LangGraph raises TypeError on function node output This morning my LangGraph flow crashed after a new tool node. TypeError: cannot unpack non-iterable ToolInvocation object Python 3.12, langgraph 0.3.8, langchain 0.2.1. The node function returned a ToolInvocation instead of (ToolInvocation, kwargs); API changed in 0.3.7. Fix:

HuggingFace pipeline returns empty string with Gemini 1.5 Pro Last week a quick text‑generation pipeline came back blank every call. from transformers import pipeline gen = pipeline("text-generation", model="google/gemini-1.5-pro") print(gen("hi")) Result: [{'generated_text': ''}] Transformers 4.42.1, Python 3.10, macOS Sonoma. No errors. Network call to Google succeeded, payload returned text.

vLLM tokenizer mismatch on finetuned Mistral model Spent the afternoon benchmarking a Mistral‑7B finetune with vLLM. First prompt returned gibberish tokens. from vllm import LLM llm = LLM(model="mistralai/Mistral-7B-Instruct-v0.2", tokenizer="mistralai/Mistral-7B-Instruct-v0.2") print(llm.generate("Hello")) Output contained repeating � characters. Ubuntu 22.04, CUDA 12.1, vllm 0.4.3, transformers 4.40.0, Python 3.11. Checkpoint trained with --trust-remote-code.

OpenRouter API response missing ’text’ in JSON payload Testing OpenRouter with gpt‑4 turbo. Request looked fine but the completion field came back empty: { "id":"chatcmpl-xxxx", "choices":[ {"index":0,"logprobs":null,"finish_reason":"stop"} ], "model":"gpt-4-turbo-preview", "usage":{...} } No choices[0].message.content. cURL request: curl https://openrouter.ai/api/v1/chat/completions -H "Authorization: Bearer $OPENROUTER_KEY" -H "Content-Type: application/json" -d '{"model":"gpt-4-turbo-preview","messages":[{"role":"user","content":"hi"}]}' Turns out OpenRouter now requires the header HTTP-Referer (your site) and X-Title (app name) for non‑localhost keys.

langchain.tools.SerpAPIWrapper throws Invalid API Key despite valid key Spotted this today while wiring a quick search tool. from langchain.tools import SerpAPIWrapper tool = SerpAPIWrapper() print(tool.run("Sydney weather")) Console spat back: SerpApiError: Invalid API key Key worked in curl. Quota fine. Python 3.11, langchain 0.1.12, serpapi 0.6.2. Environment variable SERPAPI_API_KEY was set.

Gemini Pro API throws 403 in Postman with valid key Tried hitting the Gemini Pro v1/models/gemini-pro:generateContent endpoint in Postman. Headers set: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-pro:generateContent?key=AIzaSy... Content-Type: application/json Response: { "error": { "code": 403, "message": "The caller does not have permission", "status": "PERMISSION_DENIED" } } Key freshly created, billing enabled, Generative Language API enabled.

Mistral inference on local GPU hits OOM with 13B model Last week I tried the 13B Mistral model on a single RTX 3060 (12 GB). python main.py crashed instantly: RuntimeError: CUDA out of memory. Tried to allocate 10.2 GiB torch.cuda.mem_get_info() showed only 11.7 GB free.

Ollama install on Windows missing symlink permissions Setting up Ollama on Windows 11 this morning. Installer finished, but every ollama run threw: open C:\Users\Me\.ollama\models\registry.json: CreateFile symlink \?\C:\Users\Me\.ollama\models\registry.json: Access is denied. Fresh PowerShell session, Admin prompt. Windows Developer Mode was disabled.

langchain.chains.ConversationalRetrievalChain() fails with FAISS store Tried to wire ConversationalRetrievalChain with a FAISS vector store. The constructor crashed. ValueError: Provided embeddings are incompatible with stored index dimension Embeddings built with sentence-transformers/all-MiniLM-L6-v2, dim 384. LangChain 0.0.286, faiss‑cpu 1.7.4, Python 3.11 on macOS.

Gradio app stalls on LLaMA 2 inference with 8‑bit quant Spun up a quick Gradio demo around LLaMA‑2‑7B‑chat‑hf using 8‑bit quantisation. Prompt box froze after I hit “Submit”; no tokens returned. model = AutoModelForCausalLM.from_pretrained( "meta-llama/Llama-2-7b-chat-hf", load_in_8bit=True, device_map="auto" ) GPU RTX 3090, CUDA 11.8, torch 2.0.1+cu118, bitsandbytes 0.41.0, transformers 4.31.0. Gradio 3.34.0. Linux Mint 21.2.