huanghai
/
dsProject
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

'commit'

Browse Source
main
HuangHai 2 weeks ago
parent 96da4dbe48
commit b932e6fafa
16 changed files with 135 additions and 257 deletions
Show Stats Download Patch File Download Diff File

1
dsLightRag/T1_Train.py
Unescape View File

@ -34,6 +34,7 @@ async def main():
print(f"Deleting old file:: {file_path}")
try:
# 注意：默认设置使用NetworkX
rag = await initialize_rag(WORKING_DIR)
await rag.ainsert(content)
print("\nIndexing completed successfully!")

55
dsLightRag/T1_TrainNeo4j.py
Unescape View File

@ -0,0 +1,55 @@
import asyncio
from Config.Config import NEO4J_URI, NEO4J_USERNAME, NEO4J_PASSWORD
from Util.DocxUtil import get_docx_content_by_pandoc
from Util.LightRagUtil import configure_logging, initialize_rag
import os
# 数学
KEMU = 'Chemistry' # Chinese,Math,Chemistry
# 组装文件路径
WORKING_DIR = "./Topic/" + KEMU
docx_file = 'static/Txt/' + KEMU + '.docx'
async def main():
# 设置Neo4j连接参数
os.environ["NEO4J_URI"] = NEO4J_URI
os.environ["NEO4J_USERNAME"] = NEO4J_USERNAME
os.environ["NEO4J_PASSWORD"] = NEO4J_PASSWORD
# 注释掉或删除以下清理代码
files_to_delete = [
"graph_chunk_entity_relation.graphml",
"kv_store_doc_status.json",
"kv_store_full_docs.json",
"kv_store_text_chunks.json",
"vdb_chunks.json",
"vdb_entities.json",
"vdb_relationships.json",
]
# 获取docx文件的内容
content = get_docx_content_by_pandoc(docx_file)
# 删除文件
for file in files_to_delete:
file_path = os.path.join(WORKING_DIR, file)
if os.path.exists(file_path):
os.remove(file_path)
print(f"Deleting old file:: {file_path}")
try:
# 注意：默认设置使用NetworkX,使用Neo4J实现初始化LightRAG
rag = await initialize_rag(WORKING_DIR, graph_storage="Neo4JStorage")
await rag.ainsert(content)
print("\nIndexing completed successfully!")
except Exception as e:
print(f"An error occurred: {e}")
finally:
await rag.finalize_storages()
if __name__ == "__main__":
configure_logging()
asyncio.run(main())

241
dsLightRag/Topic/Chemistry/graph_chunk_entity_relation.graphml
Unescape View File

@ -1,241 +0,0 @@
<?xml version='1.0' encoding='utf-8'?>
<graphml xmlns="http://graphml.graphdrawing.org/xmlns" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://graphml.graphdrawing.org/xmlns http://graphml.graphdrawing.org/xmlns/1.0/graphml.xsd">
<key id="d11" for="edge" attr.name="created_at" attr.type="long" />
<key id="d10" for="edge" attr.name="file_path" attr.type="string" />
<key id="d9" for="edge" attr.name="source_id" attr.type="string" />
<key id="d8" for="edge" attr.name="keywords" attr.type="string" />
<key id="d7" for="edge" attr.name="description" attr.type="string" />
<key id="d6" for="edge" attr.name="weight" attr.type="double" />
<key id="d5" for="node" attr.name="created_at" attr.type="long" />
<key id="d4" for="node" attr.name="file_path" attr.type="string" />
<key id="d3" for="node" attr.name="source_id" attr.type="string" />
<key id="d2" for="node" attr.name="description" attr.type="string" />
<key id="d1" for="node" attr.name="entity_type" attr.type="string" />
<key id="d0" for="node" attr.name="entity_id" attr.type="string" />
<graph edgedefault="undirected">
<node id="Nitric Acid">
<data key="d0">Nitric Acid</data>
<data key="d1">category</data>
<data key="d2">Nitric acid (HNO₃) is a highly corrosive and toxic chemical used in various reactions, including decomposition and oxidation.</data>
<data key="d3">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d4">unknown_source</data>
<data key="d5">1752193132</data>
</node>
<node id="Nitrogen Dioxide">
<data key="d0">Nitrogen Dioxide</data>
<data key="d1">category</data>
<data key="d2">Nitrogen dioxide (NO₂) is a reddish-brown gas produced during the decomposition of nitric acid.</data>
<data key="d3">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d4">unknown_source</data>
<data key="d5">1752193132</data>
</node>
<node id="Oxygen">
<data key="d0">Oxygen</data>
<data key="d1">category</data>
<data key="d2">Oxygen (O₂) is a colorless, odorless gas involved in chemical reactions like combustion and decomposition.</data>
<data key="d3">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d4">unknown_source</data>
<data key="d5">1752193132</data>
</node>
<node id="Iron Oxide">
<data key="d0">Iron Oxide</data>
<data key="d1">category</data>
<data key="d2">Iron oxide (FeO) is a compound that reacts with nitric acid under heat to produce other chemicals.</data>
<data key="d3">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d4">unknown_source</data>
<data key="d5">1752193132</data>
</node>
<node id="Iron Nitrate">
<data key="d0">Iron Nitrate</data>
<data key="d1">category</data>
<data key="d2">Iron nitrate (Fe(NO₃)₃) is a product of the reaction between iron oxide and nitric acid.</data>
<data key="d3">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d4">unknown_source</data>
<data key="d5">1752193132</data>
</node>
<node id="Water">
<data key="d0">Water</data>
<data key="d1">category</data>
<data key="d2">Water (H₂O) is a byproduct of the combustion of hydrogen and oxygen.</data>
<data key="d3">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d4">unknown_source</data>
<data key="d5">1752193132</data>
</node>
<node id="Hydrogen">
<data key="d0">Hydrogen</data>
<data key="d1">category</data>
<data key="d2">Hydrogen (H₂) is a flammable gas that reacts with oxygen to form water.</data>
<data key="d3">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d4">unknown_source</data>
<data key="d5">1752193132</data>
</node>
<node id="硝酸铁">
<data key="d0">硝酸铁</data>
<data key="d1">category</data>
<data key="d2">"硝酸铁(Fe(NO₃</data>
<data key="d3">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d4">unknown_source</data>
<data key="d5">1752193132</data>
</node>
<node id="二氧化氮">
<data key="d0">二氧化氮</data>
<data key="d3">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d2">硝酸在光照条件下分解产生二氧化氮气体。</data>
<data key="d1">UNKNOWN</data>
<data key="d4">unknown_source</data>
<data key="d5">1752193132</data>
</node>
<node id="硝酸">
<data key="d0">硝酸</data>
<data key="d3">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d2">硝酸在光照条件下分解产生二氧化氮气体。</data>
<data key="d1">UNKNOWN</data>
<data key="d4">unknown_source</data>
<data key="d5">1752193132</data>
</node>
<node id="氧气">
<data key="d0">氧气</data>
<data key="d3">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d2">硝酸分解反应会释放氧气。</data>
<data key="d1">UNKNOWN</data>
<data key="d4">unknown_source</data>
<data key="d5">1752193132</data>
</node>
<node id="水">
<data key="d0">水</data>
<data key="d3">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d2">硝酸分解最终会生成水。</data>
<data key="d1">UNKNOWN</data>
<data key="d4">unknown_source</data>
<data key="d5">1752193132</data>
</node>
<node id="氧化铁">
<data key="d0">氧化铁</data>
<data key="d3">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d2">氧化铁与硝酸反应生成硝酸铁。</data>
<data key="d1">UNKNOWN</data>
<data key="d4">unknown_source</data>
<data key="d5">1752193132</data>
</node>
<node id="氢气">
<data key="d0">氢气</data>
<data key="d3">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d2">氧化铁与硝酸反应过程中会产生氢气。</data>
<data key="d1">UNKNOWN</data>
<data key="d4">unknown_source</data>
<data key="d5">1752193132</data>
</node>
<node id="光照分解">
<data key="d0">光照分解</data>
<data key="d3">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d2">光照分解是硝酸发生化学反应的条件。</data>
<data key="d1">UNKNOWN</data>
<data key="d4">unknown_source</data>
<data key="d5">1752193132</data>
</node>
<node id="加热反应">
<data key="d0">加热反应</data>
<data key="d3">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d2">加热是氧化铁与硝酸反应的必要条件。</data>
<data key="d1">UNKNOWN</data>
<data key="d4">unknown_source</data>
<data key="d5">1752193132</data>
</node>
<edge source="Nitric Acid" target="Nitrogen Dioxide">
<data key="d6">8.0</data>
<data key="d7">Nitric acid decomposes under light to produce nitrogen dioxide, oxygen, and water.</data>
<data key="d8">chemical decomposition,gas production</data>
<data key="d9">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d10">unknown_source</data>
<data key="d11">1752193132</data>
</edge>
<edge source="Nitric Acid" target="Oxygen">
<data key="d6">7.0</data>
<data key="d7">Nitric acid decomposition releases oxygen as a byproduct.</data>
<data key="d8">chemical reaction,gas release</data>
<data key="d9">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d10">unknown_source</data>
<data key="d11">1752193132</data>
</edge>
<edge source="Iron Oxide" target="Iron Nitrate">
<data key="d6">9.0</data>
<data key="d7">Iron oxide reacts with nitric acid to form iron nitrate, hydrogen, and nitrogen dioxide.</data>
<data key="d8">chemical synthesis,oxidation reaction</data>
<data key="d9">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d10">unknown_source</data>
<data key="d11">1752193132</data>
</edge>
<edge source="Water" target="Hydrogen">
<data key="d6">10.0</data>
<data key="d7">Hydrogen combusts with oxygen to produce water, a key reaction in chemistry.</data>
<data key="d8">chemical synthesis,combustion</data>
<data key="d9">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d10">unknown_source</data>
<data key="d11">1752193132</data>
</edge>
<edge source="硝酸铁" target="氧化铁">
<data key="d6">9.0</data>
<data key="d7">氧化铁与硝酸反应生成硝酸铁。</data>
<data key="d8">复分解反应,盐类生成</data>
<data key="d9">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d10">unknown_source</data>
<data key="d11">1752193132</data>
</edge>
<edge source="二氧化氮" target="硝酸">
<data key="d6">9.0</data>
<data key="d7">硝酸在光照条件下分解产生二氧化氮气体。</data>
<data key="d8">化学分解,气体生成</data>
<data key="d9">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d10">unknown_source</data>
<data key="d11">1752193132</data>
</edge>
<edge source="硝酸" target="氧气">
<data key="d6">8.0</data>
<data key="d7">硝酸分解反应会释放氧气。</data>
<data key="d8">气体产物,氧化还原</data>
<data key="d9">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d10">unknown_source</data>
<data key="d11">1752193132</data>
</edge>
<edge source="硝酸" target="水">
<data key="d6">7.0</data>
<data key="d7">硝酸分解最终会生成水。</data>
<data key="d8">产物生成,化学反应</data>
<data key="d9">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d10">unknown_source</data>
<data key="d11">1752193132</data>
</edge>
<edge source="硝酸" target="光照分解">
<data key="d6">8.0</data>
<data key="d7">光照分解是硝酸发生化学反应的条件。</data>
<data key="d8">化学变化,反应条件</data>
<data key="d9">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d10">unknown_source</data>
<data key="d11">1752193132</data>
</edge>
<edge source="水" target="氢气">
<data key="d6">10.0</data>
<data key="d7">氢气与氧气燃烧生成水。</data>
<data key="d8">氧化还原,燃烧反应</data>
<data key="d9">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d10">unknown_source</data>
<data key="d11">1752193132</data>
</edge>
<edge source="氧化铁" target="氢气">
<data key="d6">8.0</data>
<data key="d7">氧化铁与硝酸反应过程中会产生氢气。</data>
<data key="d8">气体生成,置换反应</data>
<data key="d9">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d10">unknown_source</data>
<data key="d11">1752193132</data>
</edge>
<edge source="氧化铁" target="加热反应">
<data key="d6">7.0</data>
<data key="d7">加热是氧化铁与硝酸反应的必要条件。</data>
<data key="d8">反应条件,能量输入</data>
<data key="d9">chunk-bd828dcbe5a5b2436237977039978ec4</data>
<data key="d10">unknown_source</data>
<data key="d11">1752193132</data>
</edge>
</graph>
</graphml>

8
dsLightRag/Topic/Chemistry/kv_store_doc_status.json
Unescape View File

@ -1,12 +1,12 @@
{
"doc-bd828dcbe5a5b2436237977039978ec4": {
"doc-38dc4759f21281aec253bbbfd5249836": {
"status": "processed",
"chunks_count": 1,
"content": "硝酸光照分解的方程式\n$$4HNO_{3}overset{overset{}{{Delta}}}{=}4NO_{2} uparrow + O_{2} uparrow + 2HO_{2}$$\n氧化铁与硝酸的加热反应方程式\n$$FeO + 4HNO_{3}overset{overset{}{{Delta}}}{=}Fe(NO_{3})_{3} + 2H_{2} uparrow + NO_{2} uparrow$$\n氢气与氧气燃烧的现象如下图所示：\n$$2H_{2} + O_{2}overset{overset{}{text{燃烧}}}{=}2H_{2}O$$\n![](./Images/cc34652eb4d840fca308ba8563a41d3b/media/image1.png)",
"content": "硝酸光照分解的方程式\n$$4HNO_{3}overset{overset{}{{Delta}}}{=}4NO_{2} uparrow + O_{2} uparrow + 2HO_{2}$$\n氧化铁与硝酸的加热反应方程式\n$$FeO + 4HNO_{3}overset{overset{}{{Delta}}}{=}Fe(NO_{3})_{3} + 2H_{2} uparrow + NO_{2} uparrow$$\n氢气与氧气燃烧的现象如下图所示：\n$$2H_{2} + O_{2}overset{overset{}{text{燃烧}}}{=}2H_{2}O$$\n![](./Images/4826f1dfc6ce4ba5a294167a016b736f/media/image1.png)",
"content_summary": "硝酸光照分解的方程式\n$$4HNO_{3}overset{overset{}{{Delta}}}{=}4NO_{2} uparrow + O_{2} uparrow + 2HO_{2}$$\n氧化铁与硝酸的加热反应方程式\n$$FeO + 4HNO_{3}overset{overset{}{{Delta}}}{=}Fe(NO_{3})_{3} + 2H_{2} uparrow + NO_{2} uparrow$$\n氢气与氧气燃烧的现象如下图所示：\n$$2H_{2} + O_{2}overset{ov...",
"content_length": 344,
"created_at": "2025-07-11T00:17:59.549803+00:00",
"updated_at": "2025-07-11T00:18:54.052706+00:00",
"created_at": "2025-07-11T00:25:57.391796+00:00",
"updated_at": "2025-07-11T00:26:52.778188+00:00",
"file_path": "unknown_source"
}
}

4
dsLightRag/Topic/Chemistry/kv_store_full_docs.json
Unescape View File

@ -1,5 +1,5 @@
{
"doc-bd828dcbe5a5b2436237977039978ec4": {
"content": "硝酸光照分解的方程式\n$$4HNO_{3}overset{overset{}{{Delta}}}{=}4NO_{2} uparrow + O_{2} uparrow + 2HO_{2}$$\n氧化铁与硝酸的加热反应方程式\n$$FeO + 4HNO_{3}overset{overset{}{{Delta}}}{=}Fe(NO_{3})_{3} + 2H_{2} uparrow + NO_{2} uparrow$$\n氢气与氧气燃烧的现象如下图所示：\n$$2H_{2} + O_{2}overset{overset{}{text{燃烧}}}{=}2H_{2}O$$\n![](./Images/cc34652eb4d840fca308ba8563a41d3b/media/image1.png)"
"doc-38dc4759f21281aec253bbbfd5249836": {
"content": "硝酸光照分解的方程式\n$$4HNO_{3}overset{overset{}{{Delta}}}{=}4NO_{2} uparrow + O_{2} uparrow + 2HO_{2}$$\n氧化铁与硝酸的加热反应方程式\n$$FeO + 4HNO_{3}overset{overset{}{{Delta}}}{=}Fe(NO_{3})_{3} + 2H_{2} uparrow + NO_{2} uparrow$$\n氢气与氧气燃烧的现象如下图所示：\n$$2H_{2} + O_{2}overset{overset{}{text{燃烧}}}{=}2H_{2}O$$\n![](./Images/4826f1dfc6ce4ba5a294167a016b736f/media/image1.png)"
}
}

60
dsLightRag/Topic/Chemistry/kv_store_llm_response_cache.json
View File

File diff suppressed because one or more lines are too long

8
dsLightRag/Topic/Chemistry/kv_store_text_chunks.json
Unescape View File

@ -1,9 +1,9 @@
{
"chunk-bd828dcbe5a5b2436237977039978ec4": {
"tokens": 197,
"content": "硝酸光照分解的方程式\n$$4HNO_{3}overset{overset{}{{Delta}}}{=}4NO_{2} uparrow + O_{2} uparrow + 2HO_{2}$$\n氧化铁与硝酸的加热反应方程式\n$$FeO + 4HNO_{3}overset{overset{}{{Delta}}}{=}Fe(NO_{3})_{3} + 2H_{2} uparrow + NO_{2} uparrow$$\n氢气与氧气燃烧的现象如下图所示：\n$$2H_{2} + O_{2}overset{overset{}{text{燃烧}}}{=}2H_{2}O$$\n![](./Images/cc34652eb4d840fca308ba8563a41d3b/media/image1.png)",
"chunk-38dc4759f21281aec253bbbfd5249836": {
"tokens": 198,
"content": "硝酸光照分解的方程式\n$$4HNO_{3}overset{overset{}{{Delta}}}{=}4NO_{2} uparrow + O_{2} uparrow + 2HO_{2}$$\n氧化铁与硝酸的加热反应方程式\n$$FeO + 4HNO_{3}overset{overset{}{{Delta}}}{=}Fe(NO_{3})_{3} + 2H_{2} uparrow + NO_{2} uparrow$$\n氢气与氧气燃烧的现象如下图所示：\n$$2H_{2} + O_{2}overset{overset{}{text{燃烧}}}{=}2H_{2}O$$\n![](./Images/4826f1dfc6ce4ba5a294167a016b736f/media/image1.png)",
"chunk_order_index": 0,
"full_doc_id": "doc-bd828dcbe5a5b2436237977039978ec4",
"full_doc_id": "doc-38dc4759f21281aec253bbbfd5249836",
"file_path": "unknown_source"
}
}

2
dsLightRag/Topic/Chemistry/vdb_chunks.json
View File

File diff suppressed because one or more lines are too long

2
dsLightRag/Topic/Chemistry/vdb_entities.json
View File

File diff suppressed because one or more lines are too long

2
dsLightRag/Topic/Chemistry/vdb_relationships.json
View File

File diff suppressed because one or more lines are too long

7
dsLightRag/Util/LightRagUtil.py
Unescape View File

@ -97,10 +97,13 @@ async def embedding_func(texts: list[str]) -> np.ndarray:
)
async def initialize_rag(working_dir):
async def initialize_rag(working_dir, graph_storage=None):
if graph_storage is None:
graph_storage = 'NetworkXStorage'
rag = LightRAG(
working_dir=working_dir,
llm_model_func=llm_model_func,
graph_storage=graph_storage,
embedding_func=EmbeddingFunc(
embedding_dim=EMBED_DIM,
max_token_size=EMBED_MAX_TOKEN_SIZE,
@ -139,4 +142,4 @@ def create_embedding_func():
api_key=EMBED_API_KEY,
base_url=EMBED_BASE_URL,
),
)
)

BIN
dsLightRag/Util/__pycache__/LightRagUtil.cpython-310.pyc
View File

Binary file not shown.

BIN
dsLightRag/static/Images/4826f1dfc6ce4ba5a294167a016b736f/media/image1.png
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 195 KiB

BIN
dsLightRag/static/Images/4d474d2e0348478eaf6bc8f421cb826e/media/image1.png
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 195 KiB

BIN
dsLightRag/static/Images/65bc21c8e02b4ddfbe24095566164bfb/media/image1.png
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 195 KiB

2
dsLightRag/static/markdown/Chemistry.md
Unescape View File

@ -4,4 +4,4 @@ $$4HNO_{3}\overset{\overset{}{{\Delta}}}{=}4NO_{2} \uparrow + O_{2} \uparrow + 2
$$FeO + 4HNO_{3}\overset{\overset{}{{\Delta}}}{=}Fe(NO_{3})_{3} + 2H_{2} \uparrow + NO_{2} \uparrow$$
氢气与氧气燃烧的现象如下图所示：
$$2H_{2} + O_{2}\overset{\overset{}{\text{燃烧}}}{=}2H_{2}O$$
![](./Images/cc34652eb4d840fca308ba8563a41d3b/media/image1.png)
![](./Images/4826f1dfc6ce4ba5a294167a016b736f/media/image1.png)

Write Preview
Loading…
Cancel
Save