github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-06 05:08:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: Improved notebook for vector store "HANA Cloud" (#18496)

Browse Source 
- **Description:**
This PR fixes some issues in the Jupyter notebook for the VectorStore
"SAP HANA Cloud Vector Engine":
    * Slight textual adaptations
    * Fix of wrong column name VEC_META (was: VEC_METADATA)

  - **Issue:** N/A
  - **Dependencies:** no new dependecies added
  - **Twitter handle:** @sapopensource

path to notebook:
`docs/docs/integrations/vectorstores/hanavector.ipynb`
This commit is contained in:
Martin Kolb 2024-03-04 19:44:16 +01:00 committed by GitHub
parent 8461700738
commit 63702a2044
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 12 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
docs/docs/integrations/vectorstores/sap_hanavector.ipynb
View File

@ -34,7 +34,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"To use `OpenAIEmbeddings` we use the OpenAI API Key." "For `OpenAIEmbeddings` we use the OpenAI API key from the environment."
] ]
}, },
{ {
@ -57,7 +57,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Create a database connection to a HANA Cloud instance" "Create a database connection to a HANA Cloud instance."
] ]
}, },
{ {
@ -170,7 +170,7 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"Perform a query to get the two best-matching document chunks from the ones that we added in the previous step.\n", "Perform a query to get the two best-matching document chunks from the ones that were added in the previous step.\n",
"By default \"Cosine Similarity\" is used for the search." "By default \"Cosine Similarity\" is used for the search."
] ]
}, },
@ -527,10 +527,11 @@
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"As default behaviour, the table for the embeddings is created with 3 columns\n", "As default behaviour, the table for the embeddings is created with 3 columns:\n",
"* A column `VEC_TEXT`, which contains the text of the Document\n", "\n",
"* A column `VEC_METADATA`, which contains the metadata of the Document\n", "- A column `VEC_TEXT`, which contains the text of the Document\n",
"* A column `VEC_VECTOR`, which contains the embeddings-vector of the document's text" "- A column `VEC_META`, which contains the metadata of the Document\n",
"- A column `VEC_VECTOR`, which contains the embeddings-vector of the Document's text"
] ]
}, },
{ {
@ -609,9 +610,10 @@
"metadata": {}, "metadata": {},
"source": [ "source": [
"Custom tables must have at least three columns that match the semantics of a standard table\n", "Custom tables must have at least three columns that match the semantics of a standard table\n",
"* A column with type `NCLOB` or `NVARCHAR` for the text/context of the embeddings\n", "\n",
"* A column with type `NCLOB` or `NVARCHAR` for the metadata \n", "- A column with type `NCLOB` or `NVARCHAR` for the text/context of the embeddings\n",
"* A column with type REAL_VECTOR for the embedding vector\n", "- A column with type `NCLOB` or `NVARCHAR` for the metadata \n",
"- A column with type `REAL_VECTOR` for the embedding vector\n",
"\n", "\n",
"The table can contain additional columns. When new Documents are inserted into the table, these additional columns must allow NULL values." "The table can contain additional columns. When new Documents are inserted into the table, these additional columns must allow NULL values."
] ]