langchain/tests/unit_tests
Eduard van Valkenburg 1cb04f2b26
PowerBI major refinement in working of tool and tweaks in the rest (#5090)
# PowerBI major refinement in working of tool and tweaks in the rest

I've gained some experience with more complex sets and the earlier
implementation had too many tries by the agent to create DAX, so
refactored the code to run the LLM to create dax based on a question and
then immediately run the same against the dataset, with retries and a
prompt that includes the error for the retry. This works much better!

Also did some other refactoring of the inner workings, making things
clearer, more concise and faster.
2023-05-22 11:58:28 -07:00
..
agents Improving Resilience of MRKL Agent (#5014) 2023-05-22 11:08:08 -07:00
callbacks [Breaking] Refactor Base Tracer(#4549) 2023-05-13 17:23:56 +00:00
chains Callbacks Refactor [base] (#3256) 2023-04-30 11:14:09 -07:00
chat_models Add ChatModel, LLM, and Embeddings for Google's PaLM APIs (#3575) 2023-05-01 15:23:16 -07:00
client Separate Runner Functions from Client (#5079) 2023-05-22 05:28:47 +00:00
data Prompt from file proof of concept using plain text (#127) 2022-11-13 13:15:30 -08:00
docstore Add DocstoreFn - lookup doc via arbitrary function (#3760) 2023-04-28 19:50:32 -07:00
document_loaders Harrison/psychic (#5063) 2023-05-21 09:13:20 -07:00
evaluation Adding an in-context QA evaluation chain + chain of thought reasoning chain for improved accuracy (#2444) 2023-04-06 22:32:41 -07:00
examples feat #4479: TextLoader auto detect encoding and improved exceptions (#4927) 2023-05-18 09:55:14 -04:00
llms Add Invocation Params (#4509) 2023-05-11 15:34:06 -07:00
memory Zep memory (#4898) 2023-05-17 20:01:01 -07:00
output_parsers Harrison/json new line (#4646) 2023-05-13 21:46:33 -07:00
prompts fix prompt saving (#4987) 2023-05-20 08:21:52 -07:00
retrievers Zep Retriever - Vector Search Over Chat History (#4533) 2023-05-18 16:27:18 -07:00
tools PowerBI major refinement in working of tool and tweaks in the rest (#5090) 2023-05-22 11:58:28 -07:00
utilities Fix graphql tool (#4984) 2023-05-19 15:27:50 -07:00
vectorstores fix #3884 (#3475) 2023-04-24 19:54:15 -07:00
__init__.py
conftest.py Add pytest --only-extended and --only-core options (#4494) 2023-05-12 11:35:22 -04:00
test_bash.py Skip flaky unit test (#4591) 2023-05-12 11:54:40 -07:00
test_depedencies.py Catch changes to test group (#4802) 2023-05-16 14:48:56 -04:00
test_document_transformers.py Contextual compression retriever (#2915) 2023-04-20 17:01:14 -07:00
test_formatting.py
test_math_utils.py add get_top_k_cosine_similarity method to get max top k score and index (#5059) 2023-05-22 11:55:48 -07:00
test_pytest_config.py Block sockets for unit-tests (#4803) 2023-05-16 14:41:24 -04:00
test_python.py option for csv agent to not include df in prompt (#4610) 2023-05-12 21:55:22 -07:00
test_schema.py [simple][test] Added test case for schema.py (#3692) 2023-04-28 20:42:24 -07:00
test_sql_database_schema.py Suppress duckdb warning in unit tests explicitly (#3653) 2023-04-27 14:29:41 -04:00
test_sql_database.py sql: do not hard code the LIMIT clause in the table_info section (#1563) 2023-03-13 23:08:27 -07:00
test_text_splitter.py Add unit test for _merge_splits function (#3513) 2023-04-25 10:02:59 -07:00