You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Alexander Hoyle 42b892c21b Avoid IntegrityError for SQLiteCache updates (#1286) ... While using a `SQLiteCache`, if there are duplicate `(prompt, llm, idx)` tuples passed to [`update_cache()`](c5dd491a21/langchain/llms/base.py (L39)), then an `IntegrityError` is thrown. This can happen when there are duplicated prompts within the same batch. This PR changes the SQLAlchemy `session.add()` to a `session.merge()` in `cache.py`, [following the solution from this SO thread](https://stackoverflow.com/questions/10322514/dealing-with-duplicate-primary-keys-on-insert-in-sqlalchemy-declarative-style). I believe this fixes #983, but not entirely sure since that also involves async Here's a minimal example of the error: ```python from pathlib import Path import langchain from langchain.cache import SQLiteCache llm = langchain.OpenAI(model_name="text-ada-001", openai_api_key=Path("/.openai_api_key").read_text().strip()) langchain.llm_cache = SQLiteCache("test_cache.db") llm.generate(['a'] * 5) ``` ``` > IntegrityError: (sqlite3.IntegrityError) UNIQUE constraint failed: full_llm_cache.prompt, full_llm_cache.llm, full_llm_cache.idx [SQL: INSERT INTO full_llm_cache (prompt, llm, idx, response) VALUES (?, ?, ?, ?)] [parameters: ('a', "[('_type', 'openai'), ('best_of', 1), ('frequency_penalty', 0), ('logit_bias', {}), ('max_tokens', 256), ('model_name', 'text-ada-001'), ('n', 1), ('presence_penalty', 0), ('request_timeout', None), ('stop', None), ('temperature', 0.7), ('top_p', 1)]", 0, '\n\nA is for air.\n\nA is for atmosphere.')] (Background on this error at: https://sqlalche.me/e/14/gkpj) ``` After the change, we now have the following ```python class Output: def __init__(self, text): self.text = text # make dummy data cache = SQLiteCache("test_cache_2.db") cache.update(prompt="prompt_0", llm_string="llm_0", return_val=[Output("text_0")]) cache.engine.execute("SELECT * FROM full_llm_cache").fetchall() # output > [('prompt_0', 'llm_0', 0, 'text_0')] ``` ```python # update data, before change this would have thrown an `IntegrityError` cache.update(prompt="prompt_0", llm_string="llm_0", return_val=[Output("text_0_new")]) cache.engine.execute("SELECT * FROM full_llm_cache").fetchall() # output > [('prompt_0', 'llm_0', 0, 'text_0_new')] ```		1 year ago
..
agents	searx: remove duplicate param (#1219)	1 year ago
callbacks	rfc: callback changes (#1165)	1 year ago
chains	Harrison/source docs (#1275)	1 year ago
docstore	Harrison/wiki update (#622)	1 year ago
document_loaders	add CoNLL-U document loader (#1297)	1 year ago
embeddings	Harrison/cohere params (#1278)	1 year ago
evaluation	Refactor some loops into list comprehensions (#1185)	1 year ago
graphs	catch networkx error (#1201)	1 year ago
indexes	Harrion/kg (#1016)	1 year ago
llms	Harrison/banana fix (#1311)	1 year ago
prompts	ruff ruff (#1203)	1 year ago
tools	add ifttt tool (#1244)	1 year ago
utilities	Harrison/errors (#1276)	1 year ago
vectorstores	Harrison/add documents (#1197)	1 year ago
__init__.py	Add Writer, Banana, Modal, StochasticAI (#1270)	1 year ago
cache.py	Avoid IntegrityError for SQLiteCache updates (#1286)	1 year ago
docker-compose.yaml	add tracing support to langchain (#741)	1 year ago
example_generator.py	Harrison/improve cache (#368)	1 year ago
formatting.py	initial commit	2 years ago
input.py	Add asyncio support for LLM (OpenAI), Chain (LLMChain, LLMMathChain), and Agent (#841)	1 year ago
model_laboratory.py	Harrison/improve cache (#368)	1 year ago
py.typed	Add py.typed marker to package (#121)	2 years ago
python.py	Harrison/tools exp (#372)	1 year ago
requests.py	LLMRequestsChain (#267)	2 years ago
schema.py	add tracing support to langchain (#741)	1 year ago
serpapi.py	move serpapi wrapper (#1199)	1 year ago
server.py	add tracing support to langchain (#741)	1 year ago
sql_database.py	fix sqlite internal tables breaking table_info (#1224)	1 year ago
text_splitter.py	fix bug with length function (#1257)	1 year ago
utils.py	Harrison/bing wrapper (#656)	1 year ago