Archives/langchain
2
0
Fork 1
mirror of https://github.com/hwchase17/langchain synced 2024-11-06 03:20:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

Updates fireworks (#8765)

Browse Source 
<!-- Thank you for contributing to LangChain!

Replace this comment with:
  - Description: Updates to Fireworks Documentation, 
  - Issue: N/A,
  - Dependencies: N/A,
  - Tag maintainer: @rlancemartin,

---------

Co-authored-by: Raj Janardhan <rajjanardhan@Rajs-Laptop.attlocal.net>
This commit is contained in:
rjanardhan3 2023-08-04 10:32:22 -07:00 committed by GitHub
parent 8c35fcb571
commit affaaea87b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 24 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
docs/extras/integrations/llms/Fireworks.ipynb
View File

@ -7,7 +7,7 @@
"source": [
"# Fireworks\n",
"\n",
">[Fireworks](https://www.fireworks.ai/) is an AI startup focused on accelerating product development on generative AI by creating an innovative AI experiment and production platform. \n",
">[Fireworks](https://app.fireworks.ai/) accelerates product development on generative AI by creating an innovative AI experiment and production platform. \n",
"\n",
"This example goes over how to use LangChain to interact with `Fireworks` models."
]
@ -37,7 +37,7 @@
"\n",
"Contact Fireworks AI for the an API Key to access our models\n",
"\n",
"Set up your model using a model id. If the model is not set, the default model is fireworks-llama-v2-13b-chat."
"Set up your model using a model id. If the model is not set, the default model is fireworks-llama-v2-7b-chat."
]
},
{
@ -49,7 +49,7 @@
"source": [
"# Initialize a Fireworks LLM\n",
"os.environ['FIREWORKS_API_KEY'] = \"\" #change this to your own API KEY\n",
"llm = Fireworks(model_id=\"fireworks-llama-v2-13b-chat\")"
"llm = Fireworks(model_id=\"accounts/fireworks/models/fireworks-llama-v2-13b-chat\")"
]
},
{
@ -73,11 +73,10 @@
"You can use the LLMs to call the model for specified prompt(s). \n",
"\n",
"Current Specified Models: \n",
"* fireworks-falcon-7b, fireworks-falcon-40b-w8a16\n",
"* fireworks-guanaco-30b, fireworks-guanaco-33b-w8a16\n",
"* fireworks-llama-7b, fireworks-llama-13b, fireworks-llama-30b-w8a16\n",
"* fireworks-llama-v2-13b, fireworks-llama-v2-13b-chat, fireworks-llama-v2-13b-w8a16, fireworks-llama-v2-13b-chat-w8a16\n",
"* fireworks-llama-v2-7b, fireworks-llama-v2-7b-chat, fireworks-llama-v2-7b-w8a16, fireworks-llama-v2-7b-chat-w8a16"
"* accounts/fireworks/models/fireworks-falcon-7b, accounts/fireworks/models/fireworks-falcon-40b-w8a16\n",
"* accounts/fireworks/models/fireworks-starcoder-1b-w8a16-1gpu, accounts/fireworks/models/fireworks-starcoder-3b-w8a16-1gpu, accounts/fireworks/models/fireworks-starcoder-7b-w8a16-1gpu, accounts/fireworks/models/fireworks-starcoder-16b-w8a16 \n",
"* accounts/fireworks/models/fireworks-llama-v2-13b, accounts/fireworks/models/fireworks-llama-v2-13b-chat, accounts/fireworks/models/fireworks-llama-v2-13b-w8a16, accounts/fireworks/models/fireworks-llama-v2-13b-chat-w8a16\n",
"* accounts/fireworks/models/fireworks-llama-v2-7b, accounts/fireworks/models/fireworks-llama-v2-7b-chat, accounts/fireworks/models/fireworks-llama-v2-7b-w8a16, accounts/fireworks/models/fireworks-llama-v2-7b-chat-w8a16, accounts/fireworks/models/fireworks-llama-v2-70b-chat-4gpu"
]
},
{
@ -147,7 +146,7 @@
],
"source": [
"#setting parameters: model_id, temperature, max_tokens, top_p\n",
"llm = Fireworks(model_id=\"fireworks-llama-v2-13b-chat\", temperature=0.7, max_tokens=15, top_p=1.0)\n",
"llm = Fireworks(model_id=\"accounts/fireworks/models/fireworks-llama-v2-13b-chat\", temperature=0.7, max_tokens=15, top_p=1.0)\n",
"print(llm(\"What's the weather like in Kansas City in December?\"))"
]
},

2
docs/extras/integrations/providers/fireworks.md
View File

@ -19,4 +19,4 @@ llm = Fireworks(model="fireworks-llama-v2-13b-chat", max_tokens=256, temperature
llm("Name 3 sports.")
```
For a more detailed walkthrough, see [here](/docs/extras/modules/model_io/models/llms/integrations/Fireworks.ipynb).
For a more detailed walkthrough, see [here](/docs/integrations/llms/Fireworks).

6
libs/langchain/langchain/llms/fireworks.py
View File

@ -28,7 +28,9 @@ logger = logging.getLogger(__name__)
class BaseFireworks(BaseLLM):
"""Wrapper around Fireworks large language models."""
model_id: str = Field("fireworks-llama-v2-7b-chat", alias="model")
model_id: str = Field(
"accounts/fireworks/models/fireworks-llama-v2-7b-chat", alias="model"
)
"""Model name to use."""
temperature: float = 0.7
"""What sampling temperature to use."""
@ -175,7 +177,7 @@ class FireworksChat(BaseLLM):
fireworkschat = FireworksChat(model_id=""fireworks-llama-v2-13b-chat"")
"""
model_id: str = "fireworks-llama-v2-7b-chat"
model_id: str = "accounts/fireworks/models/fireworks-llama-v2-7b-chat"
"""Model name to use."""
temperature: float = 0.7
"""What sampling temperature to use."""

20
libs/langchain/tests/integration_tests/llms/test_fireworks.py
View File

@ -21,7 +21,9 @@ from langchain.vectorstores import DeepLake
def test_fireworks_call() -> None:
"""Test valid call to fireworks."""
llm = Fireworks(model_id="fireworks-llama-v2-13b-chat", max_tokens=900)
llm = Fireworks(
model_id="accounts/fireworks/models/fireworks-llama-v2-13b-chat", max_tokens=900
)
output = llm("What is the weather in NYC")
assert isinstance(output, str)
@ -136,17 +138,17 @@ def test_fireworkschat_chain() -> None:
_EXPECTED_NUM_TOKENS = {
"fireworks-llama-v2-13b": 17,
"fireworks-llama-v2-7b": 17,
"fireworks-llama-v2-13b-chat": 17,
"fireworks-llama-v2-7b-chat": 17,
"accounts/fireworks/models/fireworks-llama-v2-13b": 17,
"accounts/fireworks/models/fireworks-llama-v2-7b": 17,
"accounts/fireworks/models/fireworks-llama-v2-13b-chat": 17,
"accounts/fireworks/models/fireworks-llama-v2-7b-chat": 17,
}
_MODELS = models = [
"fireworks-llama-v2-13b",
"fireworks-llama-v2-7b",
"fireworks-llama-v2-13b-chat",
"fireworks-llama-v2-7b-chat",
"accounts/fireworks/models/fireworks-llama-v2-13b",
"accounts/fireworks/models/fireworks-llama-v2-7b",
"accounts/fireworks/models/fireworks-llama-v2-13b-chat",
"accounts/fireworks/models/fireworks-llama-v2-7b-chat",
]