Issue with Google_Adk agent
@Brandon Hancock - Follow up to earlier question today. After doing some more testing of my agent that consumes a class from a tool call that points to a chroma vector db. When we were on the call I displayed that issue where my chroma vector db wasn't returning any data from my call but when I ran the class with an instance locally it queried and returned results from chroma db without issue. I'm using persistentclient db with a path of ./chroma_db. I did a test and when I run locally the collection has a size of 225 but when the agent calls from adk_web run however it has a size of 0. Could it be an issue of path the adk_web agent is calling or something with permissions the agent doesn't have. Very odd issue. Pretty straight forward class. I have snippet of code below. Any suggestions??? The AI Agent calls getTechInfo2. And I did take your advice and add description to the tool class EmbedFeedsnew: def __init__(self, collection_name="arcade_issues"): self.client = chromadb.PersistentClient("./chroma_db") self.embedder = OpenAIEmbeddingFunction( api_key=os.getenv("OPENAI_API_KEY"), model_name="text-embedding-3-small" ) self.collection = self.client.get_or_create_collection( name="rollomarkdown", embedding_function=self.embedder ) def getTechinfo2(self,criteria:str) -> dict : # Directory containing your markdown files markdown_directory = "files" # Initialize ChromaDB client (using persistent client for saving to disk) chroma_client = self.client # Define the OpenAI embedding function #embedding_function = OpenAIEmbeddingFunction(api_key=os.environ.get("OPENAI_API_KEY"), model_name="text-embedding-3-small") embedding_function = self.embedder # Create or get a ChromaDB collection #collection = chroma_client.get_or_create_collection(name="rollomarkdown", embedding_function=embedding_function) collection = self.collection # Example query query_text = criteria print(f"The query test is: {query_text}") results = collection.query(