Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Pdf parse test #212

Draft
wants to merge 28 commits into
base: dev-2.3
Choose a base branch
from
Draft

Pdf parse test #212

wants to merge 28 commits into from

Conversation

cristianoc
Copy link
Contributor

No description provided.

@cristianoc
IR: fix counter for guards.
eb52f1d
@cristianoc
IR: support default values in python functions.
47dfdd6
@cristianoc
Index (#204)
a19080d 
* index

* Update index.py

* move

* Use project.

* load and save

* benchmark search

* unused

* async

* openai embedding

* async only in index creation

* Avoid nan in embeddings.
@cristianoc
Add lean tree sitter (#205)
cead7c8 
* Vendor tree-sitter-lean

Vendor tree-sitter-lean from https://github.com/Julian/tree-sitter-lean

* Add Lean to custom parsers.

* IR: add Lean parser.

* IR: add Lean tests.

* IR: correctly build lean tree sitter
@cristianoc
Clean up agents code (#208)
ddb6a05 
* Clean up agents code

The agent params are sent from the client, and are the same for all agents. So there's no customisation in practice.

Remove redundant class member that were set per agent but were already inherited from the abstract agent class.

* Clean up server parameter of agent create.
@cristianoc
Agents cleanup: move messages to abstract state.
b230003 
All agents use messages in the state. This avoids repeating it in every agent.
@cristianoc
Add metalanguage.
0f77ea7
@cristianoc
Update metalanguage.py
b30ddeb
@cristianoc
IR: rearrange symbol kinds. Get a sorted list on top.
48e8559
@cristianoc
IR: document symbol kinds
06d71a5
@cristianoc
IR: document symbol
01713cb
@cristianoc
IR: add file symbol as parent of toplevel symbols.
f6e213a
@cristianoc
IR File: remove statements
52893d2 
Statements are redundant: use the body of the file block.
@cristianoc
IR: no need to return from parse statement and block.
3ede4ef
@cristianoc
IR: introduce Unknown symbol in pace of statement with no sybol
4721bf3 
Then statements can be removed.
@cristianoc
IR: remove concept of Item and make Block a list of symbols.
87d8e8b 
Items are not required now that Unknown symbols have replaced statements without symbols.
@cristianoc
IR: clean up statements.
7506221
@cristianoc
IR: remove parse_statement
cf389b1
@cristianoc
Index: refactor embedding.
e267633
@cristianoc
Index: support searching function, file, class.
059ceaa
@cristianoc
Index API: use Query class.
75fc096
@cristianoc
Index: test boolean queries.
77f9f72
@cristianoc
IR: File() constructor takes a code argument now.
283bc33
@cristianoc
sort imports
ab66fc1
@cristianoc
Test the idea of parsing .pdf's.
5d769c4
@cristianoc
Arbitrary depth in principle.
3168fbd
@cristianoc
Complete generalisation to arbitrary depth.
4c001e8
@cristianoc
Support sections with a dot: "1. Intro"
77160f5
@cristianoc cristianoc marked this pull request as draft October 3, 2023 13:35
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
1 participant
@cristianoc