Validated Bigframes.pands package to query BQ#1
Open
alexhumpy98 wants to merge 5 commits into
Open
Conversation
MarkEdmondson1234
requested changes
Feb 19, 2024
|
|
||
| # csv-agent | ||
|
|
||
| This template uses a [csv agent](https://python.langchain.com/docs/integrations/toolkits/csv) with tools (Python REPL) and memory (vectorstore) for interaction (question-answering) with text data. |
Member
There was a problem hiding this comment.
Need some docs on bq-agent
| ) | ||
| tools = [repl, retriever_tool] | ||
| agent = OpenAIFunctionsAgent( | ||
| llm=ChatOpenAI(temperature=0, model="gpt-4"), prompt=prompt, tools=tools |
Member
There was a problem hiding this comment.
this model doesn't have a large context window (8k ?)
| from langchain.indexes import VectorstoreIndexCreator | ||
| from langchain.vectorstores import FAISS | ||
|
|
||
| loader = CSVLoader("/Users/harrisonchase/Downloads/titanic.csv") |
Member
There was a problem hiding this comment.
this file is not needed?
| @@ -0,0 +1,37 @@ | |||
| [tool.poetry] | |||
| name = "csv-agent" | |||
Member
There was a problem hiding this comment.
this needs to be updated to bq_agent for langserve to work
| langchain-cli = ">=0.0.15" | ||
|
|
||
| [tool.langserve] | ||
| export_module = "csv_agent" |
Member
There was a problem hiding this comment.
this needs updating too, to bq_agent
MarkEdmondson1234
left a comment
MarkEdmondson1234
left a comment
Member
There was a problem hiding this comment.
@alexhumpy98 can the bq_agent/dev folder be ignored too?
![ellipsis-dev[bot]](https://avatars.githubusercontent.com/in/64358?s=60&v=4){kind=small}
There was a problem hiding this comment.
❌ Changes requested.
- Reviewed the entire pull request up to 63a7879
- Looked at
181lines of code in8files - Took 1 minute and 26 seconds to review
More info
- Skipped
6files when reviewing. - Skipped posting
4additional comments because they didn't meet confidence threshold of50%.
1. /langserve/packages/bq-agent/bq_agent/agent.py:21:
- Assessed confidence :
100% - Grade:
0% - Comment:
Consider parameterizing the SQL query or making it more dynamic to increase the flexibility and robustness of the agent. - Reasoning:
The bq_agent/agent.py file contains a hardcoded SQL query. This could be a problem if the table structure or the database changes. It also limits the flexibility of the agent.
2. /langserve/packages/bq-agent/bq_agent/agent.py:27:
- Assessed confidence :
100% - Grade:
0% - Comment:
Consider removing the hardcoded question or making it more dynamic to increase the flexibility of the agent. - Reasoning:
The bq_agent/agent.py file contains a hardcoded question 'How many rows are there in this dataframe?'. This could be a problem if the agent is supposed to handle different types of questions.
3. /langserve/packages/bq-agent/ingest.py:5:
- Assessed confidence :
100% - Grade:
0% - Comment:
Consider parameterizing the file path or making it more dynamic to increase the flexibility and robustness of the agent. - Reasoning:
The ingest.py file contains a hardcoded path to a CSV file. This could be a problem if the file location changes or if the agent is supposed to handle different files.
4. /langserve/packages/bq-agent/main.py:4:
- Assessed confidence :
100% - Grade:
0% - Comment:
Consider removing the hardcoded question or making it more dynamic to increase the flexibility of the agent. - Reasoning:
The main.py file contains a hardcoded question 'how many unique users are there?'. This could be a problem if the agent is supposed to handle different types of questions.
Workflow ID: wflow_uKs5hpo0BST7zUD7
Want Ellipsis to fix these issues? Tag @ellipsis-dev in a comment. We'll respond in a few minutes. Learn more here.
| @@ -0,0 +1,71 @@ | |||
|
|
|||
| # csv-agent | |||
There was a problem hiding this comment.
The title of the README.md file should be updated to reflect the correct package name. Consider changing 'csv-agent' to 'bq-agent'.
| @@ -0,0 +1 @@ | |||
| {"username":"alexanderhumpert","key":"ecebeed6b450fd85320b282a494866bd"} No newline at end of file | |||
There was a problem hiding this comment.
Sensitive information such as usernames and keys should not be stored in plaintext. Consider using environment variables or a secure method of storing these values.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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.
Summary:
This PR introduces a new 'BQ-agent' that reads a BigQuery table into a pandas dataframe, creates a pandas dataframe agent, and provides instructions on how to use the new package.
Key points:
agent.pyfile reads a BigQuery table into a pandas dataframe using thebigframes.pandaspackage.ingest.pyfile creates a vectorstore index from a CSV file.main.pyfile invokes the agent executor with a question.kaggle.jsonfile contains sensitive information and should be removed.csv_agent/agent.pyfile is just a newline at the end of the file.Generated with ❤️ by ellipsis.dev