improve multi doc retrieval #11346
Merged
improve multi doc retrieval #11346
Conversation
This file contains 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
dosubot
bot
added
the
size:S
dosubot
bot
added
size:XS
hatianzhang
changed the title
| @@ -57,7 +57,7 @@ def get_nodes_from_node(self, node: TextNode) -> List[BaseNode]: | |||
| self.extract_table_summaries(table_elements) | |||
| # convert into nodes | |||
| # will return a list of Nodes and Index Nodes | |||
| return self.get_nodes_from_elements(elements) | |||
| return self.get_nodes_from_elements(elements, node.id_) | |||
There was a problem hiding this comment.
So its not really a filename, but assumes the node id is file name?
Should we just instead inherit all metadata?
There was a problem hiding this comment.
node.id_ is a filename if node parser is getting documents from local files.
for inherit all metadata, do you mean we could inherit all the metadata from base nodes to the inherited nodes. but base nodes sometime has just empty metadata. The only useful information from base node is that id_ is filename. so that is the only information useful for inherited nodes.
sorry, maybe have a quick call to understand this better
dosubot
bot
added
size:S
llama-index-core/llama_index/core/node_parser/relational/base_element.py
Outdated
Show resolved
Hide resolved
Dominastorm
pushed a commit
to uptrain-ai/llama_index
that referenced
this pull request
Feb 28, 2024
* improve multi doc retrieval * cr * cr * cr * cr
anoopshrma
pushed a commit
to anoopshrma/llama_index
that referenced
this pull request
Mar 2, 2024
* improve multi doc retrieval * cr * cr * cr * cr
Izukimat
pushed a commit
to Izukimat/llama_index
that referenced
this pull request
Mar 29, 2024
* improve multi doc retrieval * cr * cr * cr * cr
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Description
Index filename into each node's metadata (for node parser) so that we can filter or retrieve doc based on file name
Fixes # (issue)
Type of Change
Please delete options that are not relevant.
How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration
Suggested Checklist:
make format; make lintto appease the lint gods