I'm deploying an LLM in a server that has primitive features, including a feasible networking infrastructure. The owners of the servers were asking my client to split the cost of creating an API networking infrastructure to allow the LLM (hosted in their A100 GPUs) to other servers. The indicated that the estimated cost of developing this API infrastructure was going to be $12-15,000, developed in a time period of ~2.5 weeks with 4-5 developers with 90-95% chance of success. They wanted my client to go halfsies of the total cost, to which he agreed. A couple of week after the meeting, I proposed to him that I might be able to developed the networking infrastructure from their servers to any other server. To me it just seemed costly to spend $15,000 for an API. Having gained his trust, he agreed. So today, I spend about 2.5 hours on setting up a SSH connection from the Linux based environment of the server to my local computer. The attempt was to connect my Windsurf agentic IDE to the server so I didn't have to use the terminal and or the outdated VS code editor innately integrated in their UI. To by-pass the firewall of the server, I simply rellied on VPN service to make a safe encrypted connection between their server and my computer and.....BOOM! Now I can use my Windsurf agentic IDE from my computer to connect to their server in order vibe code (while as before, I could only hard-code, ew!). This now has to be tested on making inferential request to the deployed LLM but I think the current networking infrastructure will work on this. I should make a video 🤔 about this

In this agent masterclass, where can I get those folders, you showed how to download dependencies, but what is the source to these folders. I am not talking about finished project source code, but beginning state. Would be grateful, if anyone can guide. I am begineer. These folders: 1-basic-agent 2-tool-agent . . https://www.youtube.com/watch?v=P4VFL9nIaIA

I'm trying to develop a little SaaS. I've developed a prototype of the front end using the bolt platform, but when trying to connect it to the to the backed end to get real data instead of just having it stubbed out, I'm running into IAM issues accessing google maps and the solar api despite having enabled the API and having keys for them. I can't seem to figure out how to describe the IAM permissions to have a project that access them or makes them available externally to my front end whether a web app or the project I built with bolt. Any suggestions? I keep on going in circles with the docs and can't make any progress. Any help greatly appreciated. Thanks, pk

I am at that point where I need to shell out for more storage. Specificaly database storage. I run my frontend on Vercel and I was running with Supabase for a while, and as I was working on a mickey mouse project I just dumped it when I hit 0.5GB. Now I have ran into the same issue with Neon. Now I have to dig out the wallet. Theres only $5 between Neon and Supabase, but as I have not dug into either much I am surfing the 'wisdom of crowds' I am thinking Supabase is probably the better option, and its a simple switch in Drizzle ORM to swap over but Neon is Postgres and it has years behind it, but also the baggage. Does anyone wish to venture an opinion on which is better then the other and why? feel free to chime in @Brandon Hancock , @Maksym Liamin , @Bastian Venegas

@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(