docs(weekly): add this week in databend 88 #10990
Merged
Conversation
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
Signed-off-by: Chojan Shang <psiace@outlook.com>
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
Signed-off-by: Chojan Shang <psiace@outlook.com>
soyeric128
reviewed
Apr 9, 2023
|
|
||
| ### Support Eager Aggregation | ||
|
|
||
| Eager aggregation is a technique that can help improve the performance of queries that involve grouping and joining data. It works by partially pushing a groupby past a join, which reduces the number of input rows to the join and may result in a better overall plan. |
Contributor
There was a problem hiding this comment.
Eager aggregation helps improve ...
soyeric128
reviewed
Apr 9, 2023
|
|
||
| ### databend-driver - A driver for Databend in Rust | ||
|
|
||
| The Databend community has developed a driver for Databend in Rust. It allows developers to easily connect to Databend and execute SQL queries using Rust. |
Contributor
There was a problem hiding this comment.
The Databend community has crafted a Rust driver that allows developers to connect to Databend and execute SQL queries in Rust.
soyeric128
reviewed
Apr 9, 2023
| conn.exec(sql_insert).await.unwrap(); | ||
| ``` | ||
|
|
||
| Welcome to try it out and give us feedback. If you want to learn more information, you can also follow the resources listed below. |
Contributor
There was a problem hiding this comment.
Feel free to try it out.... . For more information, follow the resources...
soyeric128
reviewed
Apr 9, 2023
|
|
||
| AskBend is a Rust project that utilizes the power of Databend and OpenAI to create a SQL-based knowledge base from Markdown files. | ||
|
|
||
| With AskBend, you can easily search and retrieve the most relevant information to your queries using SQL. The project automatically generates document embeddings from the content, enabling users to quickly find the information they need. |
Contributor
There was a problem hiding this comment.
With AskBend, you can easily search and retrieve the most relevant information to your queries using SQL. The project automatically generates document embeddings from the content, enabling you to quickly find the information you need.
soyeric128
reviewed
Apr 9, 2023
|
|
||
| With AskBend, you can easily search and retrieve the most relevant information to your queries using SQL. The project automatically generates document embeddings from the content, enabling users to quickly find the information they need. | ||
|
|
||
| Here's how it works: |
soyeric128
reviewed
Apr 9, 2023
| 1. Read and parse Markdown files from a directory. | ||
| 2. Store the content in the `askbend.doc` table. | ||
| 3. Compute embeddings for the content using Databend Cloud's built-in AI capabilities. | ||
| 4. When a user queries, generate the query embedding using Databend Cloud's SQL-based `ai_embedding_vector` function. |
Contributor
There was a problem hiding this comment.
Query means SQL query? otherwise, pls use "When a users asks a question, ...."
soyeric128
reviewed
Apr 9, 2023
| 3. Compute embeddings for the content using Databend Cloud's built-in AI capabilities. | ||
| 4. When a user queries, generate the query embedding using Databend Cloud's SQL-based `ai_embedding_vector` function. | ||
| 5. Find the most relevant doc.content using Databend Cloud's SQL-based `cosine_distance` function. | ||
| 6. Use OpenAI's completion capabilities with Databend Cloud's SQL-based `ai_text_completion` function |
Contributor
There was a problem hiding this comment.
missing a period (.) at the end.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
I hereby agree to the terms of the CLA available at: https://databend.rs/dev/policies/cla/
Summary
Summary about this PR
Closes #issue