pixeltable 0.3.14__py3-none-any.whl → 0.5.7__py3-none-any.whl

pixeltable/functions/mistralai.py

@@ -1,11 +1,11 @@
 """
-Pixeltable [UDFs](https://pixeltable.readme.io/docs/user-defined-functions-udfs)
+Pixeltable UDFs
 that wrap various endpoints from the Mistral AI API. In order to use them, you must
 first `pip install mistralai` and configure your Mistral AI credentials, as described in
-the [Working with Mistral AI](https://pixeltable.readme.io/docs/working-with-mistralai) tutorial.
+the [Working with Mistral AI](https://docs.pixeltable.com/notebooks/integrations/working-with-mistralai) tutorial.
 """
 
-from typing import TYPE_CHECKING, Optional, TypeVar, Union
+from typing import TYPE_CHECKING, Any
 
 import numpy as np
 
@@ -16,7 +16,7 @@ from pixeltable.func.signature import Batch
 from pixeltable.utils.code import local_public_names
 
 if TYPE_CHECKING:
-    import mistralai.types.basemodel
+    import mistralai
 
 
 @register_client('mistral')
@@ -32,16 +32,7 @@ def _mistralai_client() -> 'mistralai.Mistral':
 
 @pxt.udf(resource_pool='request-rate:mistral')
 async def chat_completions(
-    messages: list[dict[str, str]],
-    *,
-    model: str,
-    temperature: Optional[float] = 0.7,
-    top_p: Optional[float] = 1.0,
-    max_tokens: Optional[int] = None,
-    stop: Optional[list[str]] = None,
-    random_seed: Optional[int] = None,
-    response_format: Optional[dict] = None,
-    safe_prompt: Optional[bool] = False,
+    messages: list[dict[str, str]], *, model: str, model_kwargs: dict[str, Any] | None = None
 ) -> dict:
     """
     Chat Completion API.
@@ -60,8 +51,8 @@ async def chat_completions(
     Args:
         messages: The prompt(s) to generate completions for.
         model: ID of the model to use. (See overview here: <https://docs.mistral.ai/getting-started/models/>)
-
-    For details on the other parameters, see: <https://docs.mistral.ai/api/#tag/chat>
+        model_kwargs: Additional keyword args for the Mistral `chat/completions` API.
+            For details on the available parameters, see: <https://docs.mistral.ai/api/#tag/chat>
 
     Returns:
         A dictionary containing the response and other metadata.
@@ -73,34 +64,20 @@ async def chat_completions(
         >>> messages = [{'role': 'user', 'content': tbl.prompt}]
         ... tbl.add_computed_column(response=completions(messages, model='mistral-latest-small'))
     """
+    if model_kwargs is None:
+        model_kwargs = {}
+
     Env.get().require_package('mistralai')
     result = await _mistralai_client().chat.complete_async(
         messages=messages,  # type: ignore[arg-type]
         model=model,
-        temperature=temperature,
-        top_p=top_p,
-        max_tokens=_opt(max_tokens),
-        stop=stop,
-        random_seed=_opt(random_seed),
-        response_format=response_format,  # type: ignore[arg-type]
-        safe_prompt=safe_prompt,
+        **model_kwargs,
     )
     return result.dict()
 
 
 @pxt.udf(resource_pool='request-rate:mistral')
-async def fim_completions(
-    prompt: str,
-    *,
-    model: str,
-    temperature: Optional[float] = 0.7,
-    top_p: Optional[float] = 1.0,
-    max_tokens: Optional[int] = None,
-    min_tokens: Optional[int] = None,
-    stop: Optional[list[str]] = None,
-    random_seed: Optional[int] = None,
-    suffix: Optional[str] = None,
-) -> dict:
+async def fim_completions(prompt: str, *, model: str, model_kwargs: dict[str, Any] | None = None) -> dict:
     """
     Fill-in-the-middle Completion API.
 
@@ -118,6 +95,8 @@ async def fim_completions(
     Args:
         prompt: The text/code to complete.
         model: ID of the model to use. (See overview here: <https://docs.mistral.ai/getting-started/models/>)
+        model_kwargs: Additional keyword args for the Mistral `fim/completions` API.
+            For details on the available parameters, see: <https://docs.mistral.ai/api/#tag/fim>
 
     For details on the other parameters, see: <https://docs.mistral.ai/api/#tag/fim>
 
@@ -130,18 +109,11 @@ async def fim_completions(
 
         >>> tbl.add_computed_column(response=completions(tbl.prompt, model='codestral-latest'))
     """
+    if model_kwargs is None:
+        model_kwargs = {}
+
     Env.get().require_package('mistralai')
-    result = await _mistralai_client().fim.complete_async(
-        prompt=prompt,
-        model=model,
-        temperature=temperature,
-        top_p=top_p,
-        max_tokens=_opt(max_tokens),
-        min_tokens=_opt(min_tokens),
-        stop=stop,
-        random_seed=_opt(random_seed),
-        suffix=_opt(suffix),
-    )
+    result = await _mistralai_client().fim.complete_async(prompt=prompt, model=model, **model_kwargs)
     return result.dict()
 
 
@@ -182,15 +154,6 @@ def _(model: str) -> ts.ArrayType:
     return ts.ArrayType((dimensions,), dtype=ts.FloatType())
 
 
-_T = TypeVar('_T')
-
-
-def _opt(arg: Optional[_T]) -> Union[_T, 'mistralai.types.basemodel.Unset']:
-    from mistralai.types import UNSET
-
-    return arg if arg is not None else UNSET
-
-
 __all__ = local_public_names(__name__)
 
 

pixeltable/functions/net.py

@@ -0,0 +1,70 @@
+"""
+Pixeltable UDF for converting media file URIs to presigned HTTP URLs.
+"""
+
+from pixeltable import exceptions as excs
+from pixeltable.func.udf import udf
+from pixeltable.utils.code import local_public_names
+from pixeltable.utils.object_stores import ObjectOps, ObjectPath, StorageTarget
+
+
+@udf
+def presigned_url(uri: str, expiration_seconds: int) -> str:
+    """
+    Convert a blob storage URI to a presigned HTTP URL for direct access.
+
+    Generates a time-limited, publicly accessible URL from cloud storage URIs
+    (S3, GCS, Azure, etc.) that can be used to serve media files over HTTP.
+
+    Note:
+        This function uses presigned URLs from storage providers. Provider-specific
+        limitations apply:
+
+        - Google Cloud Storage: maximum 7-day expiration
+        - AWS S3: requires proper region configuration
+        - Azure: subject to storage account access policies
+
+    Args:
+        uri: The media file URI (e.g., `s3://bucket/path`, `gs://bucket/path`, `azure://container/path`)
+        expiration_seconds: How long the URL remains valid
+
+    Returns:
+        A presigned HTTP URL for accessing the file
+
+    Raises:
+        Error: If the URI is a local file:// path
+
+    Examples:
+        Generate a presigned URL for a video column with 1-hour expiration:
+
+        >>> tbl.select(
+        ...     original_url=tbl.video.fileurl,
+        ...     presigned_url=pxtf.net.presigned_url(tbl.video.fileurl, 3600)
+        ... ).collect()
+    """
+    if not uri:
+        return uri
+
+    # Parse the object storage address from the URI
+    soa = ObjectPath.parse_object_storage_addr(uri, allow_obj_name=True)
+
+    # HTTP/HTTPS URLs are already publicly accessible
+    if soa.storage_target == StorageTarget.HTTP_STORE:
+        return uri
+
+    # For file:// URLs, we can't generate presigned URLs
+    if soa.storage_target == StorageTarget.LOCAL_STORE:
+        raise excs.Error(
+            'Cannot generate presigned URL for local file:// URLs. '
+            'Please use cloud storage (S3, GCS, Azure) for presigned URLs.'
+        )
+
+    store = ObjectOps.get_store(soa, allow_obj_name=True)
+    return store.create_presigned_url(soa, expiration_seconds)
+
+
+__all__ = local_public_names(__name__)
+
+
+def __dir__() -> list[str]:
+    return __all__

pixeltable/functions/ollama.py

@@ -1,4 +1,11 @@
-from typing import TYPE_CHECKING, Optional
+"""
+Pixeltable UDFs for Ollama local models.
+
+Provides integration with Ollama for running large language models locally,
+including chat completions and embeddings.
+"""
+
+from typing import TYPE_CHECKING
 
 import numpy as np
 
@@ -18,7 +25,7 @@ def _(host: str) -> 'ollama.Client':
     return ollama.Client(host=host)
 
 
-def _ollama_client() -> Optional['ollama.Client']:
+def _ollama_client() -> 'ollama.Client | None':
     try:
         return env.Env.get().get_client('ollama')
     except Exception:
@@ -33,10 +40,10 @@ def generate(
     suffix: str = '',
     system: str = '',
     template: str = '',
-    context: Optional[list[int]] = None,
+    context: list[int] | None = None,
     raw: bool = False,
-    format: Optional[str] = None,
-    options: Optional[dict] = None,
+    format: str | None = None,
+    options: dict | None = None,
 ) -> dict:
     """
     Generate a response for a given prompt with a provided model.
@@ -50,9 +57,9 @@ def generate(
         template: Prompt template to use.
         context: The context parameter returned from a previous call to `generate()`.
         raw: If `True`, no formatting will be applied to the prompt.
-        options: Additional options to pass to the `chat` call, such as `max_tokens`, `temperature`, `top_p`, and
+        options: Additional options for the Ollama `chat` call, such as `max_tokens`, `temperature`, `top_p`, and
             `top_k`. For details, see the
-            [Valid Parameters and Values](https://github.com/ollama/ollama/blob/main/docs/modelfile.md#valid-parameters-and-values)
+            [Valid Parameters and Values](https://github.com/ollama/ollama/blob/main/docs/modelfile.mdx#valid-parameters-and-values)
             section of the Ollama documentation.
     """
     env.Env.get().require_package('ollama')
@@ -77,9 +84,9 @@ def chat(
     messages: list[dict],
     *,
     model: str,
-    tools: Optional[list[dict]] = None,
-    format: Optional[str] = None,
-    options: Optional[dict] = None,
+    tools: list[dict] | None = None,
+    format: str | None = None,
+    options: dict | None = None,
 ) -> dict:
     """
     Generate the next message in a chat with a provided model.
@@ -91,7 +98,7 @@ def chat(
         format: The format of the response; must be one of `'json'` or `None`.
         options: Additional options to pass to the `chat` call, such as `max_tokens`, `temperature`, `top_p`, and
             `top_k`. For details, see the
-            [Valid Parameters and Values](https://github.com/ollama/ollama/blob/main/docs/modelfile.md#valid-parameters-and-values)
+            [Valid Parameters and Values](https://github.com/ollama/ollama/blob/main/docs/modelfile.mdx#valid-parameters-and-values)
             section of the Ollama documentation.
     """
     env.Env.get().require_package('ollama')
@@ -103,7 +110,7 @@ def chat(
 
 @pxt.udf(batch_size=16)
 def embed(
-    input: Batch[str], *, model: str, truncate: bool = True, options: Optional[dict] = None
+    input: Batch[str], *, model: str, truncate: bool = True, options: dict | None = None
 ) -> Batch[pxt.Array[(None,), pxt.Float]]:
     """
     Generate embeddings from a model.
@@ -115,7 +122,7 @@ def embed(
             Returns error if false and context length is exceeded.
         options: Additional options to pass to the `embed` call.
             For details, see the
-            [Valid Parameters and Values](https://github.com/ollama/ollama/blob/main/docs/modelfile.md#valid-parameters-and-values)
+            [Valid Parameters and Values](https://github.com/ollama/ollama/blob/main/docs/modelfile.mdx#valid-parameters-and-values)
             section of the Ollama documentation.
     """
     env.Env.get().require_package('ollama')