From 25220cc60501792dcb68c68a5b1fdc6873f9b611 Mon Sep 17 00:00:00 2001
From: oldwinter <cdd2zju@gmail.com>
Date: Wed, 9 Aug 2023 17:35:41 +0800
Subject: [PATCH 1/3] aa

---
 ...n\347\232\204\345\211\257\346\234\2542.py" | 62 +++++++++++++++++++
 1 file changed, 62 insertions(+)
 create mode 100644 "tmp-test-gpt-cr/obsidian\347\232\204\345\211\257\346\234\2542.py"

diff --git "a/tmp-test-gpt-cr/obsidian\347\232\204\345\211\257\346\234\2542.py" "b/tmp-test-gpt-cr/obsidian\347\232\204\345\211\257\346\234\2542.py"
new file mode 100644
index 00000000..3ebb80c7
--- /dev/null
+++ "b/tmp-test-gpt-cr/obsidian\347\232\204\345\211\257\346\234\2542.py"
@@ -0,0 +1,62 @@
+## 1.终端里设置环境变量
+
+# export OPENAI_API_TYPE=azure
+# export OPENAI_API_VERSION=2023-05-15
+# export OPENAI_API_BASE=https://ingtubeopenai.openai.azure.com
+# export OPENAI_API_KEY=ea31775d794e47beb2f6cd479817ce81
+
+# export PINECONE_API_KEY=d0e32935-ca46-4a82-be38-34cc17dbdcce
+# export PINECONE_ENV=gcp-starter
+
+## 2.加载原始csv数据
+
+# llm(documents1[0].page_content)
+
+
+from langchain.document_loaders import ObsidianLoader
+
+loader = ObsidianLoader("/Users/yingtu/知识库/ingtube")
+documents = loader.load()
+
+## 3.embddings对象模型初始化，实际调用在后面。
+from langchain.embeddings import OpenAIEmbeddings
+embeddings = OpenAIEmbeddings(
+    client="",
+    model="text-embedding-ada-002",
+    deployment="ingtube-ada",
+    # input="texts",
+    # chunk_size=1
+    show_progress_bar=True,
+)
+
+## 4.pinecone初始化
+import pinecone
+import os
+# PINECONE_API_KEY="d0e32935-ca46-4a82-be38-34cc17dbdcce"
+# PINECONE_ENV="gcp-starter"
+
+# initialize pinecone
+
+pinecone.init(
+    api_key=os.getenv('PINECONE_API_KEY'),  # find at app.pinecone.io
+    environment=os.getenv('PINECONE_ENV'),  # next to api key in console
+)
+
+index_name = "ingtube-test"
+
+if index_name not in pinecone.list_indexes():
+    pinecone.create_index(
+      name=index_name,
+      metric='cosine',
+      dimension=1536  
+)
+
+
+# 将documents按照每16个元素为一组进行分割
+chunks = [documents[i:i + 16] for i in range(0, len(documents), 16)]
+
+from langchain.vectorstores import Pinecone
+## 5.循环调用Pinecone.from_documents方法，从embedding接口生成数据，同时存储向量数据至pinecone
+for chunk in chunks:
+    Pinecone.from_documents(chunk, embeddings, index_name=index_name)
+

From 93dc4aabee6e4d3952c9fbdd24ce3e306cd3a57b Mon Sep 17 00:00:00 2001
From: oldwinter <cdd2zju@gmail.com>
Date: Wed, 9 Aug 2023 17:42:06 +0800
Subject: [PATCH 2/3] aab

---
 ...n\347\232\204\345\211\257\346\234\2542.py" | 32 -------------------
 1 file changed, 32 deletions(-)

diff --git "a/tmp-test-gpt-cr/obsidian\347\232\204\345\211\257\346\234\2542.py" "b/tmp-test-gpt-cr/obsidian\347\232\204\345\211\257\346\234\2542.py"
index 3ebb80c7..b0462f90 100644
--- "a/tmp-test-gpt-cr/obsidian\347\232\204\345\211\257\346\234\2542.py"
+++ "b/tmp-test-gpt-cr/obsidian\347\232\204\345\211\257\346\234\2542.py"
@@ -28,35 +28,3 @@
     # chunk_size=1
     show_progress_bar=True,
 )
-
-## 4.pinecone初始化
-import pinecone
-import os
-# PINECONE_API_KEY="d0e32935-ca46-4a82-be38-34cc17dbdcce"
-# PINECONE_ENV="gcp-starter"
-
-# initialize pinecone
-
-pinecone.init(
-    api_key=os.getenv('PINECONE_API_KEY'),  # find at app.pinecone.io
-    environment=os.getenv('PINECONE_ENV'),  # next to api key in console
-)
-
-index_name = "ingtube-test"
-
-if index_name not in pinecone.list_indexes():
-    pinecone.create_index(
-      name=index_name,
-      metric='cosine',
-      dimension=1536  
-)
-
-
-# 将documents按照每16个元素为一组进行分割
-chunks = [documents[i:i + 16] for i in range(0, len(documents), 16)]
-
-from langchain.vectorstores import Pinecone
-## 5.循环调用Pinecone.from_documents方法，从embedding接口生成数据，同时存储向量数据至pinecone
-for chunk in chunks:
-    Pinecone.from_documents(chunk, embeddings, index_name=index_name)
-

From 53213e02a490897306294b0d0fcee6bb2c5d065a Mon Sep 17 00:00:00 2001
From: oldwinter <cdd2zju@gmail.com>
Date: Wed, 9 Aug 2023 17:43:59 +0800
Subject: [PATCH 3/3] aabd

---
 .github/workflows/chatgpt-cr.yaml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/chatgpt-cr.yaml b/.github/workflows/chatgpt-cr.yaml
index 9926310a..a381bbc1 100644
--- a/.github/workflows/chatgpt-cr.yaml
+++ b/.github/workflows/chatgpt-cr.yaml
@@ -23,5 +23,5 @@ jobs:
           PROMPT: "请检查以下代码差异是否有混淆或不规范之处：" # example: Please check if there are any confusions or irregularities in the following code diff:
           top_p: 1 # https://platform.openai.com/docs/api-reference/chat/create#chat/create-top_p
           temperature: 1 # https://platform.openai.com/docs/api-reference/chat/create#chat/create-temperature
-          max_tokens: 10000
-          MAX_PATCH_LENGTH: 10000 # if the patch/diff length is large than MAX_PATCH_LENGTH, will be ignored and won't review. By default, with no MAX_PATCH_LENGTH set, there is also no limit for the patch/diff length.
\ No newline at end of file
+          max_tokens: 1024
+          MAX_PATCH_LENGTH: 1024 # if the patch/diff length is large than MAX_PATCH_LENGTH, will be ignored and won't review. By default, with no MAX_PATCH_LENGTH set, there is also no limit for the patch/diff length.