From d12eb28c2d3857b4d39f26381f89ef7a61664d78 Mon Sep 17 00:00:00 2001 From: Safi Date: Thu, 18 Jun 2026 02:26:01 +0100 Subject: [PATCH] Note intra-file slicing in the JSON-truncation troubleshooting entry (#1369) Co-Authored-By: Claude Opus 4.8 (1M context) --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 918271be..e2be2749 100644 --- a/README.md +++ b/README.md @@ -471,7 +471,7 @@ GRAPHIFY_OLLAMA_NUM_CTX=8192 graphify extract ./docs --backend ollama --token-bu ``` **`LLM returned invalid JSON` / `Unterminated string` warnings** -The model's JSON response hit its output-token limit and was cut off mid-string. graphify auto-recovers (it splits the chunk and re-extracts the halves), so these warnings are noisy but not data loss. To reduce the churn, raise the output cap or shrink each chunk's output: +The model's JSON response hit its output-token limit and was cut off mid-string. graphify auto-recovers (it splits the chunk and re-extracts the halves, and an oversized single document is first sliced at heading/paragraph boundaries so the whole file is still covered), so these warnings are noisy but not data loss. To reduce the churn, raise the output cap or shrink each chunk's output: ```bash GRAPHIFY_MAX_OUTPUT_TOKENS=16384 graphify extract . --mode deep # lift the cap graphify extract . --mode deep --token-budget 4000 # smaller input chunks -> smaller output