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

[llm unify 3/n] Reimplement SummarizeImages as an LLMMapElements #1146

Merged
merged 54 commits into from
Jan 30, 2025
Merged

[llm unify 3/n] Reimplement SummarizeImages as an LLMMapElements #1146

merged 54 commits into from
Jan 30, 2025

Conversation

HenryL27
Copy link
Collaborator

  • also adds a filter param to LLMMap and LLMMapElements to filter the docs/elements you want to render / call the llm on

I should probably go to a new branch for the next one, huh.

HenryL27 added 30 commits January 16, 2025 16:40
@HenryL27
add prompt base classes and ElementListPrompt
c2a8cfa 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
override .instead in ElementListPrompt to store net-new keys in self.…
21a115a 
…kwargs

Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
add ElementPrompt and StaticPrompt
f94da80 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
add unit tests for prompts
b73c162 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
forgot to commit this
17b2163 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
address pr comments; flatten properties with flatten_data
5d145d5 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
support multiple user prompts
7fa2ff1 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
rename instead to set
abf9b0b 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
Merge branch 'main' of github.com:aryn-ai/sycamore into hml-llm-unify
9909c7e
@HenryL27
add LLMMap and LLMMapElements transforms
2d1315b 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
Merge branch 'main' of github.com:aryn-ai/sycamore into hml-llm-unify
1853d51
@HenryL27
move llm implementations to use RenderedPrompts
5e86e56 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
also this guy
27581ef 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
add docset methods
739b672 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
docstrings
73d9bdd 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
add llm_map unit tests
ed8785e 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
fix bedrock tests and chaching
523d6e3 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
fix anthropic and bedrock ITs
e1b3206 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
adjust caching to handle pydantic class response format properly
6500e1c 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
fix base llm unit tests
f50032d 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
adjust all testing mock llms to updated llm interface
c3c7ea8 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
deprecate extract entity and implement it with llm_map
ffaaf0f 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
add context_params decorator to llm_map
d71cf1a 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
revert extract_entity docset method re-implementation
4225e11 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
add initial support for prompts that generate a sequence of rendered …
0d39b27 
…prompts (to do things like adhere to token limits)

Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
add stuff to EntityExtractor/OpenAIEntityExtractor to convert to LLMMap
0b5ded4 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
make docset.extract_entity construct an LLMMap from its entity_extractor
a52f7c2 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
get extract entity working with tokenizer and token limit
3a9ac3c 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
get all extract_entity unit tests passing
befc3d0 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
fix llm_map_elements to deal with postprocess index
8bf42d5 
Signed-off-by: Henry Lindeman <[email protected]>
HenryL27 added 23 commits January 28, 2025 11:00
@HenryL27
add postprocess_fn unit tests for llm_map
d7ff1eb 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
ruff complaint
a7a2cc0 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
fix docset unittests
ebf721e 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
move a bunch of stuff back to llm.generate_old. This includes the act…
0bd2a45 
…ive implementation of extract entity bc I don't want to deal with llm_filter just yet

Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
move more stuff back to llm.generate_old
95cbaaf 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
fix the last few mocks
ea7f0e6 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
Merge branch 'main' of github.com:aryn-ai/sycamore into hml-llm-unify
2e51ee1
@HenryL27
ruff linelength
57a4e4b 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
mypy!!!
a312ba3 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
type: ignore + line length is tricky
ebde879 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
fix generate_old with SimplePrompts
ff5efdc 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
set openai system role name to system instead of developer like their…
370e2b7 
… docs say because azure disagrees and they'd better both accept 'system'

Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
address simple pr comments
98ce6a0 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
pickle stuff in llm caching path bc not everything is jsonifiable
1789409 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
rewrite llm_map to deal with iterative prompting better
8b6f085 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
add a b64encode-to-str to cache bc you can't put bytes in json either
763acc5 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
fix llm its to mimic the _llm_cache_set/get pickle/unpickle operations
0331866 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
fix docstrings
dfb7540 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
oops bad type signature
f7c06e7 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
initial summarize_images translation
faf450e 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
Merge branch 'main' of github.com:aryn-ai/sycamore into hml-llm-unify
6d8276e
@HenryL27
make SummarizeImages work
8ea76d0 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27
update docstrings and delete old ImageSummarizer implementation
32fcf17 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27 HenryL27 requested a review from bohou-aryn January 30, 2025 22:44
@HenryL27
fix filter type signature
e443147 
Signed-off-by: Henry Lindeman <[email protected]>
@HenryL27 HenryL27 merged commit 0ebf836 into main Jan 30, 2025
13 of 15 checks passed
@HenryL27 HenryL27 deleted the hml-llm-unify branch January 30, 2025 23:31
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@bohou-aryn bohou-aryn bohou-aryn approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@HenryL27 @bohou-aryn