isaac47

Hi

Hi,

Please I really need help:

I use llama_index to query my nodes, ANd then verify if it works.

Plain Text

# code 1:

from llama_index import GPTVectorStoreIndex, ServiceContext

# storage_context = mongodb_storage_context()
embed_model = huggingface_embed_model()

# Set up the service context, i.e., the embedding model (and completion if used)
service_context = ServiceContext.from_defaults(embed_model=embed_model)

index_GPTVectorStoreIndex = GPTVectorStoreIndex(nodes=nodes,
                                service_context=service_context,
                                show_progress=True
                                )


# Code 2:

from llama_index import GPTSimpleKeywordTableIndex, ServiceContext

# storage_context = mongodb_storage_context()
embed_model = huggingface_embed_model()

# Set up the service context, i.e., the embedding model (and completion if used)
service_context = ServiceContext.from_defaults(embed_model=embed_model)

index_GPTSimpleKeywordTableIndex = GPTSimpleKeywordTableIndex(nodes=nodes,
                                service_context=service_context,
                                show_progress=True
                                )


# Verification: my metadata has url field

filter_nodes = [x for x in nodes if " " + query_term.lower() in x.text.lower()]
filter_nodes_urls = list(set([x.metadata["url"] for x in filter_nodes]))

retriever_nodes_GPTVectorStoreIndex_urls = []
for each_node in retriever_nodes_GPTVectorStoreIndex:
  for _node in nodes:
    if _node.id_ == each_node.id_:
      retriever_nodes_GPTVectorStoreIndex_urls.append(_node.metadata["url"])
      break

retriever_nodes_GPTVectorStoreIndex_urls = list(set(retriever_nodes_GPTVectorStoreIndex_urls))


retriever_nodes_GPTVectorStoreIndex_urls == filter_nodes_urls
False

4 comments

iisaac47

```

Plain Text

index = GPTSimpleKeywordTableIndex(nodes=nodes,
                            storage_context=storage_context,
                            service_context=service_context,
                            show_progress=True
                            )

retriever = index.as_retriever()
nodes = retriever.retrieve("formation")

Hello,

I need your help for my use case.

How to retrieve all matching nodes; not only 2 or similarity_top_k. I want to retrieve all nodes matching my query.

7 comments

iisaac47

Hello indexers,

Hello indexers,

I want to use weaviate client with llama-index. I have 2 questions:

I have a docker service hosting my weaviate indexes. How to connect to this client
I want to implement RAG via llamaIndex. But I don't understand how (in my use case where the index and the RAG will be host in differents service) to achieve it

23 comments

iisaac47

Hello

Hello,

Since yesterday I got an error with llama_index and llama_cpp to load llama-2 13B model

Plain Text

/usr/local/lib/python3.10/dist-packages/llama_index/indices/service_context.py in from_defaults(cls, llm_predictor, llm, prompt_helper, embed_model, node_parser, llama_logger, callback_manager, system_prompt, query_wrapper_prompt, chunk_size, chunk_overlap, context_window, num_output, chunk_size_limit)
    153                 raise ValueError("Cannot specify both llm and llm_predictor")
    154             llm = resolve_llm(llm)
--> 155         llm_predictor = llm_predictor or LLMPredictor(llm=llm)
    156         if isinstance(llm_predictor, LLMPredictor):
    157             llm_predictor.llm.callback_manager = callback_manager

/usr/local/lib/python3.10/dist-packages/llama_index/llm_predictor/base.py in __init__(self, llm, callback_manager, system_prompt, query_wrapper_prompt)
     93     ) -> None:
     94         """Initialize params."""
---> 95         self._llm = resolve_llm(llm)
     96 
     97         if callback_manager:

1 comment

iisaac47

```

Plain Text

similarity_top_k=1000
response_mode="no_text"
query_term = "formation"

query_engine = picone_index_llama.as_query_engine(
    retriever_mode="embedding", 
    service_context=service_context,
    verbose=True,
    similarity_top_k=similarity_top_k,
    response_mode=response_mode
)

query_engine.query(query_term)

----------------
ApiException: (400)
Reason: Bad Request
HTTP response headers: HTTPHeaderDict({'content-type': 'application/json', 'Content-Length': '103', 'date': 'Sat, 09 Sep 2023 10:45:46 GMT', 'x-envoy-upstream-service-time': '0', 'server': 'envoy', 'Via': '1.1 google', 'Alt-Svc': 'h3=":443"; ma=2592000,h3-29=":443"; ma=2592000'})
HTTP response body: {"code":3,"message":"Vector dimension 1536 does not match the dimension of the index 768","details":[]}

How to set the embedding size into my query engine?

13 comments

iisaac47

Mongo

Plain Text

from llama_index import load_index_from_storage
storage_context = StorageContext.from_defaults(
    docstore=MongoDocumentStore.from_uri(uri=mongo_url, db_name=db_name),
    index_store=MongoIndexStore.from_uri(uri=mongo_url, db_name=db_name),
)

index_test = load_index_from_storage(storage_context)

I try to load an index from my mongodb using this code. It's load someting but when trying to use it as query, it's return always 0 results.

Can you help me please?

6 comments

Find answers from the community

Hi

```

Hello indexers,

Hello

```

Mongo