github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2026-06-09 10:17:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: port various nit changes from wip-v0.4 (#32506)

Browse Source 
Lots of work that wasn't directly related to core
improvements/messages/testing functionality
This commit is contained in:
Mason Daugherty
2025-08-11 15:09:08 -04:00
committed by GitHub
parent 7db9e60601
commit ee4c2510eb
63 changed files with 2213 additions and 2862 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
libs/partners/ollama/langchain_ollama/llms.py
View File

@@ -61,26 +61,26 @@ class OllamaLLM(BaseLLM):
mirostat: Optional[int] = None
"""Enable Mirostat sampling for controlling perplexity.
(default: 0, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0)"""
(default: ``0``, ``0`` = disabled, ``1`` = Mirostat, ``2`` = Mirostat 2.0)"""
mirostat_eta: Optional[float] = None
"""Influences how quickly the algorithm responds to feedback
from the generated text. A lower learning rate will result in
slower adjustments, while a higher learning rate will make
the algorithm more responsive. (Default: 0.1)"""
the algorithm more responsive. (Default: ``0.1``)"""
mirostat_tau: Optional[float] = None
"""Controls the balance between coherence and diversity
of the output. A lower value will result in more focused and
coherent text. (Default: 5.0)"""
coherent text. (Default: ``5.0``)"""
num_ctx: Optional[int] = None
"""Sets the size of the context window used to generate the
next token. (Default: 2048)"""
next token. (Default: ``2048``)"""
num_gpu: Optional[int] = None
"""The number of GPUs to use. On macOS it defaults to 1 to
enable metal support, 0 to disable."""
"""The number of GPUs to use. On macOS it defaults to ``1`` to
enable metal support, ``0`` to disable."""
num_thread: Optional[int] = None
"""Sets the number of threads to use during computation.
@@ -90,20 +90,20 @@ class OllamaLLM(BaseLLM):
num_predict: Optional[int] = None
"""Maximum number of tokens to predict when generating text.
(Default: 128, -1 = infinite generation, -2 = fill context)"""
(Default: ``128``, ``-1`` = infinite generation, ``-2`` = fill context)"""
repeat_last_n: Optional[int] = None
"""Sets how far back for the model to look back to prevent
repetition. (Default: 64, 0 = disabled, -1 = num_ctx)"""
repetition. (Default: ``64``, ``0`` = disabled, ``-1`` = ``num_ctx``)"""
repeat_penalty: Optional[float] = None
"""Sets how strongly to penalize repetitions. A higher value (e.g., 1.5)
will penalize repetitions more strongly, while a lower value (e.g., 0.9)
will be more lenient. (Default: 1.1)"""
"""Sets how strongly to penalize repetitions. A higher value (e.g., ``1.5``)
will penalize repetitions more strongly, while a lower value (e.g., ``0.9``)
will be more lenient. (Default: ``1.1``)"""
temperature: Optional[float] = None
"""The temperature of the model. Increasing the temperature will
make the model answer more creatively. (Default: 0.8)"""
make the model answer more creatively. (Default: ``0.8``)"""
seed: Optional[int] = None
"""Sets the random number seed to use for generation. Setting this
@@ -115,21 +115,21 @@ class OllamaLLM(BaseLLM):
tfs_z: Optional[float] = None
"""Tail free sampling is used to reduce the impact of less probable
tokens from the output. A higher value (e.g., 2.0) will reduce the
impact more, while a value of 1.0 disables this setting. (default: 1)"""
tokens from the output. A higher value (e.g., ``2.0``) will reduce the
impact more, while a value of 1.0 disables this setting. (default: ``1``)"""
top_k: Optional[int] = None
"""Reduces the probability of generating nonsense. A higher value (e.g. 100)
will give more diverse answers, while a lower value (e.g. 10)
will be more conservative. (Default: 40)"""
"""Reduces the probability of generating nonsense. A higher value (e.g. ``100``)
will give more diverse answers, while a lower value (e.g. ``10``)
will be more conservative. (Default: ``40``)"""
top_p: Optional[float] = None
"""Works together with top-k. A higher value (e.g., 0.95) will lead
to more diverse text, while a lower value (e.g., 0.5) will
generate more focused and conservative text. (Default: 0.9)"""
"""Works together with top-k. A higher value (e.g., ``0.95``) will lead
to more diverse text, while a lower value (e.g., ``0.5``) will
generate more focused and conservative text. (Default: ``0.9``)"""
format: Literal["", "json"] = ""
"""Specify the format of the output (options: json)"""
"""Specify the format of the output (options: ``'json'``)"""
keep_alive: Optional[Union[int, str]] = None
"""How long the model will stay loaded into memory."""
@@ -139,33 +139,35 @@ class OllamaLLM(BaseLLM):
client_kwargs: Optional[dict] = {}
"""Additional kwargs to pass to the httpx clients.
These arguments are passed to both synchronous and async clients.
Use sync_client_kwargs and async_client_kwargs to pass different arguments
Use ``sync_client_kwargs`` and ``async_client_kwargs`` to pass different arguments
to synchronous and asynchronous clients.
"""
async_client_kwargs: Optional[dict] = {}
"""Additional kwargs to merge with client_kwargs before passing to the HTTPX
"""Additional kwargs to merge with ``client_kwargs`` before passing to the HTTPX
AsyncClient.
For a full list of the params, see the `HTTPX documentation <https://www.python-httpx.org/api/#asyncclient>`__.
"""
sync_client_kwargs: Optional[dict] = {}
"""Additional kwargs to merge with client_kwargs before passing to the HTTPX Client.
"""Additional kwargs to merge with ``client_kwargs`` before
passing to the HTTPX Client.
For a full list of the params, see the `HTTPX documentation <https://www.python-httpx.org/api/#client>`__.
"""
_client: Optional[Client] = PrivateAttr(default=None)
"""
The client to use for making requests.
"""
"""The client to use for making requests."""
_async_client: Optional[AsyncClient] = PrivateAttr(default=None)
"""
The async client to use for making requests.
"""
"""The async client to use for making requests."""
def _generate_params(
self,