Skip to content

Updated available chat models #362

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Updated available chat models #362

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
44ebbf6
Updated the models available to the latest from the respective provid…
leowalker89 Aug 7, 2024
185e9ed
Updated models available on front and backend
leowalker89 Aug 7, 2024
c98d8dd
cleaned up descriptions
leowalker89 Aug 7, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 11 additions & 11 deletions backend/graph.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,8 +103,8 @@
OPENAI_MODEL_KEY = "openai_gpt_4o_mini"
ANTHROPIC_MODEL_KEY = "anthropic_claude_3_haiku"
FIREWORKS_MIXTRAL_MODEL_KEY = "fireworks_mixtral"
GOOGLE_MODEL_KEY = "google_gemini_pro"
COHERE_MODEL_KEY = "cohere_command"
GOOGLE_MODEL_KEY = "google_gemini_flash"
COHERE_MODEL_KEY = "cohere_command_r"
GROQ_LLAMA_3_MODEL_KEY = "groq_llama_3"

FEEDBACK_KEYS = ["user_score", "user_click"]
Expand Down Expand Up @@ -147,20 +147,20 @@ class AgentState(TypedDict):
max_tokens=16384,
fireworks_api_key=os.environ.get("FIREWORKS_API_KEY", "not_provided"),
)
gemini_pro = ChatGoogleGenerativeAI(
model="gemini-pro",
gemini_flash = ChatGoogleGenerativeAI(
model="gemini-1.5-flash",
temperature=0,
max_output_tokens=16384,
convert_system_message_to_human=True,
google_api_key=os.environ.get("GOOGLE_API_KEY", "not_provided"),
)
cohere_command = ChatCohere(
model="command",
cohere_command_r = ChatCohere(
model="command-r",
temperature=0,
cohere_api_key=os.environ.get("COHERE_API_KEY", "not_provided"),
)
groq_llama3 = ChatGroq(
model="llama3-70b-8192",
model="llama-3.1-70b-versatile",
temperature=0,
groq_api_key=os.environ.get("GROQ_API_KEY", "not_provided"),
)
Expand All @@ -172,17 +172,17 @@ class AgentState(TypedDict):
**{
ANTHROPIC_MODEL_KEY: claude_3_haiku,
FIREWORKS_MIXTRAL_MODEL_KEY: fireworks_mixtral,
GOOGLE_MODEL_KEY: gemini_pro,
COHERE_MODEL_KEY: cohere_command,
GOOGLE_MODEL_KEY: gemini_flash,
COHERE_MODEL_KEY: cohere_command_r,
GROQ_LLAMA_3_MODEL_KEY: groq_llama3,
},
).with_fallbacks(
[
gpt_4o_mini,
claude_3_haiku,
fireworks_mixtral,
gemini_pro,
cohere_command,
gemini_flash,
cohere_command_r,
groq_llama3,
]
)
Expand Down
8 changes: 4 additions & 4 deletions frontend/app/components/ChatWindow.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -322,16 +322,16 @@ export function ChatWindow() {
<option value="anthropic_claude_3_haiku">
Claude 3 Haiku
</option>
<option value="google_gemini_pro">
Google Gemini Pro
<option value="google_gemini_flash">
Google Gemini 1.5 Flash
</option>
<option value="fireworks_mixtral">
Mixtral (via Fireworks.ai)
</option>
<option value="groq_llama_3">
Llama 3 (via Groq.com)
Llama 3.1 (via Groq.com)
</option>
<option value="cohere_command">Cohere</option>
<option value="cohere_command_r">Cohere</option>
</Select>
)}
</div>
Expand Down