semantic-router
semantic-router copied to clipboard
aurelio-labs
Superfast AI decision making and intelligent processing of multi-modal data.
Maybe "text-embedding-3-small" should be the new default, considering the price/quality improvements over ada v2 that is now the default embedding for that service.
https://github.com/aurelio-labs/semantic-router/blob/main/docs/03-basic-langchain-agent.ipynb In the above notebook, there is small bug where we are importing ChatOpenAI class from deprecated version of LangChain `langchain.chat_model` not from `langchain_openai`. Had to change: ```python from langchain.agents...
How to use the splitters with langchain loaders for huge amount of unstructured data? did someone try using that? and can we have the metadata with splitter chunks?
### Summary This pull request introduces the GigaChatEncoder class, a new encoder for generating embeddings using the GigaChat API. The implementation includes initialization, embedding generation, and error handling functionalities. ###...
Do you have more detailed documents? 1. How do I set the threshold in RouteLayer after fitting? I don't want to retrain it every time I run it. `rl.fit(X=X, y=y)`...
### **PR Type** enhancement ___ ### **Description** - Introduced a new `function_schemas` parameter to the `add` method in the base index class. - Enhanced the `PineconeRecord` class to include a...
When running: ``` from semantic_router.encoders import HuggingFaceEncoder model = "nomic-ai/nomic-embed-text-v1.5" encoder = HuggingFaceEncoder(name=t_model) ``` I need to set an additional arg `"trust_remote_code=True"` in order to use the Hugging Face model....
HuggingFace models are causing errors to be raised, do not seem to be legit errors but need to be resolved in CI. 
With #381 we can start adding dynamic routes and support for function calls to our ollama LLM implementation
Metadata
Owner
Metadata
Superfast AI decision making and intelligent processing of multi-modal data.