llama index Raptor

[deepakpapu]

How to load persistent vector store with raptorretriver.

[dosubot[bot]]

To load a persistent vector store with RaptorRetriever, use the from_persist_dir method of the RaptorRetriever class. Here's a quick example:

retriever = RaptorRetriever.from_persist_dir(
    persist_dir="path_to_your_persisted_store_directory",
    embed_model=your_embed_model_instance
)

Replace "path_to_your_persisted_store_directory" with the actual path to your persisted store directory and your_embed_model_instance with your embedding model instance. This method initializes a RaptorRetriever with a previously persisted vector store for retrieval operations.

Be aware of potential errors such as NotImplementedError, pickle.PickleError, or a generic Exception due to issues like file not found, permissions, or data corruption. These are handled within the RaptorRetriever class and related components, ensuring robust loading of your vector store.

For more detailed implementation and handling of exceptions, you might want to look into the RaptorRetriever class source code and related documentation.

Details

Sources

• llama-index-packs/llama-index-packs-raptor/llama_index/packs/raptor/base.py
• llama-index-core/llama_index/core/objects/base_node_mapping.py
• llama-index-core/llama_index/core/objects/base.py

About Dosu
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

To continue the conversation, mention @dosu.

[amMistic]

I am using langchain_groq's "chatgroq" api for using llama3 llm model, and RaptorRetriever as retriever but i keep getting an error

Traceback (most recent call last):
  File "D:\LLM_Txtbuk\src\rag.py", line 79, in get_vector_store
    RaptorPack(
  File "D:\LLM_Txtbuk\.txtbuk\Lib\site-packages\llama_index\packs\raptor\base.py", line 348, in __init__
    self.retriever = RaptorRetriever(
                     ^^^^^^^^^^^^^^^^
  File "D:\LLM_Txtbuk\.txtbuk\Lib\site-packages\llama_index\packs\raptor\base.py", line 128, in __init__
    self.summary_module = summary_module or SummaryModule(llm=llm)
                                            ^^^^^^^^^^^^^^^^^^^^^^
  File "D:\LLM_Txtbuk\.txtbuk\Lib\site-packages\llama_index\packs\raptor\base.py", line 67, in __init__
    response_synthesizer = get_response_synthesizer(
                           ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\LLM_Txtbuk\.txtbuk\Lib\site-packages\llama_index\core\response_synthesizers\factory.py", line 62, in get_response_synthesizer
    or PromptHelper.from_llm_metadata(
       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\LLM_Txtbuk\.txtbuk\Lib\site-packages\llama_index\core\indices\prompt_helper.py", line 120, in from_llm_metadata
    context_window = llm_metadata.context_window
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'context_window

Can anybody help me with that?