diff options
| author | sigoden <sigoden@gmail.com> | 2024-06-26 08:18:58 +0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-06-26 08:18:58 +0800 |
| commit | 95bad975f4fb47fe86df1837660a1341009ea12a (patch) | |
| tree | 1d88411576d07d6e46311ac726a8577d1e5e38f2 /config.example.yaml | |
| parent | 34a6d13fb6e492860e1340ab7a97cbd1bdeb9d4d (diff) | |
| download | aichat-95bad975f4fb47fe86df1837660a1341009ea12a.tar.gz | |
feat: custom rag document loaders (#650)
Diffstat (limited to 'config.example.yaml')
| -rw-r--r-- | config.example.yaml | 23 |
1 files changed, 15 insertions, 8 deletions
diff --git a/config.example.yaml b/config.example.yaml index 43c3876..286bb83 100644 --- a/config.example.yaml +++ b/config.example.yaml @@ -41,14 +41,21 @@ agents: dangerously_functions_filter: null # ---- RAG ---- -rag_embedding_model: null # Specifies the embedding model to use -rag_reranker_model: null # Specifies the rerank model to use -rag_top_k: 4 # Specifies the number of documents to retrieve -rag_chunk_size: null # Specifies the chunk size -rag_chunk_overlap: null # Specifies the chunk overlap -rag_min_score_vector_search: 0 # Specifies the minimum relevance score for vector-based searching -rag_min_score_keyword_search: 0 # Specifies the minimum relevance score for keyword-based searching -rag_min_score_rerank: 0 # Specifies the minimum relevance score for reranking +rag_embedding_model: null # Specifies the embedding model to use +rag_reranker_model: null # Specifies the rerank model to use +rag_top_k: 4 # Specifies the number of documents to retrieve +rag_chunk_size: null # Specifies the chunk size +rag_chunk_overlap: null # Specifies the chunk overlap +rag_min_score_vector_search: 0 # Specifies the minimum relevance score for vector-based searching +rag_min_score_keyword_search: 0 # Specifies the minimum relevance score for keyword-based searching +rag_min_score_rerank: 0 # Specifies the minimum relevance score for reranking +# Defines document loaders +rag_document_loaders: + # You can add more loaders, here is the syntax: + # <file-extension>: <command-to-load-the-file> + pdf: 'pdftotext $1 -' # Load .pdf file + docx: 'pandoc --to plain $1' # Load .docx file + # Defines the query structure using variables like __CONTEXT__ and __INPUT__ to tailor searches to specific needs rag_template: | Use the following context as your learned knowledge, inside <context></context> XML tags. |