Components¶
ModelClient¶
Anthropic ModelClient integration with OpenAI SDK compatibility. |
|
Cohere ModelClient integration. |
|
Google GenAI ModelClient integration. |
|
Groq ModelClient integration. |
|
OpenAI ModelClient integration. |
|
Huggingface transformers ModelClient integration. |
|
Ollama ModelClient integration. |
|
Helpers for model client for integrating models and parsing the output. |
Retriever¶
BM25 retriever implementation. |
|
Semantic search/embedding-based retriever using FAISS. |
|
LLM as retriever module. |
|
Leverage a postgres database to store and retrieve documents. |
|
Reranking model using modelclient as a retriever. |
Output Parsers¶
The most commonly used output parsers for the Generator. |
|
DataClassParser will help users interact with LLMs even better than JsonOutputParser and YamlOutputParser with DataClass. |
Agent¶
Implementation and optimization of React agent. |
|
Agent component for building conversational AI agents with tool integration. |
|
Agent runner component for managing and executing agent workflows. |
|
System prompts and task descriptions for agent components. |
Data Process¶
Splitting texts is commonly used as a preprocessing step before embedding and retrieving texts. |
|
Helper components for data transformation such as embeddings and document splitting. |
Memory¶
Simple converation memory component for user-assistant conversations. |