is there a way i can use VLLM embedding endpoint?

any suggestion to build multimodel rag with 1TB of Data of jsons, pdf, docs, excel, , png and jpgs?

is there a tool which i can use to track indexing latency and get maximum stats while indexing

hey i want to use HuggingFaceInferenceAPIEmbedding, to call Text Embedding Inference that i have deployed on my virtual machine with access to GPU and this program will be on different Virtual Machine

read_code_file_tool = FunctionTool.from_defaults(fn=read_code_file)

query_engine_tools = [
QueryEngineTool(
query_engine=query_engine,
metadata=ToolMetadata(
name="codebase",
description=(
"Provides the entine code base."
"Use a detailed plain text question as input to the tool."
),
),
)
]

agent = OpenAIAgent.from_tools(tools=[query_engine_tools, read_code_file_tool],
llm=OpenAI(model="gpt-3.5-turbo-1106",temperature=0.1,api_key=str(config.OPENAI_API_KEY) ),
system_prompt=SYSTEM_PROMPT,
max_function_calls=10,
verbose=True)

gives this error: 2024-07-13 15:10:55.659 | DEBUG | core.engine.query:query_agent:34 - Error querying agent: 'list' object has no attribute 'metadata'
2024-07-13 15:10:55.706 | ERROR | core.routes.query:user_input:19 - Error processing request: too many values to unpack (expected 2)

Traceback (most recent call last):
File "/Users/bhavyagiri/Developer/studypod/agent/core/main.py", line 13, in <module>
indexing_local_repo(path,language)
File "/Users/bhavyagiri/Developer/studypod/agent/core/main.py", line 7, in indexing_local_repo
indexing.indexing_local_repo(path,language)
File "/Users/bhavyagiri/Developer/studypod/agent/core/engine/indexing.py", line 10, in indexing_local_repo
nodes = get_nodes(documents,language)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/bhavyagiri/Developer/studypod/agent/core/engine/utils.py", line 28, in get_nodes
splitter = CodeSplitter(
^^^^^^^^^^^^^
File "/Users/bhavyagiri/Developer/studypod/agent/.venv/lib/python3.11/site-packages/llama_index/core/node_parser/text/code.py", line 63, in init
parser = tree_sitter_languages.get_parser(language)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "tree_sitter_languages/core.pyx", line 19, in tree_sitter_languages.core.get_parser
File "tree_sitter_languages/core.pyx", line 14, in tree_sitter_languages.core.get_language
TypeError: init() takes exactly 1 argument (2 given)

is there way to indexed local repository similar to github reader which provides all the meta data?

https://docs.llamaindex.ai/en/stable/examples/query_engine/citation_query_engine/?h=citationqueryengine

i am try to increase similarity_top_k=20 but it tops to 10

hey man,
https://learn.deeplearning.ai/courses/building-agentic-rag-with-llamaindex/lesson/1/introduction
I was going through the course how to implement it with a vector store. And which vector you suggest for multi-document agent. Also looking for something cheap

Need help: Goal is to query Milvus colection with specific doc_ids,
meaning user enters a query and instead query whole collection i want to be queried to some specific doc ids

from ..config import settings
from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.core import Settings
from llama_index.vector_stores.milvus import MilvusVectorStore
from llama_index.llms.openai import OpenAI
from llama_index.core.vector_stores.types import VectorStoreQuery

Settings.embed_model = OpenAIEmbedding(model=settings.EMBEDDING_MODEL ,api_key=settings.OPENAI_KEY)
Settings.llm = OpenAI(temperature=0.1,api_key= settings.OPENAI_KEY)
vector_store = MilvusVectorStore(
collection_name=f"testing",
uri=settings.MILVUS_URI,
overwrite=False,
token=settings.MILVUS_TOKEN,
similarity_metric="L2",
dim=1536,
)


query = VectorStoreQuery(doc_ids=[ "/notebooks/notebooks/data/output/131/emails/2018_08_01_12_27_05_513065_David_Yeagy_140.txt"])
vector_store.query(query)

Implementing Advanced Fusion Retriever with Storage Context
I want to try Advance Fusion Retriever with Milvus Vector Store with already indexed data
https://docs.llamaindex.ai/en/stable/examples/low_level/fusion_retriever.html
It's not working with already indexed data, It wants to reindex all everytime

https://docs.llamaindex.ai/en/stable/examples/node_postprocessor/ColbertRerank/


can call this using api call from one vm to another vm?

2024-08-18 12:02:11.732 | ERROR | indexing.indexing_hugging:indexing:104 - Error injecting nodes: Got a larger chunk overlap (80) than chunk size (1024), should be smaller.

what's wrong?

is there a wat to parse a complex pdf extracting tables, images and text, maybe even llm (gpt4o or maybe a local multimodel one)?
maybe while reading files
@Logan M

2024-08-16 13:28:35.675 | ERROR | indexing.indexing_hugging:indexing:178 - Error indexing: 1 validation error for TextNode
embedding

any clue what's this error?
@WhiteFang_Jr @Logan M

Failed to load file /Users/bhavyagiri/Developer/studypod/indexing/hc_verma/hc_verma.pdf with error: RetryError[<Future at 0x127c61b50 state=finished raised PdfReadError>]. Skipping...

BadRequestError: Error code: 400 - {'error': {'message': "Invalid 'tools[0].function.name': string does not match pattern. Expected a string that matches the pattern '^[a-zA-Z0-9_-]+$'.", 'type': 'invalid_request_error', 'param': 'tools[0].function.name', 'code': 'invalid_value'}}

@Logan M

I am building a query engine with LlamaIndex, based on a large database of PDFs, and I would like to be able to retrieve the page number with the sources @Logan M

Can anyone help with storying Chat History?