feat: Add DeepSeek Harness ingestion - #14
Open
daoistvet wants to merge 1 commit into
Open
Conversation
Add `pipeline/dsh_to_rdf.py` — converts DeepSeek Harness event-log exports (`.jsonl` or `.zip` containing `session.jsonl`) to RDF Turtle with platform `deepseek-harness`. Mirrors `deepseek_to_rdf.py`: session/message/model nodes, linear parent chaining, assistant-text-only LLM triple extraction with the SQLite cache, and reified KnowledgeTriple provenance. Verification: - `python -m pipeline.dsh_to_rdf <input.jsonl|.zip> <output.ttl> --skip-extraction` — 32 user + 306 assistant messages, 2,309 structural triples, platform/title/model metadata correct. Since the release of Deepseek-V4 0731 Flash and Pro models, DeepSeek has released their official DeepSeek Harness (DSH), and chat.deepseek.com is fully integrated with DSH.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add
pipeline/dsh_to_rdf.py— converts DeepSeekHarness event-log exports (
.jsonlor.zipcontainingsession.jsonl) to RDF Turtlewith platform
deepseek-harness. Mirrorsdeepseek_to_rdf.py: session/message/model nodes,linear parent chaining, assistant-text-only LLM triple extraction with the SQLite cache,
and reified KnowledgeTriple provenance.
Verification:
python -m pipeline.dsh_to_rdf <input.jsonl|.zip> <output.ttl> --skip-extraction— 32 user + 306 assistant messages, 2,309 structural triples, platform/title/model metadata correct.Since the release of Deepseek-V4 0731 Flash and Pro models, DeepSeek has released their official DeepSeek Harness (DSH), and chat.deepseek.com is fully integrated with DSH.