Archives/langchain
2
0
Fork 1
mirror of https://github.com/hwchase17/langchain synced 2024-11-10 01:10:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

community[patch]: Updating default PPLX model to supported llama-3.1 model. (#25643)

Browse Source 
# Issue

As of late July, Perplexity [no longer supports Llama 3
models](https://docs.perplexity.ai/changelog/introducing-new-and-improved-sonar-models).

# Description

This PR updates the default model and doc examples to reflect their
latest supported model. (Mostly updating the same places changed by
#23723.)

# Twitter handle

`@acompa_` on behalf of the team at Not Diamond. Check us out
[here](https://notdiamond.ai).

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
This commit is contained in:
Alejandro Companioni 2024-08-23 04:33:30 -04:00 committed by GitHub
parent 163ef35dd1
commit bcd5842b5d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 12 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
docs/docs/integrations/chat/perplexity.ipynb
View File

@ -62,6 +62,12 @@
"id": "97a8ce3a",
"metadata": {},
"source": [
"The code provided assumes that your PPLX_API_KEY is set in your environment variables. If you would like to manually specify your API key and also choose a different model, you can use the following code:\n",
"\n",
"```python\n",
"chat = ChatPerplexity(temperature=0, pplx_api_key=\"YOUR_API_KEY\", model=\"llama-3.1-sonar-small-128k-online\")\n",
"```\n",
"\n",
"You can check a list of available models [here](https://docs.perplexity.ai/docs/model-cards). For reproducibility, we can set the API key dynamically by taking it as an input in this notebook."
]
},
@ -92,7 +98,7 @@
},
"outputs": [],
"source": [
"chat = ChatPerplexity(temperature=0, model=\"llama-3-sonar-small-32k-online\")"
"chat = ChatPerplexity(temperature=0, model=\"llama-3.1-sonar-small-128k-online\")"
]
},
{
@ -160,7 +166,7 @@
}
],
"source": [
"chat = ChatPerplexity(temperature=0, model=\"llama-3-sonar-small-32k-online\")\n",
"chat = ChatPerplexity(temperature=0, model=\"llama-3.1-sonar-small-128k-online\")\n",
"prompt = ChatPromptTemplate.from_messages([(\"human\", \"Tell me a joke about {topic}\")])\n",
"chain = prompt | chat\n",
"response = chain.invoke({\"topic\": \"cats\"})\n",
@ -209,7 +215,7 @@
}
],
"source": [
"chat = ChatPerplexity(temperature=0.7, model=\"llama-3-sonar-small-32k-online\")\n",
"chat = ChatPerplexity(temperature=0.7, model=\"llama-3.1-sonar-small-128k-online\")\n",
"prompt = ChatPromptTemplate.from_messages(\n",
" [(\"human\", \"Give me a list of famous tourist attractions in Pakistan\")]\n",
")\n",

6
libs/community/langchain_community/chat_models/perplexity.py
View File

@ -55,20 +55,20 @@ class ChatPerplexity(BaseChatModel):
from langchain_community.chat_models import ChatPerplexity
chat = ChatPerplexity(
model="llama-3-sonar-small-32k-online",
model="llama-3.1-sonar-small-128k-online",
temperature=0.7,
)
"""
client: Any #: :meta private:
model: str = "llama-3-sonar-small-32k-online"
model: str = "llama-3.1-sonar-small-128k-online"
"""Model name."""
temperature: float = 0.7
"""What sampling temperature to use."""
model_kwargs: Dict[str, Any] = Field(default_factory=dict)
"""Holds any model parameters valid for `create` call not explicitly specified."""
pplx_api_key: Optional[str] = Field(None, alias="api_key")
"""Base URL path for API requests,
"""Base URL path for API requests,
leave blank if not using a proxy or service emulator."""
request_timeout: Optional[Union[float, Tuple[float, float]]] = Field(
None, alias="timeout"