Skip to content

armgit / dspy

Public Imported from GitHub
0

DSPy: The framework for programming—not prompting—language models

Python

Replace ujson with orjson in docs (#9148)

Toshiki Ogimotobecb4c9e849a
diff --git a/docs/docs/tutorials/cache/index.md b/docs/docs/tutorials/cache/index.md
index f2cc35727..275882b3e 100644
--- a/docs/docs/tutorials/cache/index.md
+++ b/docs/docs/tutorials/cache/index.md
@@ -153,7 +153,7 @@ class CustomCache(dspy.clients.Cache):
def cache_key(self, request: dict[str, Any], ignored_args_for_cache_key: Optional[list[str]] = None) -> str:
messages = request.get("messages", [])
- return sha256(ujson.dumps(messages, sort_keys=True).encode()).hexdigest()
+ return sha256(orjson.dumps(messages, option=orjson.OPT_SORT_KEYS)).hexdigest()
dspy.cache = CustomCache(enable_disk_cache=True, enable_memory_cache=True, disk_cache_dir=dspy.clients.DISK_CACHE_DIR)
```
@@ -188,7 +188,7 @@ import dspy
import os
import time
from typing import Dict, Any, Optional
-import ujson
+import orjson
from hashlib import sha256
os.environ["OPENAI_API_KEY"] = "{your_openai_key}"
@@ -199,7 +199,7 @@ class CustomCache(dspy.clients.Cache):
def cache_key(self, request: dict[str, Any], ignored_args_for_cache_key: Optional[list[str]] = None) -> str:
messages = request.get("messages", [])
- return sha256(ujson.dumps(messages, sort_keys=True).encode()).hexdigest()
+ return sha256(orjson.dumps(messages, option=orjson.OPT_SORT_KEYS)).hexdigest()
dspy.cache = CustomCache(enable_disk_cache=True, enable_memory_cache=True, disk_cache_dir=dspy.clients.DISK_CACHE_DIR)
diff --git a/docs/docs/tutorials/deployment/index.md b/docs/docs/tutorials/deployment/index.md
index fea3d0c4f..58c709e23 100644
--- a/docs/docs/tutorials/deployment/index.md
+++ b/docs/docs/tutorials/deployment/index.md
@@ -83,7 +83,7 @@ You can configure the async capacity using the new `async_max_workers` setting.
data = {"prediction": value.labels().toDict()}
elif isinstance(value, litellm.ModelResponse):
data = {"chunk": value.json()}
- yield f"data: {ujson.dumps(data)}\n\n"
+ yield f"data: {orjson.dumps(data).decode()}\n\n"
yield "data: [DONE]\n\n"
return StreamingResponse(generate(), media_type="text/event-stream")
diff --git a/docs/docs/tutorials/multihop_search/index.ipynb b/docs/docs/tutorials/multihop_search/index.ipynb
index ca9ae098c..030151357 100644
--- a/docs/docs/tutorials/multihop_search/index.ipynb
+++ b/docs/docs/tutorials/multihop_search/index.ipynb
@@ -126,12 +126,12 @@
}
],
"source": [
- "import ujson\n",
+ "import orjson\n",
"corpus = []\n",
"\n",
"with open(\"wiki.abstracts.2017.jsonl\") as f:\n",
" for line in f:\n",
- " line = ujson.loads(line)\n",
+ " line = orjson.loads(line)\n",
" corpus.append(f\"{line['title']} | {' '.join(line['text'])}\")\n",
"\n",
"len(corpus)"
diff --git a/docs/docs/tutorials/rag/index.ipynb b/docs/docs/tutorials/rag/index.ipynb
index fe29371e7..47d6223f7 100644
--- a/docs/docs/tutorials/rag/index.ipynb
+++ b/docs/docs/tutorials/rag/index.ipynb
@@ -264,14 +264,14 @@
"metadata": {},
"outputs": [],
"source": [
- "import ujson\n",
+ "import orjson\n",
"from dspy.utils import download\n",
"\n",
"# Download question--answer pairs from the RAG-QA Arena \"Tech\" dataset.\n",
"download(\"https://huggingface.co/dspy/cache/resolve/main/ragqa_arena_tech_examples.jsonl\")\n",
"\n",
"with open(\"ragqa_arena_tech_examples.jsonl\") as f:\n",
- " data = [ujson.loads(line) for line in f]"
+ " data = [orjson.loads(line) for line in f]"
]
},
{
@@ -822,7 +822,7 @@
"topk_docs_to_retrieve = 5 # number of documents to retrieve per search query\n",
"\n",
"with open(\"ragqa_arena_tech_corpus.jsonl\") as f:\n",
- " corpus = [ujson.loads(line)['text'][:max_characters] for line in f]\n",
+ " corpus = [orjson.loads(line)['text'][:max_characters] for line in f]\n",
" print(f\"Loaded {len(corpus)} documents. Will encode them below.\")\n",
"\n",
"embedder = dspy.Embedder('openai/text-embedding-3-small', dimensions=512)\n",
diff --git a/docs/docs/tutorials/rl_multihop/index.ipynb b/docs/docs/tutorials/rl_multihop/index.ipynb
index 0ab7bd74e..2a1508dd1 100644
--- a/docs/docs/tutorials/rl_multihop/index.ipynb
+++ b/docs/docs/tutorials/rl_multihop/index.ipynb
@@ -80,7 +80,7 @@
"metadata": {},
"outputs": [],
"source": [
- "import ujson\n",
+ "import orjson\n",
"import bm25s\n",
"import Stemmer\n",
"\n",
@@ -88,7 +88,7 @@
"\n",
"with open(\"wiki.abstracts.2017.jsonl\") as f:\n",
" for line in f:\n",
- " line = ujson.loads(line)\n",
+ " line = orjson.loads(line)\n",
" corpus.append(f\"{line['title']} | {' '.join(line['text'])}\")\n",
"\n",
"stemmer = Stemmer.Stemmer(\"english\")\n",
diff --git a/docs/docs/tutorials/tool_use/index.ipynb b/docs/docs/tutorials/tool_use/index.ipynb
index 406847f41..dca08d802 100644
--- a/docs/docs/tutorials/tool_use/index.ipynb
+++ b/docs/docs/tutorials/tool_use/index.ipynb
@@ -64,7 +64,7 @@
"outputs": [],
"source": [
"import dspy\n",
- "import ujson\n",
+ "import orjson\n",
"import random\n",
"\n",
"gpt4o = dspy.LM(\"openai/gpt-4o\", temperature=0.7)\n",
@@ -96,7 +96,7 @@
"\n",
"download(\"https://huggingface.co/datasets/bytedance-research/ToolHop/resolve/main/data/ToolHop.json\")\n",
"\n",
- "data = ujson.load(open(\"ToolHop.json\"))\n",
+ "data = orjson.loads(open(\"ToolHop.json\").read())\n",
"random.Random(0).shuffle(data)"
]
},
diff --git a/tests/predict/test_predict.py b/tests/predict/test_predict.py
index 23b6e1d78..f36c7e283 100644
--- a/tests/predict/test_predict.py
+++ b/tests/predict/test_predict.py
@@ -201,8 +201,8 @@ def test_typed_demos_after_dump_and_load_state():
# assert len(dumped_state["demos"]) == len(original_instance.demos)
# assert dumped_state["demos"][0]["input"] == original_instance.demos[0].input.model_dump_json()
-# saved_state = ujson.dumps(dumped_state)
-# loaded_state = ujson.loads(saved_state)
+# saved_state = orjson.dumps(dumped_state).decode()
+# loaded_state = orjson.loads(saved_state)
# new_instance = TypedPredictor(TypedTranslateToEnglish).predictor
# new_instance.load_state(loaded_state)