
-### CLI
-```bash
-# Run a chat completion
-MODEL="Llama-4-Scout-17B-16E-Instruct"
-
-llama-stack-client --endpoint http://localhost:8321 \
-inference chat-completion \
---model-id meta-llama/$MODEL \
---message "write a haiku for meta's llama 4 models"
-
-OpenAIChatCompletion(
-    ...
-    choices=[
-        OpenAIChatCompletionChoice(
-            finish_reason='stop',
-            index=0,
-            message=OpenAIChatCompletionChoiceMessageOpenAIAssistantMessageParam(
-                role='assistant',
-                content='...**Silent minds awaken,**  \n**Whispers of billions of words,**  \n**Reasoning breaks the night.**  \n\n—  \n*This haiku blends the essence of LLaMA 4\'s capabilities with nature-inspired metaphor, evoking its vast training data and transformative potential.*',
-                ...
-            ),
-            ...
-        )
-    ],
-    ...
-)
-```
-### Python SDK
-```python
-from llama_stack_client import LlamaStackClient
-
-client = LlamaStackClient(base_url=f"http://localhost:8321")
-
-model_id = "meta-llama/Llama-4-Scout-17B-16E-Instruct"
-prompt = "Write a haiku about coding"
-
-print(f"User> {prompt}")
-response = client.chat.completions.create(
-    model=model_id,
-    messages=[
-        {"role": "system", "content": "You are a helpful assistant."},
-        {"role": "user", "content": prompt},
-    ],
-)
-print(f"Assistant> {response.choices[0].message.content}")
-```
-As more providers start supporting Llama 4, you can use them in Llama Stack as well. We are adding to the list. Stay tuned!
-
-
-</details>
-
 ### 🚀 One-Line Installer 🚀
 
 To try Llama Stack locally, run:

{llama_stack-0.3.4 → llama_stack-0.3.5}/llama_stack.egg-info/requires.txt

@@ -4,7 +4,7 @@ fire
 httpx
 jinja2>=3.1.6
 jsonschema
-llama-stack-client>=0.3.4
+llama-stack-client==0.3.5
 openai>=1.107
 prompt-toolkit
 python-dotenv
@@ -28,5 +28,5 @@ starlette>=0.49.1
 [ui]
 streamlit
 pandas
-llama-stack-client>=0.3.4
+llama-stack-client==0.3.5
 streamlit-option-menu

{llama_stack-0.3.4 → llama_stack-0.3.5}/pyproject.toml

@@ -7,7 +7,7 @@ required-version = ">=0.7.0"
 
 [project]
 name = "llama_stack"
-version = "0.3.4"
+version = "0.3.5"
 authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
 description = "Llama Stack"
 readme = "README.md"
@@ -30,7 +30,7 @@ dependencies = [
     "httpx",
     "jinja2>=3.1.6",
     "jsonschema",
-    "llama-stack-client>=0.3.4",
+    "llama-stack-client==0.3.5",
     "openai>=1.107",                                  # for expires_after support
     "prompt-toolkit",
     "python-dotenv",
@@ -56,7 +56,7 @@ dependencies = [
 ui = [
     "streamlit",
     "pandas",
-    "llama-stack-client>=0.3.4",
+    "llama-stack-client==0.3.5",
     "streamlit-option-menu",
 ]