search

langchain-ai / langchain

🦜🔗 Build context-aware reasoning applications
https://python.langchain.com
MIT License
95.4k stars 15.48k forks source link

query_constructor throws OutputParserException is query is null #15914

Closed JanHorcicka closed 7 months ago

JanHorcicka commented 10 months ago

Checked other resources

Example Code

See description.

Description

I am using SelfQueryRetriever. For a response JSON that contains null query, for example:

json
    {
        "query": null,
        "filter": ...
    }

The output parser throws OutputParserException at line 51.

OutputParserException('Parsing text\njson\n{\n "query": null,\n "filter": "eq(\\"kategorie\\", \\"Pravo\\")"\n}\n\n raised following error:\nobject of type \'NoneType\' has no len()')Traceback (most recent call last):

File "/home/MetaExponential/.local/lib/python3.10/site-packages/langchain/chains/query_constructor/base.py", line 51, in parse if len(parsed["query"]) == 0:

System Info

absl-py==2.0.0 ai21==1.2.8 aioboto3==12.0.0 aiobotocore==2.7.0 aiohttp==3.8.4 aioitertools==0.11.0 aiosignal==1.3.1 altgraph @ file:///AppleInternal/Library/BuildRoots/9dd5efe2-7fad-11ee-b588-aa530c46a9ea/Library/Caches/com.apple.xbs/Sources/python3/altgraph-0.17.2-py2.py3-none-any.whl annotated-types==0.6.0 annoy==1.17.3 antlr4-python3-runtime==4.9.3 anyio==3.7.1 argilla==1.7.0 astunparse==1.6.3 async-generator==1.10 async-timeout==4.0.2 attrs==23.1.0 Babel==2.12.1 backoff==2.2.1 bcrypt==4.0.1 beautifulsoup4==4.12.2 blinker==1.6.2 boto3==1.28.64 botocore==1.31.64 build==0.10.0 CacheControl==0.12.11 cachetools==5.3.1 camel-converter==3.1.0 certifi==2022.12.7 cffi==1.15.1 cfgv==3.3.1 chardet==5.2.0 charset-normalizer==3.1.0 Chroma==0.2.0 chroma-hnswlib==0.7.3 chromadb==0.4.13 cleo==2.0.1 click==8.1.7 clickhouse-connect==0.6.18 CoffeeScript==2.0.3 cohere==4.31 coloredlogs==15.0.1 commonmark==0.9.1 contourpy==1.0.7 crashtest==0.4.1 cryptography==40.0.2 cssselect==1.2.0 cycler==0.11.0 dataclasses-json==0.5.7 datasets==2.12.0 decorator==5.1.1 Deprecated==1.2.13 deprecation==2.1.0 dill==0.3.7 distlib==0.3.6 distro==1.8.0 dnspython==2.3.0 docutils==0.19 duckdb==0.7.1 dulwich==0.21.5 effdet==0.3.0 elastic-transport==8.10.0 elasticsearch==7.13.4 et-xmlfile==1.1.0 exceptiongroup==1.1.1 facebook-sdk==3.1.0 facebooktoken==0.0.1 faiss-cpu==1.7.4 fastapi==0.103.2 fastavro==1.8.2 feedfinder2==0.0.4 feedparser==6.0.11 filelock==3.12.0 Flask==2.3.2 Flask-Cors==4.0.0 Flask-Limiter==3.4.1 Flask-Mail==0.9.1 flatbuffers==23.5.26 fonttools==4.39.4 frozenlist==1.3.3 fsspec==2023.6.0 future @ file:///AppleInternal/Library/BuildRoots/9dd5efe2-7fad-11ee-b588-aa530c46a9ea/Library/Caches/com.apple.xbs/Sources/python3/future-0.18.2-py3-none-any.whl fuzzywuzzy==0.18.0 gast==0.5.4 google-ai-generativelanguage==0.4.0 google-api-core==2.12.0 google-auth==2.23.3 google-auth-oauthlib==1.0.0 google-cloud-aiplatform==1.38.1 google-cloud-bigquery==3.12.0 google-cloud-core==2.3.3 google-cloud-resource-manager==1.10.4 google-cloud-storage==2.12.0 google-crc32c==1.5.0 google-generativeai==0.3.2 google-pasta==0.2.0 google-resumable-media==2.6.0 googleapis-common-protos==1.56.4 grpc-gateway-protoc-gen-openapiv2==0.1.0 grpc-google-iam-v1==0.12.6 grpcio==1.59.0 grpcio-status==1.59.0 grpcio-tools==1.59.0 h11==0.14.0 h2==4.1.0 h5py==3.10.0 hnswlib==0.7.0 hpack==4.0.0 html5lib==1.1 httpcore==0.16.3 httptools==0.5.0 httpx==0.23.3 huggingface-hub==0.14.1 humanfriendly==10.0 humbug==0.3.2 hyperframe==6.0.1 identify==2.5.23 idna==3.4 importlib-metadata==6.6.0 importlib-resources==5.12.0 iniconfig==2.0.0 install==1.3.5 installer==0.7.0 iopath==0.1.10 itsdangerous==2.1.2 jaraco.classes==3.2.3 jieba3k==0.35.1 Jinja2==3.1.2 jmespath==1.0.1 joblib==1.2.0 jq==1.6.0 jsonpatch==1.33 jsonpointer==2.4 jsonschema==4.17.3 jwt==1.3.1 keras==2.14.0 keyring==23.13.1 kiwisolver==1.4.4 lancedb==0.3.2 langchain==0.1.0 langchain-community==0.0.11 langchain-core==0.1.9 langchain-google-genai==0.0.5 langsmith==0.0.77 lark==1.1.7 layoutparser==0.3.4 Levenshtein==0.23.0 libclang==16.0.6 libdeeplake==0.0.84 limits==3.5.0 llama-cpp-python==0.1.39 lockfile==0.12.2 loguru==0.7.0 lxml==4.9.2 lz4==4.3.2 macholib @ file:///AppleInternal/Library/BuildRoots/9dd5efe2-7fad-11ee-b588-aa530c46a9ea/Library/Caches/com.apple.xbs/Sources/python3/macholib-1.15.2-py2.py3-none-any.whl Mako==1.2.4 Markdown==3.4.3 markdown2==2.4.8 MarkupSafe==2.1.2 marshmallow==3.19.0 marshmallow-enum==1.5.1 matplotlib==3.7.1 meilisearch==0.28.4 ml-dtypes==0.2.0 monotonic==1.6 more-itertools==9.1.0 mpmath==1.3.0 msg-parser==1.2.0 msgpack==1.0.5 multidict==6.0.4 multiprocess==0.70.15 mypy-extensions==1.0.0 nest-asyncio==1.5.8 networkx==3.1 newspaper3k==0.2.8 nltk==3.8.1 nodeenv==1.7.0 numexpr==2.8.4 numpy==1.26.1 oauthlib==3.2.2 olefile==0.46 omegaconf==2.3.0 onnxruntime==1.14.1 openai==1.3.5 openapi-schema-pydantic==1.2.4 opencv-python==4.7.0.72 openpyxl==3.1.2 opt-einsum==3.3.0 ordered-set==4.1.0 outcome==1.2.0 overrides==7.4.0 packaging==23.2 pandas==1.5.3 pathos==0.3.1 pdf2image==1.16.3 pdfminer.six==20221105 pdfplumber==0.9.0 pexpect==4.8.0 Pillow==9.5.0 pinecone-client==2.2.4 pkginfo==1.9.6 platformdirs==2.6.2 Plim==1.0.0 pluggy==1.3.0 poetry==1.4.2 poetry-core==1.5.2 poetry-plugin-export==1.3.1 poppler-utils==0.1.0 portalocker==2.7.0 posthog==3.0.1 pox==0.3.3 ppft==1.7.6.7 pre-commit==3.2.2 proto-plus==1.22.3 protobuf==4.24.4 ptyprocess==0.7.0 pulsar-client==3.3.0 py==1.11.0 pyarrow==12.0.0 pyasn1==0.5.0 pyasn1-modules==0.3.0 pycocotools==2.0.6 pycparser==2.21 pydantic==2.4.2 pydantic_core==2.10.1 PyExecJS==1.5.1 pyfb==0.6.0 Pygments==2.15.1 PyJWT==2.7.0 pylance==0.8.7 PyMuPDF==1.22.3 pypandoc==1.11 pyparsing==3.0.9 pypdf==3.8.1 PyPDF2==3.0.1 PyPika==0.48.9 pyproject_hooks==1.0.0 pyrsistent==0.19.3 pyScss==1.4.0 PySocks==1.7.1 pytesseract==0.3.10 pytest==7.4.4 python-dateutil==2.8.2 python-docx==0.8.11 python-dotenv==1.0.0 python-Levenshtein==0.23.0 python-magic==0.4.27 python-multipart==0.0.6 python-pptx==0.6.21 pytz==2023.3 PyYAML==6.0 qdrant-client==1.6.4 rank-bm25==0.2.2 rapidfuzz==3.4.0 ratelimiter==1.2.0.post0 readability-lxml==0.8.1 redis==5.0.1 regex==2023.3.23 requests==2.31.0 requests-file==1.5.1 requests-oauthlib==1.3.1 requests-toolbelt==0.10.1 responses==0.18.0 retry==0.9.2 rfc3986==1.5.0 rich==13.0.1 rsa==4.9 s3transfer==0.7.0 safetensors==0.3.1 scikit-learn==1.2.2 scipy==1.10.1 selenium==4.9.1 semver==3.0.2 sentence-transformers==2.2.2 sentencepiece==0.1.98 sgmllib3k==1.0.0 shapely==2.0.2 shellingham==1.5.0.post1 simplejson==3.19.1 six @ file:///AppleInternal/Library/BuildRoots/9dd5efe2-7fad-11ee-b588-aa530c46a9ea/Library/Caches/com.apple.xbs/Sources/python3/six-1.15.0-py2.py3-none-any.whl snakeviz==2.2.0 sniffio==1.3.0 sortedcontainers==2.4.0 soupsieve==2.5 SQLAlchemy==2.0.16 sqlean.py==0.21.8.4 starlette==0.27.0 stylus==0.1.2 sympy==1.11.1 tenacity==8.2.2 tensorboard==2.14.1 tensorboard-data-server==0.7.2 tensorflow==2.14.0 tensorflow-estimator==2.14.0 tensorflow-io-gcs-filesystem==0.34.0 tensorflow-macos==2.14.0 termcolor==2.3.0 threadpoolctl==3.1.0 tiktoken==0.4.0 timm==0.9.1 tinysegmenter==0.3 tldextract==5.1.1 tokenizers==0.13.3 tomli==2.0.1 tomlkit==0.11.8 torch==2.1.0 torchvision==0.15.1 tornado==6.2 tqdm==4.65.0 transformers==4.28.1 trio==0.22.0 trio-websocket==0.10.3 trove-classifiers==2023.5.2 typer==0.9.0 typing-inspect==0.8.0 typing_extensions==4.8.0 tzdata==2023.3 unstructured==0.6.6 unstructured-inference==0.4.4 urllib3==1.26.15 uvicorn==0.22.0 uvloop==0.17.0 virtualenv==20.21.1 Wand==0.6.11 watchfiles==0.19.0 webencodings==0.5.1 websockets==11.0.2 Werkzeug==2.3.6 wrapt==1.14.1 wsproto==1.2.0 xattr==0.10.1 XlsxWriter==3.1.0 xxhash==3.2.0 yarl==1.9.2 zipp==3.15.0 zstandard==0.21.0

Related Components

dosubot[bot] commented 10 months ago

🤖

Hey there, @JanHorcicka! Good to see you back in the LangChain repository. Let's dive into this.

The OutputParserException you're encountering when the response JSON contains a null query is likely due to the way the output parser in the LangChain library is handling the response. The output parser expects a ChatGeneration object and certain keys in the additional_kwargs of the message object and the function_call object. If these expectations are not met, an OutputParserException is raised.

Here's a brief explanation of the possible causes:

  1. The output parser is expecting a ChatGeneration object, but it's receiving a different type. This is checked in the parse_result method of both OutputFunctionsParser and JsonOutputFunctionsParser classes. If the generation object is not an instance of ChatGeneration, an OutputParserException is raised.

  2. The function_call key is not present in the additional_kwargs of the message object. This is checked in the parse_result method of both OutputFunctionsParser and JsonOutputFunctionsParser classes. If the function_call key is not found, an OutputParserException is raised.

  3. The arguments key is not present in the function_call object or the JSON parsing of the arguments fails. This is checked in the parse_result method of the JsonOutputFunctionsParser class. If the arguments key is not found or the JSON parsing fails, an OutputParserException is raised.

To resolve this issue, ensure that the generation object is of type ChatGeneration, the function_call key is present in the additional_kwargs of the message object, and the arguments key is present in the function_call object and its value is a valid JSON string.

You can find more details in the source code of the LangChain library, specifically in the libs/langchain/langchain/output_parsers/openai_functions.py file.

As for the SelfQueryRetriever class, it is a retriever that uses a vector store and a language model to generate vector store queries. It is a subclass of the BaseRetriever class and provides functionalities for retrieving documents relevant to a query, initializing from a language model, and more. You can find more details in the libs/langchain/langchain/retrievers/self_query/base.py file.

I hope this helps! If you have any more questions or need further clarification, feel free to ask.

-Dosu

Sources

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.